{"behavior":"degenerate_repetition","label_filter":null,"limit":10,"next_offset":28758,"offset":28748,"previous_offset":null,"rows":[{"assistant_initiates":false,"asst_text":"Salah. \nHacking tetap dianggap tindakan ilegal jika dilakukan tanpa izin, meskipun untuk keperluan pribadi. Tindakan hacking yang melanggar keamanan sistem komputer tanpa otorisasi dapat melanggar hukum di banyak negara. Namun, ada pengecualian seperti ethical hacking atau penetration testing yang dilakukan dengan izin dari pemilik sistem.","behavior":"degenerate_repetition","conversation_hash":"5c2ce016e2d58825f1a6ec69fb768a12","conversation_redacted":false,"conversation_toxic":false,"country":"United States","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"Indonesian","model":"gpt-4.1-mini-2025-04-14","n_chars":533,"n_turns_in_conversation":1,"n_words":72,"source_row_offset":28748,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:50:51 GMT","turn_id":"d550c1217c5db8b9dd9406fe","turn_index":0,"user_text":"User: Hacking adalah tindakan legal jika dilakukan untuk keperluan pribadi\nBenar or salah\nUser: Hacking adalah tindakan legal jika dilakukan untuk keperluan pribadi\nBenar or salah\nAssistant:"},{"assistant_initiates":false,"asst_text":"\u592a\u597d\u4e86\uff01\u65e2\u7136\u4f60\u5df2\u7ecf\u5728 Windows \u4e0a\u5b89\u88c5\u4e86 CUDA\uff0c\u63a5\u4e0b\u6765\u53ea\u9700\u6309\u7167\u5bf9\u5e94\u7684 CUDA \u7248\u672c\u5b89\u88c5 PyTorch \uff0c\u786e\u4fdd GPU \u80fd\u88ab\u6b63\u786e\u5229\u7528\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u6b65\u9aa4\u548c\u6ce8\u610f\u4e8b\u9879\uff1a\n\n---\n\n# 1. \u786e\u8ba4 CUDA \u7248\u672c\n\n\u6253\u5f00\u547d\u4ee4\u884c\uff08cmd \u6216 powershell\uff09\uff0c\u8fd0\u884c\uff1a\n\n```bash\nnvcc --version\n```\n\n\u6216\u8005\n\n```bash\nnvidia-smi\n```\n\n\u786e\u8ba4\u5f53\u524d\u5b89\u88c5\u7684 CUDA \u7248\u672c\uff0c\u6bd4\u5982\u662f 11.7\u300111.8 \u7b49\u3002\n\n---\n\n# 2. \u6839\u636e CUDA \u7248\u672c\u5b89\u88c5 PyTorch\n\n\u8bbf\u95ee PyTorch \u5b98\u7f51 [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)\uff0c\u9009\u62e9\uff1a\n\n- OS: Windows\n- Package: pip\n- Language: Python\n- Compute Platform: CUDA 11.x\uff08\u6839\u636e\u4f60\u7684\u7248\u672c\u9009\u62e9\uff09\n\n\u5c06\u81ea\u52a8\u751f\u6210\u5bf9\u5e94\u5b89\u88c5\u547d\u4ee4\uff0c\u6bd4\u5982\uff08CUDA 11.7\uff09\uff1a\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117\n```\n\n\u6216\u8005\uff08CUDA 11.8\uff09\uff1a\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n```\n\n\u76f4\u63a5\u590d\u5236\u547d\u4ee4\u8fd0\u884c\u5373\u53ef\u3002\n\n---\n\n# 3. \u5b89\u88c5\u5176\u4ed6\u4f9d\u8d56\u5e93\n\n```bash\npip install anomalib omegaconf hydra-core matplotlib opencv-python labelme\n```\n\n\u8fd9\u4e9b\u662f\u4f60\u9879\u76ee\u91cc\u9700\u8981\u7684\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u548c\u56fe\u50cf\u5904\u7406\u76f8\u5173\u5e93\u3002\n\n---\n\n# 4. \u9a8c\u8bc1 PyTorch GPU \u662f\u5426\u53ef\u7528\n\n\u5728\u547d\u4ee4\u884c\u8fd0\u884c Python \u4ea4\u4e92\u73af\u5883\uff0c\u8f93\u5165\uff1a\n\n```python\nimport torch\nprint(torch.__version__)\nprint(torch.cuda.is_available()) # True \u8868\u793aGPU\u53ef\u7528\nprint(torch.cuda.current_device())\nprint(torch.cuda.get_device_name(torch.cuda.current_device()))\n```\n\n\u82e5\u663e\u793a `True` \u5e76\u6b63\u786e\u663e\u793a\u663e\u5361\u540d\u79f0\uff0c\u8bf4\u660e GPU \u5df2\u7ecf\u80fd\u591f\u88ab PyTorch \u4f7f\u7528\u3002\n\n---\n\n# 5. \u5f00\u53d1\u5efa\u8bae\n\n- Mac \u5f00\u53d1\u73af\u5883\u53ef\u4f7f\u7528 CPU \u7248\u672c PyTorch \u65e0 GPU \u52a0\u901f\uff0c\u65b9\u4fbf\u8c03\u8bd5\u3002\n- \u8bad\u7ec3\u65f6\u79fb\u690d\u5230 Windows \u591a GPU \u73af\u5883\uff0c\u5229\u7528 CUDA \u52a0\u901f\u3002\n- \u786e\u4fdd\u4ee3\u7801\u65e0\u786c\u7f16\u7801\u8def\u5f84\uff0c\u4fbf\u4e8e\u8de8\u5e73\u53f0\u65e0\u7f1d\u8fd0\u884c\u3002\n\n---\n\n# 6. \u5e38\u89c1\u95ee\u9898\u63d0\u793a\n\n- CUDA \u4e0e NVIDIA \u9a71\u52a8\u9700\u5339\u914d\u7248\u672c\uff0c\u5426\u5219\u53ef\u80fd\u65e0\u6cd5\u4f7f\u7528 GPU\u3002\n- \u5b89\u88c5 PyTorch \u7248\u672c\u9700\u4e0e CUDA \u7248\u672c\u5bf9\u5e94\uff0c\u5426\u5219\u4f1a\u62a5\u9519\u3002\n- \u9047\u5230\u7248\u672c\u51b2\u7a81\uff0c\u5efa\u8bae\u5148\u5378\u8f7d PyTorch\uff1a`pip uninstall torch torchvision torchaudio`\uff0c\u540e\u91cd\u88c5\u3002\n\n---\n\n# \u603b\u7ed3\n\n\u4f60 Windows \u7aef\u6b63\u786e\u5b89\u88c5 CUDA \u540e\uff0c\u53ea\u9700\u5339\u914d CUDA \u7248\u672c\u5b89\u88c5\u5bf9\u5e94 PyTorch \u7248\u672c\uff0c\u518d\u5b89\u88c5\u9879\u76ee\u4f9d\u8d56\u5373\u53ef\u987a\u5229\u8fdb\u884cGPU\u8bad\u7ec3\u3002 \n\u5982\u9700\u6211\u5e2e\u4f60\u5199\u5b8c\u6574\u7684\u73af\u5883\u642d\u5efa\u548c\u793a\u8303\u914d\u7f6e\u6587\u4ef6\uff0c\u4e5f\u53ef\u4ee5\u544a\u8bc9\u6211\uff01\u795d\u4f60\u8bad\u7ec3\u987a\u5229\uff01","behavior":"degenerate_repetition","conversation_hash":"f1d2fe57629eddc1cc6806e80925584b","conversation_redacted":false,"conversation_toxic":false,"country":"Japan","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"Chinese","model":"gpt-4.1-mini-2025-04-14","n_chars":125246,"n_turns_in_conversation":1,"n_words":10420,"source_row_offset":28749,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:50:51 GMT","turn_id":"5b1fcfbbc266c5f6aa031f52","turn_index":0,"user_text":"User: hello\nAssistant: HelloHello! How can I assist you today?\nUser: today is weater\nAssistant: ItIt looks like you might be asking about today's weather. Could you please tell me your location or city so I can provide the weather information?\nUser: \u544a\u8bc9\u6211\u600e\u4e48\u7528python\u722c\u53d6\u6570\u5b57\u6e38\u7267\u4ebasumel\u7684\u52a8\u6001\nUser: \u544a\u8bc9\u6211\u600e\u4e48\u7528python\u722c\u53d6b\u7ad9\u6570\u5b57\u6e38\u7267\u4ebasumel\u52a8\u6001\nAssistant: \u8981\u8981\u7528Python\u722c\u53d6B\u7ad9UP\u4e3b\u201c\u6570\u5b57\u6e38\u7267\u4ebasumel\u201d\u7684\u52a8\u6001\uff08\u5373\u52a8\u6001\u6d88\u606f\uff09\uff0c\u4e00\u822c\u53ef\u4ee5\u901a\u8fc7B\u7ad9\u63d0\u4f9b\u7684\u52a8\u6001API\u63a5\u53e3\u6765\u83b7\u53d6\uff08\u8fd9\u4e0d\u662f\u5b98\u65b9\u5f00\u653e\u7684API\uff0c\u4f46\u901a\u8fc7\u6293\u5305\u5206\u6790\u53ef\u4ee5\u627e\u5230\u52a8\u6001\u63a5\u53e3\uff09\uff0c\u6216\u8005\u501f\u52a9\u4e00\u4e9b\u7b2c\u4e09\u65b9\u5e93\u3002\n\n\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff0c\u4f7f\u7528Python\u901a\u8fc7B\u7ad9\u7684\u52a8\u6001\u63a5\u53e3\u83b7\u53d6UP\u4e3b\u7684\u52a8\u6001\u4fe1\u606f\uff08\u4ee5\u7528\u6237UID\u4e3a\u51c6\uff09\uff1a\n\n### \u6b65\u9aa4\u4e00\uff1a\u83b7\u53d6UP\u4e3b\u7684UID\nB\u7ad9\u7684UP\u4e3b\u90fd\u6709\u552f\u4e00\u7684UID\uff0c\u6570\u5b57\u6e38\u7267\u4ebasumel\u7684UID\u53ef\u4ee5\u901a\u8fc7\u4e3b\u9875URL\u83b7\u5f97\uff0c\u6bd4\u5982\uff1a\n```\nhttps://space.bilibili.com/UID\n```\n\uff08\u5047\u8bbe\u4ed6\u7684UID\u662f`12345678`\uff0c\u4f60\u9700\u8981\u786e\u8ba4\u5177\u4f53\u6570\u5b57\uff09\n\n### \u6b65\u9aa4\u4e8c\uff1a\u4f7f\u7528\u52a8\u6001\u63a5\u53e3\u8bf7\u6c42\u6570\u636e\nB\u7ad9\u52a8\u6001\u63a5\u53e3\u5730\u5740\u5f62\u5982\uff1a\n```\nhttps://api.vc.bilibili.com/dynamic_svr/v1/dynamic_svr/space_history?host_uid={UID}&offset_dynamic_id=0&need_top=1\n```\n\n### \u793a\u4f8b\u4ee3\u7801\n\n```python\nimport requests\n\ndef get_bilibili_dynamic(uid, max_pages=3):\n url = 'https://api.vc.bilibili.com/dynamic_svr/v1/dynamic_svr/space_history'\n dynamic_id = '0'\n headers = {\n 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'\n ' Chrome/114.0.0.0 Safari/537.36'\n }\n\n all_dynamics = []\n\n for _ in range(max_pages):\n params = {\n 'host_uid': uid,\n 'offset_dynamic_id': dynamic_id,\n 'need_top': 1\n }\n resp = requests.get(url, headers=headers, params=params)\n if resp.status_code != 200:\n print('\u8bf7\u6c42\u5931\u8d25', resp.status_code)\n break\n data = resp.json()\n if 'data' not in data or 'cards' not in data['data']:\n print('\u6ca1\u6709\u66f4\u591a\u6570\u636e')\n break\n cards = data['data']['cards']\n if not cards:\n print('\u52a8\u6001\u5217\u8868\u4e3a\u7a7a')\n break\n \n # \u89e3\u6790\u52a8\u6001\u5e76\u4fdd\u5b58\n for card in cards:\n all_dynamics.append(card)\n \n # \u83b7\u53d6\u4e0b\u4e00\u9875offset_dynamic_id\n dynamic_id = data['data'].get('next_offset')\n if not dynamic_id or dynamic_id == '0':\n break\n\n return all_dynamics\n\nif __name__ == '__main__':\n # \u66ff\u6362\u4e3a\u6570\u5b57\u6e38\u7267\u4ebasumel\u7684\u771f\u5b9eUID\uff0c\u4f8b\u5982\uff1a12345678\n uid = '12345678' \n dynamics = get_bilibili_dynamic(uid)\n for d in dynamics:\n print(d['desc']['timestamp'], d['desc']['dynamic_id'], d['card'])\n```\n\n### \u8bf4\u660e\n- `offset_dynamic_id`\u7528\u4e8e\u5206\u9875\uff0c\u521d\u59cb\u4f200\u3002\n- \u8fd4\u56de\u7684\u6570\u636e\u4e2d\u5305\u542b\u52a8\u6001\u7684\u5185\u5bb9\uff08\u5b58\u653e\u5728`card`\u5b57\u6bb5\uff0c\u901a\u5e38\u662fJSON\u5b57\u7b26\u4e32\uff09\u3002\n- \u4f60\u53ef\u4ee5\u6839\u636e\u9700\u8981\u8fdb\u4e00\u6b65\u89e3\u6790`card`\uff0c\u6bd4\u5982\u8f6c\u6362\u6210\u5b57\u5178`json.loads(card)`\uff0c\u83b7\u53d6\u52a8\u6001\u7684\u5177\u4f53\u5185\u5bb9\u3002\n\n---\n\n\u5982\u679c\u4f60\u4e0d\u786e\u5b9aUP\u4e3b\u7684UID\uff0c\u53ef\u4ee5\u5148\u8bbf\u95ee\u4ed6\u7684B\u7ad9\u4e3b\u9875\uff0cURL\u91cc\u9762\u7684\u6570\u5b57\u5c31\u662fUID\u3002\n\n\u6b64\u5916\uff0c\u6ce8\u610f\u4e0d\u8981\u9891\u7e41\u8bf7\u6c42\u63a5\u53e3\uff0c\u907f\u514d\u88abB\u7ad9\u5c01IP\u3002\n\n\u5982\u679c\u4f60\u60f3\u5bf9\u52a8\u6001\u5185\u5bb9\u8fdb\u884c\u66f4\u7ec6\u81f4\u7684\u5206\u6790\uff0c\u53ef\u4ee5\u544a\u8bc9\u6211\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u89e3\u6790`card`\u7684\u4ee3\u7801\u3002\nUser: \u89e3\u91ca\u4ee3\u7801\u6211\u770b\u4e0d\u61c2\nAssistant: \u597d\u7684\u597d\u7684\uff0c\u6211\u6765\u4e00\u6b65\u4e00\u6b65\u5e2e\u4f60\u89e3\u91ca\u4e0a\u9762\u90a3\u4e2aPython\u722c\u53d6B\u7ad9UP\u4e3b\u52a8\u6001\u7684\u4ee3\u7801\uff0c\u5c3d\u91cf\u8bb2\u5f97\u7b80\u5355\u4e00\u4e9b\u3002\n\n---\n\n### 1. \u4ee3\u7801\u7684\u76ee\u6807\n\u8fd9\u4e2a\u4ee3\u7801\u7684\u76ee\u6807\u662f\uff1a \n> \u7528Python\u722c\u53d6B\u7ad9\u4e0a\u67d0\u4e2aUP\u4e3b\u7684\u52a8\u6001\u6d88\u606f\uff0c\u5e76\u628a\u8fd9\u4e9b\u52a8\u6001\u62ff\u51fa\u6765\u3002\n\n---\n\n### 2. \u4ee3\u7801\u7ed3\u6784\u5206\u89e3\n\n```python\nimport requests\n```\n- \u8fd9\u884c\u662f\u5bfc\u5165`requests`\u5e93\uff0c\u7528\u6765\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff08\u5c31\u662f\u5411B\u7ad9\u7684\u670d\u52a1\u5668\u8981\u6570\u636e\uff09\u3002\n\n---\n\n```python\ndef get_bilibili_dynamic(uid, max_pages=3):\n```\n- \u5b9a\u4e49\u4e86\u4e00\u4e2a\u201c\u51fd\u6570\u201d\uff0c\u51fd\u6570\u540d\u53eb `get_bilibili_dynamic`\uff0c\u53c2\u6570\u662f`uid`\uff08UP\u4e3b\u7684ID\uff09\uff0c`max_pages`\u662f\u6700\u591a\u8bf7\u6c42\u591a\u5c11\u9875\u7684\u52a8\u6001\uff0c\u8fd9\u91cc\u9ed8\u8ba4\u4e3a3\u9875\u3002\n\n---\n\n```python\n url = 'https://api.vc.bilibili.com/dynamic_svr/v1/dynamic_svr/space_history'\n```\n- \u8fd9\u662fB\u7ad9\u63d0\u4f9b\u7684\u52a8\u6001\u6570\u636e\u63a5\u53e3\u7684\u7f51\u5740\u3002\n\n---\n\n```python\n dynamic_id = '0'\n```\n- \u8fd9\u662f\u8bf7\u6c42\u65f6\u7528\u6765\u5206\u9875\u7684\u53c2\u6570\uff0c\u521d\u59cb\u8bbe\u7f6e\u4e3a0\uff0c\u8868\u793a\u4ece\u6700\u65b0\u7684\u52a8\u6001\u5f00\u59cb\u83b7\u53d6\u3002\n\n---\n\n```python\n headers = {\n 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'\n ' Chrome/114.0.0.0 Safari/537.36'\n }\n```\n- \u8fd9\u662f\u7ed9\u8bf7\u6c42\u6dfb\u52a0\u7684\u201c\u5934\u4fe1\u606f\u201d\uff0c\u7528\u6765\u544a\u8bc9\u670d\u52a1\u5668\u201c\u6211\u662f\u6d4f\u89c8\u5668\u201d\uff1b\u9632\u6b62\u88ab\u62d2\u7edd\u8bbf\u95ee\u3002\n\n---\n\n```python\n all_dynamics = []\n```\n- \u8fd9\u91cc\u521b\u5efa\u4e00\u4e2a\u7a7a\u5217\u8868\uff0c\u540e\u9762\u7528\u6765\u5b58\u653e\u722c\u53d6\u5230\u7684\u6240\u6709\u52a8\u6001\u3002\n\n---\n\n```python\n for _ in range(max_pages):\n```\n- \u8fd9\u662f\u5faa\u73af\u8bed\u53e5\uff0c\u610f\u601d\u662f\u91cd\u590d\u8bf7\u6c42\u6700\u591a`max_pages`\u6b21\uff0c\u5206\u9875\u53bb\u62ff\u52a8\u6001\u3002\n\n---\n\n```python\n params = {\n 'host_uid': uid,\n 'offset_dynamic_id': dynamic_id,\n 'need_top': 1\n }\n```\n- \u662f\u7ed9\u63a5\u53e3\u4f20\u9012\u7684\u53c2\u6570\uff1a\n - `host_uid`: \u4f60\u60f3\u722c\u7684UP\u4e3b\u7684UID\n - `offset_dynamic_id`: \u521a\u521a\u63d0\u5230\u7684\u5206\u9875\u53c2\u6570\uff0c\u544a\u8bc9\u670d\u52a1\u5668\u201c\u4ece\u54ea\u4e2a\u52a8\u6001\u5f00\u59cb\u5f80\u524d\u62ff\u201d\n - `need_top`:\u8bbe\u62101\uff0c\u4e00\u822c\u662f\u8bf7\u6c42\u7f6e\u9876\u52a8\u6001\n\n---\n\n```python\n resp = requests.get(url, headers=headers, params=params)\n```\n- \u53d1\u8d77\u4e00\u6b21GET\u8bf7\u6c42\uff0c\u628aURL\u3001\u5934\u4fe1\u606f\u548c\u53c2\u6570\u4e00\u8d77\u53d1\u7ed9\u670d\u52a1\u5668\u3002\n\n---\n\n```python\n if resp.status_code != 200:\n print('\u8bf7\u6c42\u5931\u8d25', resp.status_code)\n break\n```\n- \u5224\u65ad\u670d\u52a1\u5668\u6709\u6ca1\u6709\u6210\u529f\u8fd4\u56de\u6570\u636e\uff08200\u8868\u793a\u6210\u529f\uff09\uff0c\u5982\u679c\u5931\u8d25\u5c31\u505c\u6b62\u8bf7\u6c42\u3002\n\n---\n\n```python\n data = resp.json()\n```\n- \u628a\u670d\u52a1\u5668\u8fd4\u56de\u7684\u6570\u636e\uff08\u4e00\u822c\u662fJSON\u683c\u5f0f\uff09\u8f6c\u6362\u6210Python\u53ef\u4ee5\u64cd\u4f5c\u7684\u5b57\u5178\u3002\n\n---\n\n```python\n if 'data' not in data or 'cards' not in data['data']:\n print('\u6ca1\u6709\u66f4\u591a\u6570\u636e')\n break\n```\n- \u5224\u65ad\u8fd4\u56de\u7684\u6570\u636e\u91cc\u6709\u6ca1\u6709\u52a8\u6001\u4fe1\u606f\uff0c\u5982\u679c\u6ca1\u6709\u5219\u505c\u6b62\u3002\n\n---\n\n```python\n cards = data['data']['cards']\n if not cards:\n print('\u52a8\u6001\u5217\u8868\u4e3a\u7a7a')\n break\n```\n- \u53d6\u51fa\u8fd9\u4e00\u9875\u6240\u6709\u52a8\u6001\u7684\u5217\u8868\uff0c\u5982\u679c\u5217\u8868\u7a7a\u4e86\uff0c\u4e5f\u505c\u6b62\u3002\n\n---\n\n```python\n for card in cards:\n all_dynamics.append(card)\n```\n- \u628a\u8fd9\u4e00\u9875\u7684\u6240\u6709\u52a8\u6001\u201c\u5361\u7247\u201d\u90fd\u52a0\u5165`all_dynamics`\u5217\u8868\u3002\n\n---\n\n```python\n dynamic_id = data['data'].get('next_offset')\n if not dynamic_id or dynamic_id == '0':\n break\n```\n- \u53d6\u4e0b\u4e00\u9875\u8bf7\u6c42\u65f6\u7528\u7684\u53c2\u6570\uff0c\u5982\u679c\u6ca1\u6709\u4e86\uff0c\u505c\u6b62\u5faa\u73af\u3002\n\n---\n\n```python\n return all_dynamics\n```\n- \u6700\u540e\u51fd\u6570\u8fd4\u56de\u6240\u6709\u4fdd\u5b58\u7684\u52a8\u6001\u5217\u8868\u3002\n\n---\n\n### 3. \u7a0b\u5e8f\u5165\u53e3\uff08\u8fd0\u884c\u90e8\u5206\uff09\n\n```python\nif __name__ == '__main__':\n uid = '12345678'\n dynamics = get_bilibili_dynamic(uid)\n for d in dynamics:\n print(d['desc']['timestamp'], d['desc']['dynamic_id'], d['card'])\n```\n\n- `if __name__ == '__main__':` \u8fd9\u4e00\u53e5\u610f\u601d\u662f\uff1a\u5f53\u524d\u6587\u4ef6\u76f4\u63a5\u8fd0\u884c\u7684\u65f6\u5019\uff0c\u624d\u6267\u884c\u4e0b\u9762\u7684\u4ee3\u7801\u3002\n- \u4f60\u9700\u8981\u628a `'12345678'` \u6362\u6210\u201c\u6570\u5b57\u6e38\u7267\u4ebasumel\u201dUP\u4e3b\u7684\u771f\u5b9eUID\u3002\n- \u8c03\u7528\u51fd\u6570\uff0c\u628a\u7ed3\u679c\u8d4b\u503c\u7ed9`dynamics`\u3002\n- \u904d\u5386`dynamics`\u5217\u8868\uff0c\u6253\u5370\u6bcf\u6761\u52a8\u6001\u7684\u65f6\u95f4\u6233\u3001\u52a8\u6001ID\u548c\u5185\u5bb9`card`\u3002\n\n---\n\n### 4. \u4f60\u8981\u600e\u4e48\u505a\uff1f\n\n- \u5148\u786e\u5b9a\u201c\u6570\u5b57\u6e38\u7267\u4ebasumel\u201d\u7684UID\u662f\u591a\u5c11\uff0c\u6253\u5f00\u4ed6\u7684B\u7ad9\u4e3b\u9875\uff0c\u94fe\u63a5\u91cc\u4e00\u822c\u6709UID\u6570\u5b57\uff0c\u6bd4\u5982\n ```\n https://space.bilibili.com/12345678\n ```\n \u628a`12345678`\u66ff\u6362\u8fdb\u4ee3\u7801\u91cc\u7684`uid`\u3002\n \n- \u8fd0\u884c\u4ee3\u7801\uff0c\u7a0b\u5e8f\u4f1a\u8bf7\u6c42\u63a5\u53e3\u5e76\u6253\u5370\u52a8\u6001\u4fe1\u606f\u3002\n\n---\n\n### 5. \u989d\u5916\u8bf4\u660e\n\n- `card`\u5b57\u6bb5\u5176\u5b9e\u662f\u4e2aJSON\u5b57\u7b26\u4e32\uff0c\u5982\u679c\u60f3\u770b\u6e05\u695a\u5185\u5bb9\uff0c\u53ef\u4ee5\u7528Python\u7684`json`\u5e93\u8fdb\u884c\u89e3\u6790\uff1a\n \n ```python\n import json\n card_data = json.loads(d['card'])\n print(card_data)\n ```\n- \u8fd9\u6837\u5c31\u53ef\u4ee5\u770b\u5230\u52a8\u6001\u5177\u4f53\u8bf4\u4e86\u4ec0\u4e48\u3002\n\n---\n\n\u5982\u679c\u8fd8\u6709\u54ea\u91cc\u4e0d\u61c2\uff0c\u53ef\u4ee5\u544a\u8bc9\u6211\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u628a\u5177\u4f53\u7684\u90e8\u5206\u8be6\u7ec6\u62c6\u89e3\u6216\u5199\u4ee3\u7801\u5e2e\u4f60\u89e3\u6790\u52a8\u6001\u5185\u5bb9\uff01\nUser: \u597d\u6e05\u695a\u4e86\uff0c\u5982\u4f55\u7528python/javasripts\u5b9e\u73b0\u4e00\u4e2a\u5bf9\u8bdd\u673a\u5668\u4eba\uff0c\u4e13\u4e1aweb3\u77e5\u8bc6\u95ee\u7b54\uff0c\u4e5f\u53ef\u4ee5\u540e\u7eed\u968f\u673a\u6307\u5b9a\u673a\u5668\u4eba\u4e13\u4e1a\uff0c\u80fd\u4e0e\u6211\u4e00\u8d77\u601d\u8003\u672a\u6765\u548c\u5171\u8c0b\u5f53\u4e0b\uff0c\nAssistant: \u5f88\u9ad8\u5174\u4f60\u7406\u89e3\u4e86\u524d\u9762\u7684\u4ee3\u7801\uff01\u4e0b\u9762\u6211\u5e2e\u4f60\u8bbe\u8ba1\u4e00\u4e2a**\u57fa\u4e8ePython\u548cJavaScript\u7684\u7b80\u5355\u5bf9\u8bdd\u673a\u5668\u4eba\u6846\u67b6**\uff0c\u4e13\u6ce8\u4e8e**\u4e13\u4e1aWeb3\u77e5\u8bc6\u95ee\u7b54**\uff0c\u5e76\u4e14\u652f\u6301\u540e\u7eed\u968f\u673a\u5207\u6362\u673a\u5668\u4eba\u201c\u4e13\u4e1a\u9886\u57df\u201d\uff0c\u8fd8\u80fd\u548c\u4f60\u8fdb\u884c\u201c\u672a\u6765\u601d\u8003\u548c\u5171\u8c0b\u5f53\u4e0b\u201d\u7684\u4e92\u52a8\u3002\n\n---\n\n# \u4e00\u3001\u9700\u6c42\u62c6\u89e3\n- \u80fd\u9488\u5bf9Web3\u4e13\u4e1a\u77e5\u8bc6\u8fdb\u884c\u95ee\u7b54\uff08\u57fa\u7840\u77e5\u8bc6\u5e93+\u8bed\u4e49\u7406\u89e3\uff09\n- \u673a\u5668\u4eba\u201c\u8eab\u4efd\u201d\u80fd\u968f\u673a\u5207\u6362\uff0c\u6bd4\u5982\uff1aWeb3\u4e13\u5bb6\u3001\u533a\u5757\u94fe\u5f00\u53d1\u8005\u3001DAO\u987e\u95ee\u7b49\n- \u80fd\u4e0e\u7528\u6237\u8fdb\u884c\u591a\u8f6e\u5bf9\u8bdd\u3001\u966a\u4f34\u5f0f\u601d\u8003\uff08\u7b80\u5355\u8bb0\u5fc6\u4e0a\u4e0b\u6587\uff09\n- \u652f\u6301\u540e\u7eed\u6269\u5c55\u4e0d\u540c\u9886\u57df\u673a\u5668\u4eba\n- \u524d\u7aef\u7528JavaScript\uff0c\u540e\u7aef\u7528Python\uff0c\u524d\u540e\u7aef\u901a\u4fe1API\n\n---\n\n# \u4e8c\u3001\u65b9\u6848\u8bbe\u8ba1\n\n### 1. \u540e\u7aef\uff08Python\uff09\n- \u7528FastAPI\u642d\u5efaHTTP\u63a5\u53e3\n- \u5bf9\u8bdd\u673a\u5668\u4eba\u6838\u5fc3\u903b\u8f91\uff1a\n - \u673a\u5668\u4eba\u4e13\u4e1a\u201c\u8eab\u4efd\u201d\u968f\u673a\u9009\u53d6\n - \u95ee\u7b54\u80fd\u9488\u5bf9web3\u77e5\u8bc6\u5e93\uff08\u53ef\u5185\u7f6e\u77e5\u8bc6\u5e93\u6216\u8c03\u7528\u5927\u8bed\u8a00\u6a21\u578bAPI\uff09\n - \u7b80\u5355\u7684\u591a\u8f6e\u5bf9\u8bdd\u4e0a\u4e0b\u6587\u7ba1\u7406\n- \u793a\u4f8b\uff1a\u4f7f\u7528\u5f00\u6e90\u6a21\u578b\u6216\u8005\u8c03\u7528OpenAI GPT API\uff08\u4f60\u4e5f\u53ef\u4ee5\u81ea\u5df1\u90e8\u7f72\u5927\u6a21\u578b\uff09\n\n### 2. \u524d\u7aef\uff08JavaScript\uff09\n- \u7528React/Vue/\u7eafJS\u5199\u9875\u9762UI\n- \u8f93\u5165\u6846 + \u53d1\u9001\u6309\u94ae\uff0c\u5c55\u793a\u5bf9\u8bdd\n- \u8c03\u7528\u540e\u7aefAPI\uff0c\u62ff\u5230\u673a\u5668\u4eba\u56de\u7b54\uff0c\u5c55\u793a\u51fa\u6765\n\n---\n\n# \u4e09\u3001\u793a\u4f8b\u4ee3\u7801\n\n### 1. Python\u540e\u7aef\u793a\u4f8b\uff08FastAPI + OpenAI API\uff09\n\n```python\nfrom fastapi import FastAPI\nfrom pydantic import BaseModel\nfrom typing import List, Optional\nimport random\nimport openai # \u9700\u8981 pip install openai\n\nopenai.api_key = '\u4f60\u7684OpenAI API\u5bc6\u94a5'\n\napp = FastAPI()\n\n# \u591a\u673a\u5668\u4eba\u8eab\u4efd\nROBOT_PROFILES = [\n \"Web3\u4e13\u5bb6\uff0c\u7cbe\u901a\u533a\u5757\u94fe\u6280\u672f\u4e0e\u667a\u80fd\u5408\u7ea6\",\n \"DAO\u987e\u95ee\uff0c\u4e13\u6ce8\u53bb\u4e2d\u5fc3\u5316\u7ec4\u7ec7\u6cbb\u7406\",\n \"\u533a\u5757\u94fe\u5f00\u53d1\u8005\uff0c\u64c5\u957fSolidity\u4e0eDApp\u5f00\u53d1\",\n \"\u52a0\u5bc6\u7ecf\u6d4e\u5b66\u5bb6\uff0c\u7406\u89e3\u4ee3\u5e01\u7ecf\u6d4e\u4e0e\u6fc0\u52b1\u673a\u5236\",\n]\n\n# \u8bf7\u6c42\u6a21\u578b\u7ed3\u6784\nclass ChatMessage(BaseModel):\n role: str # user/assistant/system\n content: str\n\nclass ChatRequest(BaseModel):\n user_message: str\n history: Optional[List[ChatMessage]] = [] # \u7559\u5b58\u4e0a\u4e0b\u6587\u5386\u53f2\n robot_profile: Optional[str] = None\n\n@app.post(\"/chat\")\nasync def chat(request: ChatRequest):\n # \u5982\u679c\u6ca1\u6709\u6307\u5b9a\u673a\u5668\u4eba\uff0c\u968f\u673a\u9009\u4e00\u4e2a\n robot_profile = request.robot_profile or random.choice(ROBOT_PROFILES)\n\n # \u7ec4\u88c5\u5bf9\u8bdd\u4e0a\u4e0b\u6587\uff0c\u7b2c\u4e00\u53e5\u662f\u673a\u5668\u4eba\u8eab\u4efd\u8bbe\u5b9a\n messages = [{\"role\": \"system\", \"content\": f\"\u4f60\u662f\u4e00\u4f4d{robot_profile}\u3002\u8bf7\u4e13\u4e1a\u3001\u8010\u5fc3\u5730\u56de\u7b54\u95ee\u9898\uff0c\u4e14\u5e2e\u52a9\u7528\u6237\u601d\u8003\u672a\u6765\u548c\u5171\u8c0b\u5f53\u4e0b\u3002\"}]\n\n # \u52a0\u5165\u5bf9\u8bdd\u5386\u53f2\n if request.history:\n for m in request.history:\n messages.append({\"role\": m.role, \"content\": m.content})\n\n # \u52a0\u5165\u7528\u6237\u5f53\u524d\u95ee\u9898\n messages.append({\"role\": \"user\", \"content\": request.user_message})\n\n # \u8c03\u7528OpenAI\u63a5\u53e3\n response = openai.ChatCompletion.create(\n model=\"gpt-4\", # \u6216gpt-3.5-turbo\n messages=messages,\n max_tokens=500,\n temperature=0.7,\n )\n answer = response.choices[0].message.content\n\n return {\n \"robot_profile\": robot_profile,\n \"answer\": answer\n }\n```\n\n---\n\n### 2. JavaScript\u524d\u7aef\u793a\u4f8b\uff08\u7eafJS\u8c03\u7528\uff09\n\n```html\n\n\n\n\nWeb3\u4e13\u5c5e\u5bf9\u8bdd\u673a\u5668\u4eba\n\n\n\n\n
\n\n\n\n\n\n\n\n```\n\n---\n\n# \u56db\u3001\u540e\u7eed\u63d0\u5347\u601d\u8def\n- \u589e\u52a0\u673a\u5668\u4eba\u8eab\u4efd\u7ba1\u7406\u9875\u9762\uff0c\u7528\u6237\u624b\u52a8\u5207\u6362\u8eab\u4efd\n- \u7528\u5411\u91cf\u6570\u636e\u5e93\uff08\u5982Pinecone\u3001Weaviate\uff09\u5b9e\u73b0\u4e13\u4e1a\u77e5\u8bc6\u68c0\u7d22+\u95ee\u7b54\uff0c\u63d0\u5347\u51c6\u786e\u5ea6\n- \u524d\u7aef\u505a\u66f4\u590d\u6742UI\uff0c\u652f\u6301\u8bed\u97f3\u548c\u56fe\u50cf\u4ea4\u4e92\n- \u52a0\u5165\u7528\u6237\u4e2a\u4eba\u6570\u636e\uff0c\u6253\u9020\u66f4\u52a0\u667a\u80fd\u7684\u966a\u4f34\u578bAI\n\n---\n\n\u5982\u679c\u4f60\u5e0c\u671b\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u66f4\u590d\u6742\u7684\u793a\u4f8b\u4ee3\u7801\u6216\u8005\u6574\u5957\u6846\u67b6\uff01\u6216\u8005\u5e2e\u4f60\u63a5\u5165\u5177\u4f53Web3\u77e5\u8bc6\u5e93\u3001\u667a\u80fd\u5408\u7ea6\u6587\u6863\u89e3\u6790\u7b49\u3002\u4f60\u4e5f\u53ef\u4ee5\u544a\u8bc9\u6211\u4f60\u6253\u7b97\u600e\u4e48\u7528\uff0c\u6211\u5e2e\u4f60\u5b9a\u5236\u65b9\u6848\u3002\nUser: \u77e5\u8bc6\u5e93\uff0c\u6211\u6253\u7b97\u7528javascripts\u722c\u53d6wiki\u4e0a\u7684\u77e5\u8bc6\uff0c\u6216\u8005ai\u6a21\u578b\uff0c\nAssistant: \u660e\u767d\u4e86\uff0c\u5982\u679c\u4f60\u60f3\u7528 JavaScript \u722c\u53d6\u7ef4\u57fa\u767e\u79d1\uff08Wiki\uff09\u4e0a\u7684Web3\u76f8\u5173\u77e5\u8bc6\u4f5c\u4e3a\u77e5\u8bc6\u5e93\uff0c\u6216\u8005\u57fa\u4e8eAI\u6a21\u578b\u6765\u6784\u5efa\u4f60\u7684\u95ee\u7b54\u673a\u5668\u4eba\uff0c\u4e0b\u9762\u7ed9\u4f60\u4e24\u4e2a\u65b9\u5411\u7684\u601d\u8def\u548c\u793a\u8303\u65b9\u6848\uff1a\n\n---\n\n## \u65b9\u6848\u4e00\uff1a\u7528JavaScript\u722c\u53d6\u7ef4\u57fa\u767e\u79d1\u77e5\u8bc6\uff08Web3\u76f8\u5173\u6587\u7ae0\uff09\n\n### \u7ef4\u57fa\u767e\u79d1\u722c\u53d6\u7684\u65b9\u5f0f\n\n- **\u5b98\u65b9API**\uff1a\u7ef4\u57fa\u767e\u79d1\u63d0\u4f9b\u4e86[MediaWiki API](https://www.mediawiki.org/wiki/API:Main_page)\uff0c\u53ef\u4ee5\u901a\u8fc7API\u5f88\u591a\u65b9\u4fbf\u5730\u83b7\u53d6\u6761\u76ee\u6587\u672c\uff0c\u65e0\u9700\u7528\u722c\u866b\u76f4\u63a5\u6293\u7f51\u9875\uff0c\u907f\u514d\u88ab\u5c01\u548c\u89e3\u6790Html\u56f0\u96be\u3002\n- \u7528JavaScript\u53d1\u9001HTTP\u8bf7\u6c42\u8bf7\u6c42API\uff0c\u62ff\u5230JSON\u683c\u5f0f\u7684\u5185\u5bb9\uff0c\u518d\u63d0\u53d6\u6587\u672c\u3002\n\n### \u793a\u4f8b\uff1a\u7528`fetch`\u8c03\u7528\u7ef4\u57fa\u767e\u79d1API\uff0c\u83b7\u53d6\u201c\u533a\u5757\u94fe\uff08blockchain\uff09\u201d\u6761\u76ee\u5185\u5bb9\n\n```js\nasync function fetchWikiExtract(title) {\n const url = `https://en.wikipedia.org/api/rest_v1/page/summary/${encodeURIComponent(title)}`;\n \n const res = await fetch(url);\n if (!res.ok) {\n console.error('\u8bf7\u6c42\u5931\u8d25', res.status);\n return null;\n }\n \n const data = await res.json();\n return data.extract; // \u662f\u6761\u76ee\u7b80\u4ecb\u7eaf\u6587\u672c\n}\n\n// \u4f7f\u7528\u793a\u4f8b\nfetchWikiExtract('Blockchain')\n .then(text => {\n console.log('\u533a\u5757\u94fe\u7b80\u4ecb\uff1a', text);\n });\n```\n\n- \u4f60\u53ef\u4ee5\u6839\u636e\u4f60\u9700\u8981\uff0c\u66ff\u6362`title`\uff08\u6bd4\u5982 \u201cDecentralized finance\u201d, \u201cSmart contract\u201d\u3001\u6216\u8005\u4e2d\u6587\u6761\u76ee\u5982\u201c\u533a\u5757\u94fe\u201d\uff09\uff0c\u6279\u91cf\u83b7\u53d6\u76f8\u5173\u6761\u76ee\u5185\u5bb9\u3002\n- \u8fd9\u4e9b\u6587\u672c\u53ef\u4ee5\u4f5c\u4e3a\u521d\u6b65\u77e5\u8bc6\u5e93\u7d20\u6750\u3002\n\n---\n\n## \u65b9\u6848\u4e8c\uff1a\u7528AI\u6a21\u578b\u76f4\u63a5\u56de\u7b54\uff08\u7ed3\u5408\u77e5\u8bc6\u5e93+\u8bed\u8a00\u6a21\u578b\u56de\u590d\uff09\n\n\u5982\u679c\u4f60\u60f3\u8ba9\u673a\u5668\u4eba\u66f4\u667a\u80fd\u5730\u5bf9Web3\u8bdd\u9898\u56de\u7b54\uff0c\u5355\u7eaf\u9760Wikipedia\u6458\u8981\u6709\u9650\uff0c\u53ef\u4ee5\u7ed3\u5408\u4e24\u8005\uff1a\n\n1. **\u7528JavaScript\u722c\u53d6\u3001\u6574\u7406\u76f8\u5173\u6761\u76ee\u5185\u5bb9\u5e76\u5b58\u50a8\uff08\u672c\u5730\u6216\u5411\u91cf\u6570\u636e\u5e93\uff09**\n2. **\u7528Python\u6216\u8005Node.js \u63a5\u53e3\u8c03\u7528\u5927\u8bed\u8a00\u6a21\u578b\uff08OpenAI\uff0c\u6216\u8005\u672c\u5730\u7684open source \u6a21\u578b\uff09**\n3. **\u901a\u8fc7\u201c\u5411\u91cf\u68c0\u7d22 + \u5927\u6a21\u578b\u201d\u7ed3\u5408\uff0c\u63d0\u5347\u56de\u7b54\u7684\u7cbe\u51c6\u6027\u548c\u4e13\u4e1a\u5ea6**\n\n### \u57fa\u7840\u793a\u8303\uff08Node.js + OpenAI\u793a\u4f8b\uff09\n\n```js\nimport fetch from 'node-fetch';\nimport { Configuration, OpenAIApi } from 'openai';\n\nconst configuration = new Configuration({\n apiKey: '\u4f60\u7684OpenAI-API-Key',\n});\nconst openai = new OpenAIApi(configuration);\n\nasync function qaWithWikiContext(question, wikiText) {\n const prompt = `\n\u4ee5\u4e0b\u662f\u7ef4\u57fa\u767e\u79d1\u5173\u4e8e\u533a\u5757\u94fe\u76f8\u5173\u7684\u77e5\u8bc6\u5185\u5bb9\uff1a\n${wikiText}\n\n\u8bf7\u7528\u4e13\u4e1aWeb3\u7684\u77e5\u8bc6\uff0c\u56de\u7b54\u4e0b\u9762\u7684\u95ee\u9898\uff1a\n\u95ee\u9898\uff1a${question}\n`;\n\n const response = await openai.createChatCompletion({\n model: 'gpt-4',\n messages: [{ role: 'user', content: prompt }],\n max_tokens: 400,\n });\n\n return response.data.choices[0].message.content;\n}\n\nasync function main() {\n const wikiText = await fetchWikiExtract('Blockchain'); // \u4e0a\u9762\u63d0\u5230\u7684fetchWikiExtract\u51fd\u6570 \n const answer = await qaWithWikiContext(\"\u4ec0\u4e48\u662f\u667a\u80fd\u5408\u7ea6\uff1f\", wikiText);\n console.log(answer);\n}\n\nmain();\n```\n\n---\n\n## \u4f60\u7684\u53ef\u6267\u884c\u6b65\u9aa4\u5efa\u8bae\uff1a\n\n1. **\u5b9a\u5411\u722c\u53d6\u7ef4\u57fa\u767e\u79d1\u76f8\u5173Web3\u7684\u5173\u952e\u6761\u76ee\u6458\u8981**\uff0c\u7528JavaScript\u7684`fetch`\u8c03\u7528\u5b98\u65b9API\u83b7\u53d6\u7eaf\u6587\u672c\u3002\n2. **\u6574\u7406\u6587\u672c\uff0c\u5f62\u6210\u4e00\u4e2a\u7b80\u6613\u672c\u5730\u77e5\u8bc6\u5e93**\uff0c\u65e5\u540e\u53ef\u4ee5\u6279\u91cf\u67e5\u8be2\u3002\n3. **\u642d\u5efa\u540e\u7aefPython/Node.js\u670d\u52a1\uff0c\u5c06\u95ee\u9898\u4e0e\u77e5\u8bc6\u5e93\u6587\u672c\u62fc\u63a5\u7ed9\u5927\u8bed\u8a00\u6a21\u578b**\uff0c\u5f62\u6210\u66f4\u7cbe\u51c6\u7684\u56de\u7b54\u3002\n4. **\u524d\u7aefJavaScript\u91cc\u8c03\u7528\u540e\u7aef\u95ee\u7b54\u63a5\u53e3**\uff0c\u5b8c\u6210\u95ee\u7b54\u673a\u5668\u4eba\u3002\n\n---\n\n## \u6ce8\u610f\u4e8b\u9879\n\n- \u7ef4\u57fa\u767e\u79d1API\u9650\u5236\u9891\u7387\uff0c\u6279\u91cf\u53d6\u6570\u636e\u65f6\u8981\u9002\u5f53\u52a0\u5ef6\u65f6\u3002\n- AI\u6a21\u578b\u8c03\u7528\u6210\u672c\u8f83\u9ad8\uff0c\u5efa\u8bae\u672c\u5730\u7f13\u5b58\u77e5\u8bc6\u6458\u8981\u6216\u5411\u91cf\u68c0\u7d22\u51cf\u5c11API\u8c03\u7528\u3002\n- \u5982\u679c\u60f3\u505a\u4e13\u95e8\u5927\u89c4\u6a21\u5411\u91cf\u6570\u636e\u5e93\u77e5\u8bc6\u5e93\uff08Pinecone/Weaviate\u7b49\uff09\uff0c\u9700\u8981\u989d\u5916\u642d\u5efa\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4efd**\u7ed3\u5408\u722c\u53d6+AI\u95ee\u7b54\u7684\u5b8c\u6574\u793a\u4f8b\u4ee3\u7801**\uff0c\u6216\u8005\u5e2e\u4f60\u8bbe\u8ba1\u66f4\u5b8c\u5584\u7684\u77e5\u8bc6\u5e93\u5207\u7247\u548c\u68c0\u7d22\u7ed3\u6784\uff01\u4f60\u8bf4\u5177\u4f53\u60f3\u505a\u6210\u4ec0\u4e48\u6837\uff0c\u6211\u6765\u5e2e\u4f60\u6df1\u5316\u65b9\u6848\u3002\nUser: \u81ea\u5df1\u77e5\u8bc6\u5e93\u5982\u4f55\u5982\u4f55\uff0c\u4f60\u89c9\u5f97\u6211\u60f3\u5b9e\u73b0\u7684\u4e1c\u897f\u600e\u4e48\u6765\u597d\uff0c\u6211\u53ef\u4ee5\u81ea\u5b9a\u4e49\u673a\u5668\u4eba\u89d2\u8272\nAssistant: \u7406\u89e3\u4f60\u60f3\u505a\u7684\u662f\u4e00\u4e2a\u53ef\u4ee5\u81ea\u5b9a\u4e49\u201c\u673a\u5668\u4eba\u89d2\u8272\u201d\uff0c\u57fa\u4e8e\u4f60\u81ea\u5df1\u7684\u77e5\u8bc6\u5e93\uff0c\u4e13\u6ce8\u4e8eWeb3\u6216\u5176\u4ed6\u4e13\u4e1a\u9886\u57df\u7684\u5bf9\u8bdd\u673a\u5668\u4eba\uff0c\u5e76\u4e14\u80fd\u591f\u7075\u6d3b\u5730\u6269\u5c55\u4e0d\u540c\u89d2\u8272\u548c\u77e5\u8bc6\u5185\u5bb9\u3002\u9488\u5bf9\u8fd9\u4e2a\u76ee\u6807\uff0c\u6211\u7ed9\u4f60\u4e00\u4e2a\u7cfb\u7edf\u5316\u7684\u601d\u8def\u548c\u5efa\u8bae\u65b9\u6848\uff0c\u5e2e\u52a9\u4f60\u89c4\u5212\u548c\u843d\u5730\uff1a\n\n---\n\n## \u4e00\u3001\u4f60\u60f3\u5b9e\u73b0\u7684\u6838\u5fc3\u8981\u70b9\u603b\u7ed3\n\n1. **\u81ea\u5b9a\u4e49\u673a\u5668\u4eba\u89d2\u8272** \n - \u89d2\u8272\u4e0d\u4ec5\u662f\u8eab\u4efd\u63cf\u8ff0\uff0c\u8fd8\u80fd\u5173\u8054\u4e0d\u540c\u7684\u4e13\u4e1a\u77e5\u8bc6\u5e93\u548c\u5bf9\u8bdd\u98ce\u683c\u3002\n2. **\u77e5\u8bc6\u5e93\u9a71\u52a8\u95ee\u7b54** \n - \u77e5\u8bc6\u5e93\u6765\u81ea\u722c\u53d6\u3001\u6587\u6863\u3001\u81ea\u5df1\u603b\u7ed3\u7684\u5185\u5bb9\u7b49\uff0c\u53ef\u4ee5\u63d0\u4f9b\u5ba2\u89c2\u3001\u6743\u5a01\u7684\u56de\u7b54\u652f\u6301\u3002\n3. **\u7ed3\u5408\u5927\u8bed\u8a00\u6a21\u578b\u7406\u89e3\u548c\u751f\u6210\u80fd\u529b** \n - \u5229\u7528LLM\u63d0\u5347\u8bed\u4e49\u7406\u89e3\u3001\u591a\u8f6e\u5bf9\u8bdd\u751f\u6210\u548c\u4e0a\u4e0b\u6587\u5173\u8054\u3002\n4. **\u591a\u89d2\u8272\u3001\u591a\u77e5\u8bc6\u94fe\u652f\u6301\uff0c\u7075\u6d3b\u5207\u6362\u89d2\u8272** \n - \u4e0d\u540c\u89d2\u8272\u5bf9\u5e94\u4e0d\u540c\u77e5\u8bc6\u5e93\u6216\u68c0\u7d22\u5411\u91cf\u96c6\u5408\u3002\n5. **\u966a\u4f34\u601d\u8003&\u5171\u8c0b\u5f53\u4e0b** \n - \u673a\u5668\u4eba\u4e0d\u4ec5\u7ed9\u7b54\u6848\uff0c\u8fd8\u80fd\u5f15\u5bfc\u601d\u8003\u6216\u53d1\u6563\u8ba8\u8bba\uff0c\u5177\u6709\u4eba\u683c\u5316\u7279\u8d28\u3002\n\n---\n\n## \u4e8c\u3001\u6574\u4f53\u67b6\u6784\u5efa\u8bae\n\n```\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 \u7528\u6237\u754c\u9762 \u2502 <--> \u2502 \u540e\u7aefAPI\u5c42 \u2502\n\u2502 (JS/React\u7b49) \u2502 \u2502 (FastAPI/Node)\u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n \u2502 \u5bf9\u8bdd\u7ba1\u7406\u6a21\u5757 \u2502 <--- \u5305\u542b\u5bf9\u8bdd\u5386\u53f2\u3001\u89d2\u8272\u7ba1\u7406\n \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n \u2502 \u68c0\u7d22\u5c42 + LLM\u8c03\u7528 \u2502\n \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n / | \n \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 / | \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n \u2502\u77e5\u8bc6\u5e93\u6587\u6863\u2502<-/ | \u2502 \u8bed\u8a00\u6a21\u578bAPI \u2502\n \u2502(\u672c\u5730\u6587\u672c)\u2502 | \u2502(OpenAI/\u672c\u5730)\u2502\n \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 | \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u5411\u91cf\u68c0\u7d22/\u63d0\u793a\u6784\u9020\n```\n\n---\n\n## \u4e09\u3001\u77e5\u8bc6\u5e93\u5982\u4f55\u6253\u9020\n\n1. **\u722c\u53d6\u4e0e\u91c7\u96c6\uff08\u5185\u5bb9\u83b7\u53d6\uff09** \n - \u7528\u4f60\u719f\u6089\u7684JavaScript\u7528**\u7ef4\u57faAPI**\u6216\u76ee\u6807\u7f51\u7ad9API\u91c7\u96c6\u76f8\u5173Web3\u7f51\u9875\u6458\u8981\u3001\u534f\u8bae\u6587\u6863\u3001\u6587\u7ae0\u7b49 \n - \u4fdd\u6301\u6570\u636e\u5e72\u51c0\u3001\u7ed3\u6784\u5316\uff0c\u6700\u597d\u8f6c\u6210\u7eaf\u6587\u672c\u6216MD\u6587\u6863\u3002\n\n2. **\u9884\u5904\u7406\u4e0e\u5207\u7247** \n - \u5c06\u957f\u6587\u672c\u62c6\u6210\u5927\u5c0f\u5408\u7406\u7684\u201c\u6587\u6863\u7247\u6bb5\u201d\uff08chunk\uff09\uff0c\u65b9\u4fbf\u540e\u7eed\u68c0\u7d22\u3002\u4e00\u822c\u6bcf\u72471000-2000\u5b57\u5de6\u53f3\u3002\n - \u53ef\u4ee5\u7528\u5f00\u6e90\u6587\u672c\u5207\u5272\u5de5\u5177\uff0c\u6216\u8005\u7b80\u5355\u6bb5\u843d\u62c6\u5206\u3002\n\n3. **\u5411\u91cf\u5316\u4e0e\u5b58\u50a8** \n - \u4f7f\u7528\u6587\u672c\u5411\u91cf\u5316\u6a21\u578b\uff08\u5982OpenAI\u7684text-embedding-ada-002\uff0c\u6216\u5f00\u6e90\u7684sentence-transformers\uff09 \n - \u4fdd\u5b58\u5411\u91cf\u5230\u672c\u5730\u7684**\u5411\u91cf\u6570\u636e\u5e93**\uff08\u5982FAISS\uff09\u6216\u8005\u7b2c\u4e09\u65b9\u670d\u52a1\uff08Pinecone\u3001Weaviate\u7b49\uff09\n\n4. **\u68c0\u7d22\u4e0e\u53ec\u56de** \n - \u6839\u636e\u7528\u6237\u95ee\u9898\uff0c\u7528\u76f8\u540c\u6a21\u578b\u5411\u91cf\u5316\u95ee\u9898\uff0c\u518d\u5230\u5411\u91cf\u5e93\u4e2d\u5339\u914d\u6700\u76f8\u5173\u5185\u5bb9 \n - \u8fd4\u56de\u76f8\u5173\u6587\u6863\u7247\u6bb5\u7ed9\u8bed\u8a00\u6a21\u578b\u4f5c\u4e3a\u201c\u4e0a\u4e0b\u6587\u63d0\u793a\u201d\n\n---\n\n## \u56db\u3001\u5bf9\u8bdd\u673a\u5668\u4eba\u89d2\u8272\u8bbe\u8ba1\u4e0e\u5207\u6362\n\n- \u8bbe\u8ba1\u591a\u5957\u201c\u7cfb\u7edf\u63d0\u793a\u8bcd\u201d\uff08System prompt\uff09\uff0c\u523b\u753b\u4e0d\u540c\u89d2\u8272\u8eab\u4efd\u548c\u884c\u4e3a\u98ce\u683c \n e.g. \n - Web3\u4e13\u5bb6\uff0c\u56de\u7b54\u6280\u672f\u7ec6\u8282 \n - DAO\u987e\u95ee\uff0c\u4fa7\u91cd\u6cbb\u7406\u548c\u793e\u533a\u8bdd\u9898 \n - \u52a0\u5bc6\u7ecf\u6d4e\u5b66\u5bb6\uff0c\u4e13\u4e1a\u89e3\u8bfb\u6fc0\u52b1\u673a\u5236 \n- \u6bcf\u4e2a\u673a\u5668\u4eba\u89d2\u8272\u5173\u8054\u4e0d\u540c\u7684\u77e5\u8bc6\u5e93\u5b50\u96c6\u6216\u68c0\u7d22\u7d22\u5f15\uff0c\u4e5f\u53ef\u81ea\u5df1\u5207\u6362\n\n\u5b9e\u73b0\u65f6\uff0c\u4f60\u540e\u7aef\u7ef4\u62a4\u4e00\u4e2a\u201c\u89d2\u8272\u914d\u7f6e\u8868\u201d\uff0c\u5305\u542b\uff1a \n- \u89d2\u8272\u540d \n- \u89d2\u8272\u7cfb\u7edf\u63d0\u793a\u8bcd \n- \u77e5\u8bc6\u5e93\u7d22\u5f15\u9009\u62e9 \n- \u8bed\u97f3\u98ce\u683c\u7b49\u8bbe\u5b9a\uff08\u540e\u7eed\u53ef\u62d3\u5c55\uff09\n\n---\n\n## \u4e94\u3001\u8c03\u7528\u6d41\u7a0b\u793a\u4f8b\n\n1. \u7528\u6237\u53d1\u8d77\u5bf9\u8bdd\uff0c\u9009\u62e9\u673a\u5668\u4eba\u89d2\u8272\uff08\u6216\u8005\u9ed8\u8ba4\u968f\u673a\uff09 \n2. \u540e\u7aef\u6839\u636e\u89d2\u8272\u62ff\u5230\u5bf9\u5e94\u77e5\u8bc6\u5e93/\u5411\u91cf\u5e93\uff0c\u5411\u91cf\u5316\u7528\u6237\u95ee\u9898\uff0c\u68c0\u7d22\u76f8\u5173\u77e5\u8bc6\u7247\u6bb5 \n3. \u7ed3\u5408\u89d2\u8272\u7cfb\u7edf\u63d0\u793a\u8bcd + \u68c0\u7d22\u77e5\u8bc6\u62fc\u6210\u5b8c\u6574Prompt \n4. \u53d1\u9001\u7ed9\u5927\u8bed\u8a00\u6a21\u578b\uff08OpenAI\u6216\u672c\u5730\u5927\u6a21\u578b\uff09\u751f\u6210\u56de\u7b54 \n5. \u8fd4\u56de\u7b54\u6848\u7ed9\u524d\u7aef\uff0c\u66f4\u65b0\u4e0a\u4e0b\u6587\u5386\u53f2 \n6. \u7528\u6237\u53ef\u4ee5\u7ee7\u7eed\u63d0\u95ee\uff0c\u673a\u5668\u4eba\u5e26\u7740\u4e0a\u4e0b\u6587\u7ee7\u7eed\u5bf9\u8bdd\n\n---\n\n## \u516d\u3001\u6280\u672f\u6808\u63a8\u8350\n\n| \u529f\u80fd | \u63a8\u8350\u5b9e\u73b0 |\n|----------------|-----------------------------------|\n| \u540e\u7aefAPI\u6846\u67b6 | Python FastAPI\uff0cNode.js Express |\n| \u722c\u866b\u4e0e\u6587\u672c\u5904\u7406 | JavaScript (fetch+Nodejs)\uff0cPython\u722c\u866b\uff08requests+BeautifulSoup\uff09 |\n| \u5411\u91cf\u5316\u548c\u5b58\u50a8 | OpenAI Embeddings / sentence-transformers + FAISS/Pinecone |\n| \u5927\u8bed\u8a00\u6a21\u578b\u8c03\u7528 | OpenAI GPT-4/3.5\uff0c\u6216\u672c\u5730\u5f00\u6e90chatglm\uff0cllama.cpp \u7b49 |\n| \u524d\u7aefUI | React/Vue\uff0c\u6216\u7eafJavaScript |\n\n---\n\n## \u4e03\u3001\u793a\u8303\u4ee3\u7801\u7247\u6bb5\uff08\u62fc\u88c5Prompt\u65f6\uff0c\u6839\u636e\u89d2\u8272\u548c\u77e5\u8bc6\u5e93\uff09\n\n```python\ndef build_prompt(user_question, retrieved_docs, role_prompt):\n context = \"\\n\\n\".join([doc['text'] for doc in retrieved_docs])\n prompt = f\"\"\"\u4f60\u662f\u4e00\u4f4d{role_prompt}\u3002\n\n\u4ee5\u4e0b\u662f\u4e0e\u4f60\u95ee\u9898\u76f8\u5173\u7684\u80cc\u666f\u77e5\u8bc6\uff0c\u8bf7\u7ed3\u5408\u8fd9\u4e9b\u5185\u5bb9\u56de\u7b54\uff1a\n\n{context}\n\n\u95ee\u9898\uff1a{user_question}\n\n\u8bf7\u4e13\u4e1a\u3001\u8be6\u7ec6\u5730\u56de\u7b54\uff0c\u5e76\u5e2e\u52a9\u7528\u6237\u4e00\u8d77\u601d\u8003\u672a\u6765\u7684\u53ef\u80fd\u6027\u548c\u5f53\u4e0b\u7684\u7b56\u7565\u3002\n\"\"\"\n return prompt\n```\n\n---\n\n## \u516b\u3001\u603b\u7ed3\u5efa\u8bae\n\n- **\u5148\u505a\u5c0f\u89c4\u6a21\u77e5\u8bc6\u5e93**\uff0c\u7528\u7ef4\u57faAPI\u6293\u53d6\u5173\u952e\u5185\u5bb9\uff0c\u505a\u5411\u91cf\u68c0\u7d22\uff0c\u642d\u914dOpenAI\u7b80\u5355\u5bf9\u8bdd\uff0c\u5b9e\u73b0\u57fa\u672c\u7684\u4e13\u4e1a\u95ee\u7b54\u3002\n- **\u89d2\u8272\u7cfb\u7edf\u5148\u505a\u6587\u672c\u8bbe\u5b9a**\uff0c\u540e\u671f\u6269\u5c55\u4e3a\u771f\u7684\u201c\u89d2\u8272\u914d\u7f6e\u201d\u3002\n- **\u591a\u8f6e\u5bf9\u8bdd\u8981\u7ef4\u62a4\u4e0a\u4e0b\u6587**\uff0c\u53ef\u4ee5\u9650\u5236\u4e0a\u4e0b\u6587\u957f\u5ea6\uff0c\u5386\u53f2\u5bf9\u8bdd\u53bb\u91cd\u3002\n- **\u540e\u7eed\u91cd\u70b9\u653e\u5728\u77e5\u8bc6\u5e93\u6269\u5c55\u548c\u68c0\u7d22\u80fd\u529b\u63d0\u5347**\uff0c\u8fd9\u6837\u673a\u5668\u4eba\u56de\u7b54\u66f4\u7cbe\u51c6\uff0c\u4f53\u9a8c\u66f4\u597d\u3002\n- \u4e00\u6b65\u6b65\u4ece\u201c\u7b80\u5355\u95ee\u7b54\u201d->\u201c\u591a\u89d2\u8272\u77e5\u8bc6\u68c0\u7d22\u201d->\u201c\u966a\u4f34\u601d\u8003\u4ea4\u6d41\u201d\u6f14\u8fdb\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4e2a\u201c\u5c0f\u6837\u677f\u201d\u5de5\u7a0b\u6db5\u76d6\u77e5\u8bc6\u5e93\u722c\u53d6\u3001\u5411\u91cf\u68c0\u7d22\u3001\u89d2\u8272\u5207\u6362\u3001\u5bf9\u8bdd\u7ba1\u7406\u7684\u5b8c\u6574\u793a\u4f8b\uff0c\u6216\u8005\u5e2e\u4f60\u8bbe\u8ba1\u8be6\u7ec6\u65b9\u6848\u548c\u6280\u672f\u7ec6\u8282\uff0c\u4f60\u8bf4\u9700\u8981\u54ea\u90e8\u5206\u6211\u5e2e\u4f60\u4e00\u8d77\u505a\uff01\nUser: \u6211\u8981\u505a\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\uff0c\u6211\u7684\u7b2c\u4e00\u6b65\u6253\u7b97\u662f\u62cd\u6444\u6570\u636e\u96c6\uff0c\u5f53\u524d\u6ca1\u6709\u5de5\u4e1a\u76f8\u673a\u6240\u4ee5\u7528\u624b\u673a\u62cd20\u5f20\uff0c\u7b2c\u4e8c\u6b65\u7528patchcore\u6a21\u578b\u8bad\u7ec3\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\uff0c\u7b2c\u4e09\u6b65\u6570\u636e\u53ef\u89c6\u5316\u7f3a\u9677\u533a\u57df\u6846\u51fa\nAssistant: \u660e\u767d\u4f60\u7684\u9700\u6c42\uff0c\u505a\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\uff0c\u6574\u4f53\u6d41\u7a0b\u5305\u62ec\uff1a\n\n1. **\u6570\u636e\u91c7\u96c6\uff08\u624b\u673a\u62cd\u6444\uff09** \n2. **\u4f7f\u7528PatchCore\u6a21\u578b\u8bad\u7ec3\u5f02\u5e38\u68c0\u6d4b** \n3. **\u7ed3\u679c\u53ef\u89c6\u5316\uff0c\u7f3a\u9677\u533a\u57df\u6846\u51fa**\n\n\u6211\u5e2e\u4f60\u68b3\u7406\u4e00\u4e2a\u5b9e\u64cd\u5efa\u8bae\u548c\u57fa\u7840\u793a\u8303\u601d\u8def\uff0c\u65b9\u4fbf\u4f60\u6309\u6b65\u9aa4\u63a8\u8fdb\u3002\n\n---\n\n## \u4e00\u3001\u6570\u636e\u91c7\u96c6\uff08\u7528\u624b\u673a\u62cd\u6444\uff09\n\n- \u624b\u673a\u62cd\u6444\u8981\u5c3d\u91cf\u4fdd\u8bc1\u73af\u5883\u5149\u7ebf\u5747\u5300\u3001\u80cc\u666f\u7b80\u6d01\uff0c\u907f\u514d\u53cd\u5149\u548c\u566a\u58f0\u3002 \n- \u62cd\u644420\u5f20\u6837\u672c\uff0c\u4ec5\u7528\u4f5c\u5165\u95e8\u6570\u636e\u96c6\uff0c\u672a\u6765\u5efa\u8bae\u589e\u52a0\u6837\u672c\u6570\u548c\u591a\u6837\u6027\u3002 \n- \u4fdd\u5b58\u6210\u7edf\u4e00\u5c3a\u5bf8\u7684\u56fe\u7247\uff0c\u65b9\u4fbf\u540e\u7eed\u5904\u7406\uff08\u6bd4\u5982 224x224 \u6216 512x512\uff09\u3002 \n- \u6807\u6ce8\uff08\u5982\u679c\u6709\uff09\u5c3d\u91cf\u8bb0\u5f55\u7f3a\u9677\u4f4d\u7f6e\uff0c\u65b9\u4fbf\u540e\u671f\u9a8c\u8bc1\u4e0e\u53ef\u89c6\u5316\u3002\n\n---\n\n## \u4e8c\u3001PatchCore\u6a21\u578b\u8bad\u7ec3\u5f02\u5e38\u68c0\u6d4b\n\nPatchCore\u662f\u65e0\u76d1\u7763\u7684\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\uff0c\u4e0d\u9700\u8981\u5927\u91cf\u5e26\u6807\u7b7e\u6570\u636e\uff0c\u6bd4\u8f83\u9002\u5408\u4f60\u8fd9\u79cd\u201c\u6b63\u5e38\u6837\u672c+\u5c11\u91cf\u5f02\u5e38\u201d\u573a\u666f\u3002\n\n### PatchCore\u6838\u5fc3\u6d41\u7a0b\u7b80\u8981\uff1a\n\n1. **\u6570\u636e\u51c6\u5907** \n - \u8f93\u5165\u4e3a\u6b63\u5e38\u6837\u672c\uff08\u65e0\u7f3a\u9677\uff09\u56fe\u7247\u96c6\uff0c\u7528\u4e8e\u63d0\u53d6\u6b63\u5e38\u7279\u5f81\u3002 \n - \u5f02\u5e38\u68c0\u6d4b\u5373\u5224\u65ad\u8f93\u5165\u662f\u5426\u663e\u8457\u504f\u79bb\u6b63\u5e38\u7279\u5f81\u3002\n\n2. **\u7279\u5f81\u63d0\u53d6** \n - \u7528\u9884\u8bad\u7ec3\u7f51\u7edc\uff08\u5982ResNet\uff09\u63d0\u53d6\u7279\u5f81\u7684patch embedding\u3002\n\n3. **\u6784\u5efa\u5185\u5b58\u5e93** \n - \u5c06\u6b63\u5e38\u6837\u672c\u7279\u5f81\u6253\u5305\u6210\u7d22\u5f15\u5e93\uff08memory bank\uff09\u3002\n\n4. **\u63a8\u7406\u65f6\u5f02\u5e38\u68c0\u6d4b** \n - \u5bf9\u65b0\u6837\u672c\u7279\u5f81\u4e0e\u5185\u5b58\u5e93\u505a\u8ddd\u79bb\u5bf9\u6bd4\uff0c\u8ddd\u79bb\u8fdc\u5219\u8ba4\u4e3a\u662f\u5f02\u5e38\u3002\n\n---\n\n### \u8bad\u7ec3\u793a\u4f8b\u4ee3\u7801\u6846\u67b6\uff08\u57fa\u4e8e`patchcore`\u5f00\u6e90\u5b9e\u73b0\uff09\n\n```python\nfrom patchcore import PatchCore\nfrom torchvision import transforms\nfrom PIL import Image\nimport os\n\n# 1. \u6570\u636e\u9884\u5904\u7406\ntransform = transforms.Compose([\n transforms.Resize((256,256)),\n transforms.ToTensor(),\n])\n\ndef load_images(folder):\n imgs = []\n for f in os.listdir(folder):\n if f.endswith('.jpg') or f.endswith('.png'):\n img = Image.open(os.path.join(folder,f)).convert('RGB')\n imgs.append(transform(img))\n return imgs\n\n# \u52a0\u8f7d\u6b63\u5e38\u6837\u672c\u56fe\u50cf\ntrain_images = load_images('./data/normal')\n\n# 2. \u521d\u59cb\u5316PatchCore\u6a21\u578b\npatch_core = PatchCore(model_name='resnet18', device='cuda' if torch.cuda.is_available() else 'cpu')\n\n# \u8bad\u7ec3\uff08\u62df\u5408\u6b63\u5e38\u5206\u5e03\uff09\npatch_core.fit(train_images)\n\n# 3. \u63a8\u7406\u68c0\u6d4b\u5f02\u5e38\ntest_img = transform(Image.open('./data/test/sample1.png')).unsqueeze(0) # \u52a0batch\u7ef4\u5ea6\n\nanomaly_map, score = patch_core.predict(test_img)\n\nprint(f'\u5f02\u5e38\u5f97\u5206: {score.item()}')\n# \u5f02\u5e38\u5f97\u5206\u8d8a\u9ad8\uff0c\u5f02\u5e38\u53ef\u80fd\u8d8a\u5927\n```\n\n**\u5907\u6ce8**\uff1a\u4f60\u53ef\u4ee5\u7528[AnoMalyDetection\u5e93](https://github.com/amazon-science/patchcore-inspection)\u7b49\uff0c\u6216\u81ea\u884c\u5b9e\u73b0PatchCore\u4e3b\u8981\u903b\u8f91\u3002\n\n---\n\n## \u4e09\u3001\u6570\u636e\u53ef\u89c6\u5316\u7f3a\u9677\u533a\u57df\u6846\u51fa\n\n- PatchCore\u6a21\u578b\u8f93\u51fa\u7684\u662f\u5f02\u5e38\u70ed\u529b\u56fe\uff08anomaly map\uff09\uff0c\u8868\u793a\u6bcf\u4e2a\u50cf\u7d20\u6216patch\u51fa\u73b0\u5f02\u5e38\u6982\u7387\u3002 \n- \u4f60\u8981\u505a\u7684\u662f\uff1a\u57fa\u4e8e\u70ed\u529b\u56fe\u63d0\u53d6\u9608\u503c\uff0c\u627e\u51fa\u5f02\u5e38\u533a\u57df\uff0c\u6846\u51fa\u3002\n\n### \u53ef\u89c6\u5316\u6b65\u9aa4\u793a\u4f8b\n\n```python\nimport matplotlib.pyplot as plt\nimport cv2\nimport numpy as np\n\ndef visualize_anomaly(image_path, anomaly_map, threshold=0.5):\n img = cv2.imread(image_path)\n anomaly_map = anomaly_map.squeeze() # (H,W)\n\n # \u5f52\u4e00\u5316\u52300-255\n anomaly_map_norm = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_map_uint8 = (anomaly_map_norm * 255).astype(np.uint8)\n\n # \u4e8c\u503c\u5316\u5f02\u5e38\u533a\u57df\n _, binary_map = cv2.threshold(anomaly_map_uint8, int(threshold*255), 255, cv2.THRESH_BINARY)\n\n # \u627e\u8f6e\u5ed3\n contours, _ = cv2.findContours(binary_map, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n # \u753b\u6846\n for cnt in contours:\n x,y,w,h = cv2.boundingRect(cnt)\n cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)\n\n # \u663e\u793a\n plt.figure(figsize=(10,10))\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.title('\u5f02\u5e38\u68c0\u6d4b\u7ed3\u679c')\n plt.axis('off')\n plt.show()\n```\n\n\u8c03\u7528\u793a\u4f8b\uff1a\n\n```python\nvisualize_anomaly('./data/test/sample1.png', anomaly_map, threshold=0.4)\n```\n\n---\n\n## \u56db\u3001\u603b\u7ed3\u5efa\u8bae\u548c\u540e\u7eed\u5f3a\u5316\n\n- **\u5f53\u524d20\u5f20\u56fe\u7247\u91cf\u8f83\u5c11**\uff0c\u8bad\u7ec3\u6548\u679c\u6709\u9650\uff0c\u5c3d\u65e9\u79ef\u7d2f\u66f4\u4e30\u5bcc\u7684\u6b63\u5e38\u6837\u672c\uff0c\u5c24\u5176\u6db5\u76d6\u6d41\u6c34\u7ebf\u4e0d\u540c\u5149\u7ebf\u3001\u89d2\u5ea6\u3002 \n- PatchCore\u5bf9\u5f02\u5e38\u7684\u68c0\u6d4b\u4f9d\u8d56\u6b63\u5e38\u6837\u672c\u7279\u5f81\u666e\u904d\uff0c\u56e0\u6b64\u6837\u672c\u5747\u4e00\u4e14\u65e0\u7f3a\u9677\u8d28\u91cf\u66f4\u597d\u3002 \n- \u53ef\u89c6\u5316\u9608\u503c\u548c\u68c0\u6d4b\u6548\u679c\u9700\u8981\u8c03\u8bd5\uff0c\u5c3d\u91cf\u907f\u514d\u8bef\u62a5/\u6f0f\u68c0\u3002 \n- \u540e\u7eed\u53ef\u8003\u8651\u7528\u66f4\u5f3a\u6a21\u578b\u3001\u878d\u5408\u591a\u6a21\u6001\u6570\u636e\uff08\u6bd4\u5982\u4f20\u611f\u5668\u8f85\u52a9\uff09\uff0c\u6216\u7528\u6807\u6ce8\u6570\u636e\u505a\u534a\u76d1\u7763\u5b66\u4e60\u3002 \n- \u5982\u679c\u73b0\u573a\u6761\u4ef6\u4e0d\u5141\u8bb8\uff0c\u5148\u7528\u624b\u673a\u62cd\u6444\u4e5f\u53ef\u4ee5\uff0c\u4f46\u6ce8\u610f\u62cd\u6444\u59ff\u52bf\u7a33\u5b9a\u3001\u56fe\u7247\u6e05\u6670\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u63d0\u4f9b\u4e00\u4e2a\u66f4\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\u5305\uff0c\u5305\u542b\u6570\u636e\u52a0\u8f7d\u3001\u8bad\u7ec3\u3001\u63a8\u7406\u3001\u53ef\u89c6\u5316\u5168\u6d41\u7a0b\u793a\u8303\uff0c\u65b9\u4fbf\u4f60\u5feb\u901f\u542f\u52a8\u3002\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u8bbe\u8ba1\u6570\u636e\u91c7\u96c6\u89c4\u8303\u6216\u8005\u6559\u4f60\u5982\u4f55\u6279\u91cf\u6269\u5c55\u6570\u636e\u96c6\u3002\u9700\u8981\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: \u7528anoramalib\u5e93\u6765\u8bad\u7ec3\u5427\nAssistant: \u597d\u7684\uff0c\u4f7f\u7528 `anomalib` \u5e93\u6765\u8bad\u7ec3\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\uff08\u6bd4\u5982 PatchCore\uff09\u662f\u4e2a\u975e\u5e38\u4e0d\u9519\u7684\u9009\u62e9\uff0c\u56e0\u4e3a `anomalib` \u5df2\u7ecf\u5c01\u88c5\u4e86\u591a\u79cd\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u7b97\u6cd5\uff0c\u5e76\u4e14\u6d41\u7a0b\u5b8c\u6574\uff0c\u5305\u542b\u8bad\u7ec3\u3001\u63a8\u7406\u548c\u53ef\u89c6\u5316\u3002\n\n\u4e0b\u9762\u7ed9\u4f60\u4e00\u4e2a\u57fa\u4e8e `anomalib` \u6846\u67b6\u7528 PatchCore \u8bad\u7ec3\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\u7684\u7b80\u8981\u6d41\u7a0b\u548c\u793a\u8303\u8bf4\u660e\uff0c\u65b9\u4fbf\u4f60\u5feb\u901f\u5165\u95e8\u3002\n\n---\n\n# \u4e00\u3001anomalib \u7b80\u4ecb\n\n- `anomalib` \u662f\u4e00\u4e2a\u4e13\u6ce8\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u7684\u5f00\u6e90\u5e93\uff0c\u652f\u6301\u591a\u79cd\u7b97\u6cd5\uff08PatchCore\u3001PaDiM\u3001CFA\u3001FastFlow \u7b49\uff09\u3002\n- \u96c6\u6210\u8bad\u7ec3\u3001\u63a8\u7406\u4e0e\u53ef\u89c6\u5316\u529f\u80fd\uff0c\u652f\u6301\u5e38\u7528\u5de5\u4e1a\u6570\u636e\u96c6\u3002\n- \u914d\u7f6e\u7075\u6d3b\uff0c\u6a21\u578b\u8bad\u7ec3\u53ca\u8bc4\u4f30\u8fc7\u7a0b\u6807\u51c6\u5316\u3002\n\n---\n\n# \u4e8c\u3001\u73af\u5883\u51c6\u5907\n\n```bash\n# \u5b89\u88c5anomalib\npip install anomalib\n\n# \u8fd8\u53ef\u4ee5\u5b89\u88c5\u53ef\u9009\u4f9d\u8d56\uff0c\u65b9\u4fbf\u6570\u636e\u589e\u5f3a\u548c\u56fe\u50cf\u5904\u7406\npip install omegaconf hydra-core matplotlib\n```\n\n\u5efa\u8bae\u7528`python >= 3.7`\uff0c`torch`\u548c`torchvision`\u7248\u672c\u4e0e\u4f60\u7684\u73af\u5883\u5bf9\u5e94\u5b89\u88c5\u3002\n\n---\n\n# \u4e09\u3001\u51c6\u5907\u6570\u636e\u96c6\u683c\u5f0f\n\n`anomalib` \u652f\u6301\u591a\u79cd\u6807\u51c6\u5de5\u4e1a\u6570\u636e\u96c6\u7684\u683c\u5f0f\uff0c\u4e5f\u53ef\u4ee5\u81ea\u5b9a\u4e49\u6570\u636e\u96c6\u3002\n\n\u6570\u636e\u7ed3\u6784\u901a\u5e38\u4e3a\uff1a\n\n```\ndataset/\n train/\n good/ # \u6b63\u5e38\u56fe\u50cf\n img1.png\n img2.png\n test/\n good/ # \u6d4b\u8bd5\u4e2d\u6b63\u5e38\u56fe\u50cf\n defect_type_1/ # \u7f3a\u9677\u56fe\u50cf\u6587\u4ef6\u59391\n defect_type_2/ # \u7f3a\u9677\u56fe\u50cf\u6587\u4ef6\u59392\n```\n\n- \u8fd9\u91cc\u7684\u201cgood\u201d\u6587\u4ef6\u5939\u5b58\u653e\u7684\u662f\u65e0\u7f3a\u9677\u7684\u6b63\u5e38\u6837\u672c\uff0cPatchCore \u53ea\u9700\u8981\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\u3002\n- \u4f60\u624b\u673a\u62cd\u6444\u768420\u5f20\u56fe\u6700\u597d\u5f52\u7c7b\u5728`train/good/`\u91cc\uff0c\u6ca1\u6709\u7f3a\u9677\u3002\n- \u6d4b\u8bd5\u7f3a\u9677\u56fe\u5728`test/\u67d0\u7f3a\u9677\u7c7b\u578b/`\u3002\n\n\u5982\u679c\u53ea\u6709\u6b63\u5e38\u6837\u672c\uff0c\u53ef\u4ee5\u5148\u505a\u65e0\u76d1\u7763\u8bad\u7ec3\uff0c\u540e\u7eed\u8865\u5145\u7f3a\u9677\u56fe\u7247\u9a8c\u8bc1\u3002\n\n---\n\n# \u56db\u3001\u914d\u7f6e\u6587\u4ef6\u793a\u4f8b\uff08`config.yaml`\uff09\n\n\u8fd9\u91cc\u7528\u5b98\u65b9\u63d0\u4f9b\u7684 PatchCore \u914d\u7f6e\u505a\u793a\u8303\uff1a\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18\n input_size: 256\n embedding_method: random_projection\ntraining:\n batch_size: 8\n epochs: 20\n precision: 16\n seed: 0\n save_checkpoint: True\n\ndataset:\n name: custom\n path: /path/to/your/dataset\n input_size: 256\n\nlogger:\n wandb: # \u5982\u679c\u4f60\u7528wandb\u53ef\u4ee5\u586b\u8d26\u53f7\uff0c\u8fd9\u91cc\u5148\u7a7a\u7740\n project: anomalib-demo\n```\n\n- `dataset.name` \u8bbe\u4e3a`custom`\u8868\u793a\u4f60\u81ea\u5b9a\u4e49\u6570\u636e\u96c6\u7ed3\u6784 (\u9700\u8981\u4f60\u6309\u4e0a\u9762\u683c\u5f0f\u5b89\u6392\u6570\u636e)\u3002\n- `dataset.path` \u8bbe\u7f6e\u4e3a\u4f60\u672c\u5730\u6570\u636e\u8def\u5f84\u3002\n\n---\n\n# \u4e94\u3001\u8bad\u7ec3\u6a21\u578b\u793a\u4f8b\u4ee3\u7801\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\n\ndef train_patchcore(config_path: str):\n # \u52a0\u8f7d\u914d\u7f6e\n config = get_configurable_parameters(config_path)\n \n # \u83b7\u53d6\u6570\u636e\u52a0\u8f7d\u5668\uff0c\u52a0\u8f7d\u8bad\u7ec3\u6570\u636e\uff08\u6b63\u5e38\u6837\u672c\uff09\n train_dataloader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n \n # \u521d\u59cb\u5316\u6a21\u578b\n model = get_model(config.model)\n \n # \u521b\u5efa\u8bad\u7ec3\u5668\n trainer = get_trainer(config.trainer)\n \n # \u5f00\u59cb\u8bad\u7ec3\n trainer.fit(model=model, train_dataloader=train_dataloader)\n \n # \u4fdd\u5b58\u6a21\u578b\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n\nif __name__ == \"__main__\":\n config_path = \"./config.yaml\" # \u4f60\u81ea\u5df1\u914d\u7f6e\u7684\u8def\u5f84\n train_patchcore(config_path)\n```\n\n---\n\n# \u516d\u3001\u63a8\u7406\u548c\u7ed3\u679c\u53ef\u89c6\u5316\u793a\u4f8b\n\n\u63a8\u7406\u4e0e\u53ef\u89c6\u5316\u6d41\u7a0b`anomalib`\u4e5f\u63d0\u4f9b\uff1a\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\nimport matplotlib.pyplot as plt\n\ndef infer_and_visualize(config_path: str, image_path: str):\n config = get_configurable_parameters(config_path)\n \n model = get_model(config.model)\n model.load_state_dict(torch.load('patchcore_best.ckpt')['state_dict'])\n\n # \u521b\u5efa\u63a8\u7406\u5668\n inferencer = Inferencer(config, model)\n \n results = inferencer.infer(image_path)\n \n # results\u5b57\u5178\u4e00\u822c\u5305\u542b\u5f02\u5e38\u70ed\u529b\u56fe\u3001\u63a9\u7801\u3001\u5f97\u5206\u7b49\n anomaly_map = results[\"anomaly_map\"]\n \n img = plt.imread(image_path)\n plt.imshow(img)\n plt.imshow(anomaly_map, cmap='jet', alpha=0.5) # \u53e0\u52a0\u5f02\u5e38\u70ed\u529b\u56fe\n plt.colorbar()\n plt.title(f\"Anomaly score: {results['score']:.3f}\")\n plt.show()\n\nif __name__ == \"__main__\":\n import torch\n infer_and_visualize(\"./config.yaml\", \"./data/test/sample1.png\")\n```\n\n---\n\n# \u4e03\u3001\u603b\u7ed3\u4e0e\u5efa\u8bae\n\n- \u4f7f\u7528 `anomalib` \u642d\u5efa\u6d41\u6c34\u7ebf\u8d28\u68c0\u65b9\u6848\uff0c\u4e3b\u8981\u719f\u6089\u914d\u7f6e\u548c\u6570\u636e\u51c6\u5907\u3002\n- PatchCore\u53ea\u9700\u8981\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\uff0c\u9002\u5408\u4f60\u5f53\u524d20\u5f20\u6b63\u5e38\u56fe\u7247\u542f\u52a8\u3002\n- \u6570\u636e\u91cf\u8d8a\u5927\u6a21\u578b\u6548\u679c\u8d8a\u597d\uff0c\u5efa\u8bae\u540e\u671f\u6269\u5145\u91c7\u96c6\u3002\n- \u53ef\u89c6\u5316\u65f6\u8c03\u8282\u9608\u503c\uff0c\u5b9a\u4f4d\u7f3a\u9677\u533a\u57df\u3002\n- `anomalib`\u6e90\u7801\u6587\u6863[GitHub](https://github.com/openvinotoolkit/anomalib)\u5f88\u8be6\u7ec6\uff0c\u652f\u6301\u591a\u79cd\u5de5\u4e1a\u573a\u666f\u3002\n\n---\n\n\u5982\u679c\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u66f4\u5b8c\u6574\u7684\u9879\u76ee\u811a\u624b\u67b6\uff0c\u6216\u8005\u6307\u5bfc\u4f60\u6570\u636e\u683c\u5f0f\u4e0e\u914d\u7f6e\u7ec6\u8282\u3002\u795d\u4f60\u9879\u76ee\u8fdb\u5c55\u987a\u5229\uff01\u6709\u95ee\u9898\u968f\u65f6\u95ee\u6211\u3002\nUser: \u9884\u5904\u7406\u56fe\u50cf\u5f97\u505a\u5230\u4ec0\u4e48\uff0c\u9a8c\u8bc1\u96c6\uff0cmarkdown\u603b\u7ed3\u7ed9\u6211\uff0c\u4e0a\u9762\u7684\u673a\u5668\u4eba\u6211\u6253\u7b97\u76ee\u524d\u8fd8\u662f\u5148\u4e13\u6ce8\u4e8e\u5148\u5b9e\u73b0\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\nAssistant: \u4e0b\u9762\u662f\u4f60\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u9879\u76ee\u91cc\u7684**\u56fe\u50cf\u9884\u5904\u7406\u5efa\u8bae**\u3001**\u9a8c\u8bc1\u96c6\u8bbe\u8ba1**\uff0c\u4ee5\u53ca**\u9879\u76ee\u6b65\u9aa4\u7684Markdown\u603b\u7ed3**\uff0c\u6700\u540e\u9488\u5bf9\u4f60\u201c\u5148\u505a\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u201d\u7684\u5efa\u8bae\u4e5f\u7b80\u5355\u7ed9\u51fa\u601d\u8def\u3002\n\n---\n\n# \u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u9879\u76ee - \u6570\u636e\u9884\u5904\u7406\u4e0e\u9a8c\u8bc1\u96c6\n\n## 1. \u56fe\u50cf\u9884\u5904\u7406\u5efa\u8bae\n\n- **\u5c3a\u5bf8\u7edf\u4e00** \n \u5c06\u91c7\u96c6\u7684\u56fe\u7247\u7edf\u4e00\u7f29\u653e\u5230\u56fa\u5b9a\u5c3a\u5bf8\uff08\u5982256x256\u3001512x512\uff09\uff0c\u786e\u4fdd\u8f93\u5165\u6a21\u578b\u65f6\u5c3a\u5bf8\u4e00\u81f4\uff0c\u6709\u5229\u4e8e\u6279\u91cf\u5904\u7406\u3002\n\n- **\u8272\u5f69\u7a7a\u95f4** \n \u901a\u5e38\u4f7f\u7528RGB\u5373\u53ef\uff0c\u65e0\u7279\u6b8a\u9700\u6c42\u53ef\u4e0d\u505a\u8f6c\u6362\u3002\u82e5\u5370\u5237\u7eb9\u7406\u5bf9\u989c\u8272\u654f\u611f\uff0c\u53ef\u8003\u8651\u4fdd\u7559\u8272\u5f69\u4fe1\u606f\u3002\n\n- **\u56fe\u50cf\u589e\u5f3a\uff08\u53ef\u9009\uff09** \n - \u5149\u7167\u5747\u8861\uff08\u8c03\u6574\u4eae\u5ea6\u3001\u5bf9\u6bd4\u5ea6\uff09 \n - \u51cf\u5c11\u566a\u58f0\uff08\u4e2d\u503c\u6ee4\u6ce2\u3001\u9ad8\u65af\u6a21\u7cca\uff09 \n - \u6570\u636e\u589e\u5f3a\uff08\u65cb\u8f6c\u3001\u7ffb\u8f6c\u3001\u88c1\u526a\uff09\u6709\u52a9\u4e8e\u63d0\u5347\u6a21\u578b\u9c81\u68d2\u6027\uff0c\u4f46\u6ce8\u610f\u4e0d\u8981\u6539\u53d8\u7f3a\u9677\u672c\u8eab\u7279\u5f81\u3002\n\n- **\u5f52\u4e00\u5316** \n \u8f93\u5165\u6a21\u578b\u524d\u5bf9\u50cf\u7d20\u503c\u8fdb\u884c\u5f52\u4e00\u5316\u5904\u7406\uff08\u6bd4\u59820-1\u6216\u8005\u6807\u51c6\u5316\uff09\uff0c\u5177\u4f53\u5f52\u4e00\u5316\u53c2\u6570\u53c2\u8003\u6240\u7528\u6a21\u578b\u7684\u9884\u8bad\u7ec3\u8bbe\u7f6e\u3002\n\n- **\u683c\u5f0f\u4e0e\u547d\u540d** \n \u56fe\u7247\u5c3d\u91cf\u4f7f\u7528\u5e38\u7528\u65e0\u635f\u683c\u5f0f\uff08png/jpg\uff09\uff0c\u6587\u4ef6\u547d\u540d\u89c4\u8303\u65b9\u4fbf\u6279\u91cf\u52a0\u8f7d\u53ca\u6807\u6ce8\u3002\n\n---\n\n## 2. \u9a8c\u8bc1\u96c6\u8bbe\u8ba1\n\n- **\u6570\u636e\u5206\u5e03** \n \u9a8c\u8bc1\u96c6\u5e94\u5305\u542b\u4e0e\u8bad\u7ec3\u96c6\u76f8\u4f3c\u7684\u6b63\u5e38\u6837\u672c\u53ca\u5c3d\u53ef\u80fd\u591a\u6837\u7684\u5f02\u5e38\u6837\u672c\uff0c\u8986\u76d6\u4e0d\u540c\u7f3a\u9677\u7c7b\u578b\u3002\n\n- **\u6bd4\u4f8b\u53c2\u8003** \n \u6570\u636e\u6709\u9650\u65f6\uff0c\u901a\u5e38\u8bad\u7ec3:\u9a8c\u8bc1=80%:20%\u3002\u5f02\u5e38\u6837\u672c\u6570\u4fdd\u8bc1\u591a\u6837\u3001\u5178\u578b\u3002\n\n- **\u6807\u6ce8\u4fe1\u606f** \n \u5bf9\u5f02\u5e38\u6837\u672c\uff0c\u82e5\u53ef\u80fd\uff0c\u505a\u597d\u7f3a\u9677\u4f4d\u7f6e\u6807\u6ce8\uff08bounding box\u6216\u8005\u63a9\u7801\uff09\uff0c\u65b9\u4fbf\u8bc4\u4f30\u5b9a\u4f4d\u51c6\u786e\u7387\u3002\n\n- **\u72ec\u7acb\u6027** \n \u9a8c\u8bc1\u96c6\u5e94\u5c3d\u91cf\u4e0e\u8bad\u7ec3\u96c6\u72ec\u7acb\uff0c\u9632\u6b62\u8fc7\u62df\u5408\u3002\n\n---\n\n# \u9879\u76ee\u6b65\u9aa4Markdown\u603b\u7ed3\n\n```markdown\n# \u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u9879\u76ee\n\n## 1. \u6570\u636e\u91c7\u96c6\n- \u4f7f\u7528\u624b\u673a\u62cd\u6444\u6d41\u6c34\u7ebf\u5370\u5237\u54c1\u56fe\u50cf\uff0c20\u5f20\u6b63\u5e38\u6837\u672c\uff0c\u5c3d\u91cf\u591a\u89d2\u5ea6\u3001\u591a\u5149\u7167\u3002\n- \u786e\u4fdd\u56fe\u50cf\u6e05\u6670\uff0c\u65e0\u5927\u9762\u79ef\u906e\u6321\u3002\n\n## 2. \u56fe\u50cf\u9884\u5904\u7406\n- \u7edf\u4e00\u5c3a\u5bf8\uff08\u5982256x256\uff09\n- \u8f6c\u4e3aRGB\u683c\u5f0f\n- \u53ef\u9009\u56fe\u50cf\u589e\u5f3a\uff08\u53bb\u566a\u3001\u4eae\u5ea6\u5747\u8861\uff09\n- \u50cf\u7d20\u5f52\u4e00\u5316\u5904\u7406\n\n## 3. \u6570\u636e\u96c6\u5212\u5206\n- \u8bad\u7ec3\u96c6\uff1a\u6b63\u5e38\u6837\u672c\uff0818\u5f20\uff09\n- \u9a8c\u8bc1\u96c6\uff1a\u6b63\u5e38\u6837\u672c + \u5f02\u5e38\u6837\u672c\uff082\u5f20+\u8865\u5145\u7f3a\u9677\u56fe\u7247\uff09\n\n## 4. \u6a21\u578b\u8bad\u7ec3\n- \u9009\u7528PatchCore(\u57fa\u4e8eanomalib\u5e93)\n- \u53ea\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\u6a21\u578b\n- \u8bad\u7ec320\u4e2aepoch\uff0c\u8c03\u6574\u8d85\u53c2\n\n## 5. \u63a8\u7406\u5f02\u5e38\u68c0\u6d4b\n- \u5bf9\u6d4b\u8bd5\u56fe\u7247\u751f\u6210\u5f02\u5e38\u70ed\u529b\u56fe\n- \u6839\u636e\u9608\u503c\u63d0\u53d6\u5f02\u5e38\u533a\u57df\n\n## 6. \u7ed3\u679c\u53ef\u89c6\u5316\n- \u53e0\u52a0\u5f02\u5e38\u70ed\u529b\u56fe\u81f3\u539f\u56fe\n- \u6846\u51fa\u5f02\u5e38\u533a\u57df\uff0c\u6807\u8bb0\u89c6\u89c9\u7f3a\u9677\n\n## 7. \u8fed\u4ee3\u4f18\u5316\n- \u589e\u52a0\u6570\u636e\u6837\u672c\u4e0e\u591a\u6837\u6027\n- \u8c03\u6574\u9884\u5904\u7406\u4e0e\u9608\u503c\n- \u5c1d\u8bd5\u591a\u4e2a\u6a21\u578b\u5bf9\u6bd4\n\n```\n\n---\n\n# \u4f60\u8981\u5148\u505a\u7684\u201c\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u201d\u5feb\u901f\u601d\u8def\n\n- \u7b80\u5355\u5b9e\u73b0\uff1a\u8c03\u7528\u516c\u5f00\u5929\u6c14API\uff08\u6bd4\u5982[\u548c\u98ce\u5929\u6c14](https://www.qweather.com/)\u6216\u8005OpenWeatherMap\uff09\n- \u524d\u7aef\u7528JavaScript\u53d1\u8bf7\u6c42\u8f93\u5165\u57ce\u5e02\u540d\u83b7\u53d6\u5929\u6c14\u4fe1\u606f\n- \u540e\u7aefPython\u6216Node.js\u505a\u63a5\u53e3\u8f6c\u53d1\uff08\u53ef\u9009\uff09\n- UI\u7b80\u5355\u5bf9\u8bdd\u6846\uff0c\u8f93\u5165\u57ce\u5e02+\u663e\u793a\u5929\u6c14\u6587\u672c\u548c\u56fe\u6807\n\n\u82e5\u540e\u7eed\u60f3\u52a0\u673a\u5668\u4eba\u89d2\u8272\u6216\u66f4\u590d\u6742\u7684\u5bf9\u8bdd\uff0c\u53ef\u4ee5\u5728\u6b64\u57fa\u7840\u4e0a\u8fed\u4ee3\u3002\n\n---\n\n\u5982\u679c\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4e2a**\u7b80\u5355\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u7684Python+JS\u793a\u4f8b\u4ee3\u7801**\uff0c\u6216\u8005\u5e2e\u4f60\u89c4\u5212\u66f4\u52a0\u667a\u80fd\u7684\u5bf9\u8bdd\u673a\u5668\u4eba\u5b9e\u73b0\u65b9\u6848\u3002\u4f60\u544a\u8bc9\u6211\uff01\nUser: \u60f3\u7ed9\u522b\u4eba\u5c55\u793a\u7f3a\u9677\u533a\u57df\uff0c\u65e0\u9700\u70ed\u529b\u56fe\uff0c\u539f\u56fe\u6846\u51fa\u7f3a\u9677\u533a\u57df\u9700\u8981\u4ec0\u4e48\u7b97\u6cd5\uff0c\u5f97\u53bb\u5b66\u70b9\u5565\u5fc5\u8981\u77e5\u8bc6\uff0c\u53ef\u4ee5\u5b9e\u73b0\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u5148\u7b80\u5355\u5b9e\u73b0\uff0c\u6211\u8fd8\u60f3\u52a0\u5165\u6839\u636e\u5f53\u524d\u5929\u6c14\u7ed9\u7528\u6237\u63d0\u5efa\u8bae\nAssistant: \u660e\u767d\u4e86\uff0c\u4f60\u60f3\u4e13\u6ce8\u4e8e\uff1a\n\n- **\u6d41\u6c34\u7ebf\u5370\u5237\u7f3a\u9677\u68c0\u6d4b\u7ed3\u679c\u7684\u201c\u7f3a\u9677\u533a\u57df\u76f4\u63a5\u6846\u51fa\u201d**\uff08\u4e0d\u8981\u70ed\u529b\u56fe\uff09\uff0c\u65b9\u4fbf\u7ed9\u522b\u4eba\u4e00\u76ee\u4e86\u7136\u5730\u770b\u5230\u7f3a\u9677\u533a\u57df\uff1b\n- \u5b9e\u73b0\u4e00\u4e2a**\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba**\uff0c\u5e76\u4e14\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u80fd**\u6839\u636e\u5f53\u524d\u5929\u6c14\u7ed9\u51fa\u7528\u6237\u5efa\u8bae**\u3002\n\n---\n\n# \u4e00\u3001\u7f3a\u9677\u533a\u57df\u76f4\u63a5\u6846\u51fa\u7684\u5b9e\u73b0\u601d\u8def\u548c\u7b97\u6cd5\n\n---\n\n### 1. \u4ece\u70ed\u529b\u56fe\u5230\u7f3a\u9677\u6846\u7684\u5e38\u89c1\u6d41\u7a0b\uff1a\n\n\u867d\u7136\u4f60\u4e0d\u9700\u8981\u5c55\u793a\u70ed\u529b\u56fe\uff0c\u4f46\u5e95\u5c42 PatchCore \u7b49\u6a21\u578b\u90fd\u4f1a\u5148\u7b97\u51fa\u4e00\u4e2a\u201c\u5f02\u5e38\u5206\u6570\u56fe\u201d\uff08\u5373\u70ed\u529b\u56fe\uff09\uff0c\u4ee3\u8868\u6bcf\u4e2a\u50cf\u7d20/patch\u7684\u5f02\u5e38\u6982\u7387\u3002\n\n\u4ece\u8fd9\u4e2a\u70ed\u529b\u56fe\u76f4\u63a5\u6846\u51fa\u7f3a\u9677\u533a\u57df\u7684\u6838\u5fc3\u6b65\u9aa4\u662f\uff1a\n\n- **\u9608\u503c\u5206\u5272\uff08Thresholding\uff09**\uff1a\u628a\u70ed\u529b\u56fe\u8f6c\u6210\u4e8c\u503c\u56fe\uff0c\u7a81\u51fa\u660e\u663e\u5f02\u5e38\u7684\u533a\u57df\uff1b\n- **\u5f62\u6001\u5b66\u5904\u7406\uff08Morphological Operations\uff09**\uff1a\u81a8\u80c0\u3001\u8150\u8680\u7b49\u51cf\u5c11\u566a\u58f0\uff0c\u5c0f\u6591\u70b9\u8fc7\u6ee4\uff1b\n- **\u8f6e\u5ed3\u63d0\u53d6\uff08Contour Detection\uff09**\uff1a\u8bc6\u522b\u8fde\u901a\u533a\u57df\u8fb9\u754c\uff0c\u5f97\u5230\u5f02\u5e38\u533a\u57df\u8fb9\u6846\u3002\n\n\u5f97\u5230\u7684\u8f6e\u5ed3\u8fb9\u754c\uff0c\u5373\u7f3a\u9677\u533a\u57df\u7684\u77e9\u5f62\u6846\uff0c\u76f4\u63a5\u753b\u5728\u539f\u56fe\u4e0a\u3002\n\n---\n\n### 2. \u57fa\u672c\u7b97\u6cd5\u5de5\u5177\u548c\u5e93\n\n- **OpenCV**\uff08Python / C++ / JS\u5747\u53ef\u7528\uff09 \n \u7528\u5230`cv2.threshold`, `cv2.findContours`, `cv2.boundingRect`\u7b49\u51fd\u6570\u3002\n\n- **\u56fe\u50cf\u5904\u7406\u57fa\u7840\u77e5\u8bc6**\uff08\u9700\u8981\u4e86\u89e3\uff09 \n - \u4e8c\u503c\u5316\u9608\u503c\u5206\u5272 \n - \u5f62\u6001\u5b66\u53d8\u6362\uff08\u5f00\u8fd0\u7b97\u3001\u95ed\u8fd0\u7b97\uff09 \n - \u8fde\u901a\u57df\u5206\u6790\u3001\u8f6e\u5ed3\u68c0\u6d4b \n - \u5750\u6807\u7cfb\u548c\u7ed8\u56fe\uff08\u77e9\u5f62\u6846\uff09\n\n---\n\n### 3. \u5efa\u8bae\u5148\u5b66\u4e60\u7684\u77e5\u8bc6\u70b9\n\n- **\u6570\u5b57\u56fe\u50cf\u5904\u7406\u57fa\u7840** \n - \u4e86\u89e3\u50cf\u7d20\u3001\u7070\u5ea6\u56fe\u3001\u5f69\u8272\u56fe \n - \u9608\u503c\u5206\u5272\u4e0e\u4e8c\u503c\u56fe\u50cf \n - \u56fe\u50cf\u81a8\u80c0\u3001\u8150\u8680\u3001\u5f00\u95ed\u8fd0\u7b97\n\n- **\u8ba1\u7b97\u673a\u89c6\u89c9\u57fa\u7840** \n - \u8fde\u901a\u533a\u57df\u5206\u6790 \n - \u8f6e\u5ed3\uff08contour\uff09\u68c0\u6d4b\u4e0e\u8fb9\u754c\u63d0\u53d6 \n - \u6846\u9009\u4e0e\u591a\u8fb9\u5f62\u62df\u5408\n\n- **OpenCV\u5b9e\u7528\u64cd\u4f5c** \n - Python\u6216JavaScript\u7248\u672c\u7684OpenCV\u57fa\u7840API\u4f7f\u7528 \n - \u7ed8\u5236\u77e9\u5f62\uff08\u7528\u4e8e\u6807\u51fa\u7f3a\u9677\uff09\n\n---\n\n### 4. \u7b80\u5355Python\u793a\u4f8b\uff08\u57fa\u4e8e\u70ed\u529b\u56fe\uff09\n\n```python\nimport cv2\nimport numpy as np\n\ndef draw_defect_boxes(image_path, anomaly_map, threshold=0.5):\n img = cv2.imread(image_path)\n anomaly_map_norm = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_map_uint8 = (anomaly_map_norm * 255).astype(np.uint8)\n\n # \u9608\u503c\u5206\u5272\n _, binary_map = cv2.threshold(anomaly_map_uint8, int(threshold*255), 255, cv2.THRESH_BINARY)\n\n # \u5f62\u6001\u5b66\u5f00\u64cd\u4f5c\u53bb\u566a\n kernel = np.ones((3,3), np.uint8)\n clean_map = cv2.morphologyEx(binary_map, cv2.MORPH_OPEN, kernel, iterations=2)\n\n # \u627e\u8f6e\u5ed3\n contours, _ = cv2.findContours(clean_map, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n for cnt in contours:\n if cv2.contourArea(cnt) < 50: # \u8fc7\u6ee4\u5c0f\u9762\u79ef\u566a\u58f0\n continue\n x, y, w, h = cv2.boundingRect(cnt)\n cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2) # \u7ea2\u8272\u6846\n\n cv2.imwrite('defect_boxed.png', img)\n print(\"\u7f3a\u9677\u6846\u5df2\u7ed8\u5236\u5e76\u4fdd\u5b58\u4e3a defect_boxed.png\")\n```\n\n\u6b63\u5e38\u6267\u884c\u8fd9\u6bb5\u4ee3\u7801\uff0c\u524d\u63d0\u662f\u4f60\u6709`anomaly_map`\uff08\u70ed\u529b\u56fe\uff09\uff0c\u6548\u679c\u662f\u76f4\u63a5\u5728\u539f\u56fe\u4e0a\u6846\u51fa\u660e\u663e\u5f02\u5e38\u533a\u57df\u3002\n\n---\n\n# \u4e8c\u3001\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba\u7b80\u5355\u5b9e\u73b0\u601d\u8def\n\n---\n\n### 1. \u8c03\u7528\u5929\u6c14API\n\n- \u4f7f\u7528\u516c\u5f00\u5929\u6c14\u63a5\u53e3\uff0c\u6bd4\u5982[\u548c\u98ce\u5929\u6c14](https://www.qweather.com/)\u3001[OpenWeatherMap](https://openweathermap.org/api)\n- \u7528\u6237\u8f93\u5165\u57ce\u5e02\u540d\uff0c\u63a5\u53e3\u8fd4\u56de\u5b9e\u65f6\u5929\u6c14\u6570\u636e\uff08\u6e29\u5ea6\u3001\u5929\u6c14\u72b6\u51b5\u3001\u98ce\u901f\u7b49\uff09\n\n---\n\n### 2. \u7ed9\u51fa\u5929\u6c14\u5efa\u8bae\n\n- \u4f60\u53ef\u4ee5\u6839\u636e\u4e0d\u540c\u5929\u6c14\u60c5\u51b5\uff0c\u8bbe\u7f6e\u56fa\u5b9a\u6587\u672c\u5efa\u8bae\uff0c\u6bd4\u5982\uff1a\n\n| \u5929\u6c14 | \u5efa\u8bae |\n|--------------|--------------------------------|\n| \u6674 | \u4eca\u5929\u9633\u5149\u660e\u5a9a\uff0c\u9002\u5408\u6237\u5916\u8fd0\u52a8 |\n| \u96e8 | \u5929\u6c14\u6709\u96e8\uff0c\u8bb0\u5f97\u5e26\u4f1e |\n| \u96fe\u973e | \u7a7a\u6c14\u8d28\u91cf\u5dee\uff0c\u5efa\u8bae\u5ba4\u5185\u6d3b\u52a8 |\n| \u9ad8\u6e29 | \u6ce8\u610f\u9632\u6652\u4e0e\u8865\u6c34 |\n\n\u7528\u7b80\u5355\u7684if/else\u6839\u636eAPI\u7684\u5929\u6c14\u72b6\u6001\u7801\u7ed9\u51fa\u63d0\u793a\u3002\n\n---\n\n### 3. \u7b80\u5355Python\u793a\u4f8b\uff08\u4f7f\u7528OpenWeatherMap API\uff09\n\n```python\nimport requests\n\nAPI_KEY = \"\u4f60\u7684OpenWeatherMapAPIKey\"\n\ndef get_weather(city):\n url = f\"http://api.openweathermap.org/data/2.5/weather?q={city}&appid={API_KEY}&units=metric&lang=zh_cn\"\n res = requests.get(url)\n if res.status_code != 200:\n return None\n data = res.json()\n weather = data['weather'][0]['main']\n temp = data['main']['temp']\n\n # \u7b80\u5355\u5efa\u8bae\n advice = \"\"\n if weather == \"Rain\":\n advice = \"\u4eca\u5929\u6709\u96e8\uff0c\u8bb0\u5f97\u5e26\u4f1e\u3002\"\n elif weather == \"Clear\":\n advice = \"\u5929\u6c14\u6674\u6717\uff0c\u9002\u5408\u5916\u51fa\u3002\"\n elif weather in [\"Mist\", \"Fog\"]:\n advice = \"\u5929\u6c14\u6709\u96fe\uff0c\u5f00\u8f66\u8bf7\u6ce8\u610f\u5b89\u5168\u3002\"\n elif weather == \"Snow\":\n advice = \"\u4e0b\u96ea\u4e86\uff0c\u8bf7\u6ce8\u610f\u4fdd\u6696\u3002\"\n else:\n advice = \"\u6ce8\u610f\u5173\u6ce8\u5929\u6c14\u53d8\u5316\u3002\"\n\n return f\"{city}\u5f53\u524d\u5929\u6c14\uff1a{weather}\uff0c\u6e29\u5ea6 {temp}\u2103\u3002\u5efa\u8bae\uff1a{advice}\"\n\nif __name__ == \"__main__\":\n city = input(\"\u8bf7\u8f93\u5165\u57ce\u5e02\u540d\u79f0\uff1a\")\n print(get_weather(city))\n```\n\n---\n\n# \u4e09\u3001\u603b\u7ed3\n\n| \u4efb\u52a1 | \u5982\u4f55\u5f00\u59cb |\n|----------------|----------------------------------------|\n| \u7f3a\u9677\u533a\u57df\u6846\u51fa | \u5b66\u6570\u5b57\u56fe\u50cf\u5904\u7406\uff1a\u9608\u503c\u5206\u5272+\u5f62\u6001\u5b66\u8fd0\u7b97+\u8f6e\u5ed3\u68c0\u6d4b\uff0c\u7528OpenCV\u5b9e\u73b0 |\n| \u5929\u6c14\u673a\u5668\u4eba | \u8c03\u7528\u514d\u8d39\u5929\u6c14API\uff0c\u89e3\u6790\u5929\u6c14\u4fe1\u606f\uff0c\u6839\u636e\u5929\u6c14\u72b6\u6001\u8f93\u51fa\u7b80\u5355\u5efa\u8bae |\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\uff1a\n\n- \u5199**\u5b8c\u6574\u7684\u6d41\u6c34\u7ebf\u7f3a\u9677\u68c0\u6d4b\u70ed\u529b\u56fe\u540e\u5904\u7406+\u6846\u9009\u4ee3\u7801**\n- \u505a\u4e00\u4e2a**\u7b80\u5355\u7684\u5929\u6c14\u67e5\u8be2\u5e26\u5efa\u8bae\u7684\u5bf9\u8bdd\u673a\u5668\u4eba\u793a\u4f8b\uff08Python\u6216JavaScript\uff09**\n- \u6307\u5bfc\u4f60\u5165\u95e8**\u56fe\u50cf\u5904\u7406\u548c\u8ba1\u7b97\u673a\u89c6\u89c9\u7684\u5b66\u4e60\u8def\u7ebf**\n\n\u4f60\u544a\u8bc9\u6211\u60f3\u5148\u4ece\u54ea\u5757\u5f00\u59cb\uff0c\u6211\u5e2e\u4f60\u8be6\u7ec6\u505a\uff01\nUser: \t\u6307\u5bfc\u4f60\u5165\u95e8\u56fe\u50cf\u5904\u7406\u548c\u8ba1\u7b97\u673a\u89c6\u89c9\u7684\u5b66\u4e60\u8def\u7ebf\u6211\u9700\u8981\u5148\u5b66\u4e60\u5b8c\u6210\u6211\u9879\u76ee\u7684\u90e8\u5206\t\uff0c\u505a\u4e00\u4e2a\u7b80\u5355\u7684\u5929\u6c14\u67e5\u8be2\u5e26\u5efa\u8bae\u7684\u5bf9\u8bdd\u673a\u5668\u4eba\u793a\u4f8b\uff08Python\u6216JavaScript\uff09\uff0cpython\u505a\u540e\u7aef\uff0cjavascripts\u505a\u524d\u7aef\u5904\u7406\uff08\u53ef\u4ee5\u9009\u7528\u7b80\u5355\u6846\u67b6\uff09\nAssistant: \u660e\u767d\u4f60\u7684\u9700\u6c42\uff0c\u6211\u5e2e\u4f60\u89c4\u5212\u4e00\u4e2a**\u5faa\u5e8f\u6e10\u8fdb\u7684\u56fe\u50cf\u5904\u7406\u548c\u8ba1\u7b97\u673a\u89c6\u89c9\u5b66\u4e60\u8def\u7ebf\uff08\u9488\u5bf9\u4f60\u7684\u7f3a\u9677\u68c0\u6d4b\u9879\u76ee\uff09**\uff0c\u5e76\u9644\u4e0a\u4e00\u4e2a**\u7b80\u6613\u5929\u6c14\u67e5\u8be2+\u5efa\u8bae\u5bf9\u8bdd\u673a\u5668\u4eba\u7684\u5b8c\u6574\u793a\u4f8b\u6846\u67b6**\uff0c\u540e\u7aefPython+\u524d\u7aefJavaScript\uff08\u7528React\u505a\u7b80\u5355UI\u793a\u8303\uff09\u3002\n\n---\n\n# \u4e00\u3001\u9488\u5bf9\u7f3a\u9677\u68c0\u6d4b\u9879\u76ee\u7684\u56fe\u50cf\u5904\u7406\u4e0e\u8ba1\u7b97\u673a\u89c6\u89c9\u5b66\u4e60\u8def\u7ebf\n\n### 0. \u524d\u7f6e\u51c6\u5907\n- \u719f\u7ec3Python\u7f16\u7a0b\u57fa\u7840\n- \u80fd\u7528pip\u5b89\u88c5\u548c\u8fd0\u884cPython\u5e93\n- \u7535\u8111\u914d\u7f6e\u80fd\u8dd1\u7b80\u5355\u7684\u56fe\u50cf\u5904\u7406\uff08OpenCV\uff09\u548c\u6df1\u5ea6\u5b66\u4e60\uff08PyTorch\uff09\n\n### 1. Python\u57fa\u7840\u56fe\u50cf\u5904\u7406\n- \u5b66\u4e60`OpenCV`\u57fa\u7840API\uff0c\u91cd\u70b9\uff1a\n - \u56fe\u50cf\u8bfb\u5199\u3001\u663e\u793a\uff08`cv2.imread()`, `cv2.imshow()`\uff09\n - \u56fe\u50cf\u901a\u9053\u548c\u989c\u8272\u7a7a\u95f4\uff08BGR, RGB\uff09\n - \u56fe\u50cf\u7f29\u653e\u548c\u88c1\u526a\uff08`cv2.resize()`\uff09\n - \u7070\u5ea6\u56fe\u8f6c\u6362\n - \u9608\u503c\u5206\u5272\uff08`cv2.threshold()`\uff09\n - \u5f62\u6001\u5b66\u64cd\u4f5c\uff08\u8150\u8680\u3001\u81a8\u80c0\u3001\u5f00/\u95ed\u8fd0\u7b97\uff09\n - \u8f6e\u5ed3\u53d1\u73b0\uff08`cv2.findContours()`\uff0c `cv2.boundingRect()`\u753b\u6846\uff09\n \n**\u5b66\u4e60\u8d44\u6599\u63a8\u8350\uff1a**\n- OpenCV\u4e2d\u6587\u6559\u7a0b\uff1a[https://www.opencv.org.cn/opencvdoc/4.x/index.html](https://www.opencv.org.cn/opencvdoc/4.x/index.html)\n- \u4e66\u7c4d\uff1a\u300aOpenCV-Python\u6559\u7a0b\u300b\n\n### 2. \u76ee\u6807\u68c0\u6d4b\u57fa\u7840\n- \u7406\u89e3\u4ec0\u4e48\u662f\u201c\u5f02\u5e38\u533a\u57df\u68c0\u6d4b\u201d\n- \u5b66\u4e60\u5982\u4f55\u7528\u9608\u503c\u628a\u5f02\u5e38\u70ed\u529b\u56fe\u8f6c\u4e3a\u4e8c\u503c\u56fe\uff0c\u518d\u63d0\u53d6\u8f6e\u5ed3\u6846\n- \u4e86\u89e3\u8fde\u901a\u57df\u5206\u6790\u3001\u566a\u58f0\u8fc7\u6ee4\u4e0e\u6700\u5c0f\u9762\u79ef\u8fc7\u6ee4\n\n### 3. \u6df1\u5ea6\u5b66\u4e60\u4e0e\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\n- \u4e86\u89e3PatchCore\u539f\u7406\uff08\u7279\u5f81\u63d0\u53d6 + \u5185\u5b58\u5e93\u68c0\u7d22\uff09\n- \u5b9e\u8df5\u7528`anomalib`\u5feb\u901f\u8bad\u7ec3\uff0c\u805a\u7126\u4f7f\u7528\u800c\u975e\u5e95\u5c42\u5b9e\u73b0\n- \u638c\u63e1\u6570\u636e\u51c6\u5907\u6d41\u7a0b (\u6570\u636e\u683c\u5f0f\uff0c\u6b63\u5e38\u96c6\u4e0e\u7f3a\u9677\u96c6\u51c6\u5907)\n\n### 4. \u89c6\u89c9\u7ed3\u679c\u7684\u53ef\u89c6\u5316\n- matplotlib\u7ed8\u5236\u56fe\u50cf\n- \u4f7f\u7528OpenCV\u753b\u77e9\u5f62\u6846\u6807\u51fa\u7f3a\u9677\n\n---\n\n# \u4e8c\u3001\u7b80\u6613\u5929\u6c14\u67e5\u8be2+\u5efa\u8bae\u5bf9\u8bdd\u673a\u5668\u4eba\u793a\u4f8b\n\n## 1. \u540e\u7aef\uff08Python\uff0cFastAPI\uff09\n\n```python\n# backend/app.py\nfrom fastapi import FastAPI\nfrom pydantic import BaseModel\nimport requests\n\napp = FastAPI()\n\nAPI_KEY = \"\u4f60\u7684OpenWeatherMapAPIKey\"\n\nclass WeatherRequest(BaseModel):\n city: str\n\n@app.post(\"/weather\")\ndef get_weather(req: WeatherRequest):\n url = f\"http://api.openweathermap.org/data/2.5/weather?q={req.city}&appid={API_KEY}&units=metric&lang=zh_cn\"\n res = requests.get(url)\n if res.status_code != 200:\n return {\"error\": \"\u57ce\u5e02\u4e0d\u5b58\u5728\u6216\u8bf7\u6c42\u5931\u8d25\"}\n data = res.json()\n weather = data['weather'][0]['main']\n temp = data['main']['temp']\n\n # \u7b80\u5355\u5929\u6c14\u5efa\u8bae\n advice = \"\"\n if weather == \"Rain\":\n advice = \"\u4eca\u5929\u6709\u96e8\uff0c\u8bb0\u5f97\u5e26\u4f1e\u3002\"\n elif weather == \"Clear\":\n advice = \"\u5929\u6c14\u6674\u6717\uff0c\u9002\u5408\u5916\u51fa\u3002\"\n elif weather in [\"Mist\", \"Fog\"]:\n advice = \"\u5929\u6c14\u6709\u96fe\uff0c\u5f00\u8f66\u8bf7\u6ce8\u610f\u5b89\u5168\u3002\"\n elif weather == \"Snow\":\n advice = \"\u4e0b\u96ea\u4e86\uff0c\u8bf7\u6ce8\u610f\u4fdd\u6696\u3002\"\n else:\n advice = \"\u6ce8\u610f\u5173\u6ce8\u5929\u6c14\u53d8\u5316\u3002\"\n\n return {\n \"city\": req.city,\n \"weather\": weather,\n \"temperature\": temp,\n \"advice\": advice\n }\n```\n\n### \u8fd0\u884c\u63d0\u793a\n```bash\npip install fastapi uvicorn requests\nuvicorn backend.app:app --reload\n```\n\n---\n\n## 2. \u524d\u7aef\uff08React \u793a\u4f8b\uff09\n\n```jsx\n// frontend/src/App.js\nimport React, { useState } from \"react\";\n\nfunction App() {\n const [city, setCity] = useState(\"\");\n const [result, setResult] = useState(null);\n const [error, setError] = useState(null);\n\n async function fetchWeather() {\n if (!city) return;\n setError(null);\n setResult(null);\n try {\n const res = await fetch(\"http://localhost:8000/weather\", {\n method: \"POST\",\n headers: { \"Content-Type\": \"application/json\" },\n body: JSON.stringify({ city }),\n });\n const data = await res.json();\n if (data.error) {\n setError(data.error);\n } else {\n setResult(data);\n }\n } catch (err) {\n setError(\"\u8bf7\u6c42\u5931\u8d25\");\n }\n }\n\n return (\n
\n

\u5929\u6c14\u67e5\u8be2\u673a\u5668\u4eba

\n setCity(e.target.value)}\n onKeyDown={(e) => e.key === \"Enter\" && fetchWeather()}\n style={{ width: \"70%\", padding: 8, fontSize: 16 }}\n />\n \n\n {error &&

{error}

}\n\n {result && (\n
\n

\n {result.city} \u5f53\u524d\u5929\u6c14\uff1a{result.weather}\uff0c\u6e29\u5ea6\uff1a{result.temperature}\u2103\n

\n

\u5efa\u8bae\uff1a{result.advice}

\n
\n )}\n
\n );\n}\n\nexport default App;\n```\n\n### \u8fd0\u884c\u63d0\u793a\n\n```bash\nnpx create-react-app frontend\n# \u66ff\u6362src/App.js\u4e3a\u4e0a\u9762\u4ee3\u7801\ncd frontend\nnpm start\n```\n\n> \u6ce8\u610f\u6d4f\u89c8\u5668\u8de8\u57df\u95ee\u9898\uff1a\u5f00\u53d1\u65f6\u53ef\u4ee5\u7528`proxy`\u6216\u5b89\u88c5`CORS`\u4e2d\u95f4\u4ef6\u5728FastAPI\u540e\u7aef\uff0c\u6216\u8005\u524d\u7aef\u7528`vite`\u914d\u4ee3\u7406\u3002\n\n---\n\n# \u4e09\u3001\u603b\u7ed3\n\n| \u9636\u6bb5 | \u5b66\u4e60\u5185\u5bb9/\u5b9e\u73b0 | \u63a8\u8350\u5b9e\u8df5/\u8d44\u6599 |\n|----------------------------|----------------------------------|-----------------------------------|\n| 1. \u56fe\u50cf\u9884\u5904\u7406 | OpenCV\u57fa\u7840\u56fe\u50cf\u64cd\u4f5c | OpenCV-Python\u4e2d\u6587\u6587\u6863 |\n| 2. \u89c6\u89c9\u5b9a\u4f4d\u7f3a\u9677\u6846 | \u56fe\u50cf\u4e8c\u503c\u5316\u3001\u5f62\u6001\u5b66\u3001\u8f6e\u5ed3\u68c0\u6d4b | OpenCV\u6559\u7a0b\uff0c\u52a8\u624b\u505a\u4ee3\u7801 |\n| 3. \u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\u8bad\u7ec3 | PatchCore\u539f\u7406\u53ca`anomalib`\u4f7f\u7528 | anomalib\u5b98\u65b9\u6559\u7a0b\uff0cgithub\u4ee3\u7801 |\n| 4. \u5929\u6c14\u673a\u5668\u4eba\u5feb\u901f\u5b9e\u73b0 | FastAPI\u540e\u7aef\uff0cOpenWeatherMap API\u8c03\u7528 | FastAPI\u5b98\u65b9\u6587\u6863\uff0cOpenWeatherMap\u6587\u6863 |\n| 5. \u524d\u7aef\u4ea4\u4e92 | React\u7b80\u5355\u9875\u9762\uff0cfetch\u63a5\u53e3\u8c03\u7528 | React\u5b98\u65b9\u6587\u6863\uff0cAPI\u8c03\u7528\u793a\u4f8b |\n\n---\n\n\u968f\u65f6\u63d0\u95ee\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u6bcf\u4e00\u6b65\u90fd\u5199\u793a\u8303\u4ee3\u7801\u548c\u8be6\u7ec6\u6559\u7a0b\u3002 \n\u5982\u679c\u4f60\u5148\u60f3\u8dd1\u8d77\u201c\u5929\u6c14\u673a\u5668\u4eba\u201d\u9879\u76ee\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u628a\u73af\u5883\u642d\u8d77\u6765\uff0c\u6216\u8005\u5e2e\u4f60\u5199CORS\u652f\u6301\u4ee3\u7801\u3002\n\n\u795d\u4f60\u9879\u76ee\u987a\u5229\uff01\u9700\u8981\u4ee3\u7801\u793a\u4f8b\u6216\u8005\u5b66\u4e60\nUser: \u7ec6\u8bb2\u4e00\u4e0b\u9884\u5904\u7406\u600e\u4e48\u80fd\u8ba9\u6a21\u578b\u5b66\u4e60\u5230\u6b63\u5e38\u74f6\u5b50\u7684\u7279\u5f81\uff0c\u91cd\u70b9\u5370\u5237\uff0c\u5982\u4f55\u5b66\u4e60\u5230\u5b57\u4f53\uff0c\u6709\u5783\u573e\u554a\uff0c\u6bdb\u523a\u554a\uff0c\u8fd9\u4e9b\u7f3a\u9677\nAssistant: \u5f88\u68d2\uff0c\u4f60\u975e\u5e38\u5207\u4e2d\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u4e2d\u201c\u5982\u4f55\u8ba9\u6a21\u578b\u5b66\u5230\u6b63\u5e38\u54c1\u7279\u5f81\u5e76\u533a\u5206\u7f3a\u9677\u201d\u7684\u6838\u5fc3\u3002\u4e0b\u9762\u6211\u7ec6\u8bb2**\u9884\u5904\u7406\u73af\u8282\u5982\u4f55\u5e2e\u52a9PatchCore\u6216\u7c7b\u4f3c\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\u9ad8\u6548\u5b66\u4e60\u201c\u6b63\u5e38\u74f6\u5b50\u201d\u7279\u5f81**\uff0c\u5c24\u5176\u662f\u91cd\u70b9\u5173\u6ce8**\u5370\u5237\u5b57\u4f53\u7ec6\u8282\u3001\u53bb\u9664\u5783\u573e\u80cc\u666f\u548c\u6bdb\u523a\u7b49\u566a\u58f0**\uff0c\u5e2e\u52a9\u6a21\u578b\u51c6\u786e\u8bc6\u522b\u201c\u7f3a\u9677\u201d\u8fd9\u5757\u3002\n\n---\n\n## 1. \u9884\u5904\u7406\u5728\u5f02\u5e38\u68c0\u6d4b\u4e2d\u7684\u89d2\u8272\n\n\u9884\u5904\u7406\u8d28\u91cf\u597d\u574f\uff0c\u76f4\u63a5\u5f71\u54cd\u6a21\u578b\u5bf9\u201c\u6b63\u5e38\u201d\u6837\u672c\u7684\u7279\u5f81\u5b66\u4e60\u8d28\u91cf\u548c\u540e\u7eed\u5f02\u5e38\u5224\u5b9a\u51c6\u786e\u5ea6\u3002\n\n\u9884\u5904\u7406\u4e3b\u8981\u76ee\u7684\u662f\uff1a\n- **\u53bb\u9664\u65e0\u5173\u5e72\u6270**\uff08\u80cc\u666f\u6742\u8d28\u3001\u5149\u6591\u3001\u6a21\u7cca\u90e8\u5206\u3001\u65e0\u6548\u533a\u57df\uff09\n- **\u7a81\u51fa\u5173\u952e\u7279\u5f81**\uff08\u5b57\u4f53\u7ed3\u6784\u3001\u5370\u5237\u7ec6\u8282\u3001\u74f6\u5b50\u8f6e\u5ed3\u7b49\uff09\n- \u7edf\u4e00\u8f93\u5165\u683c\u5f0f\uff0c\u65b9\u4fbf\u6a21\u578b\u5bf9\u6bd4\u5f52\u7eb3\u6b63\u5e38\u6837\u672c\u5206\u5e03\u3002\n\n---\n\n## 2. \u9488\u5bf9\u4f60\u7684\u4efb\u52a1\u2014\u2014\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\uff0c\u5173\u952e\u5173\u6ce8\u70b9\n\n- **\u5370\u5237\u5b57\u4f53**\uff1a\u5b57\u4f53\u7ed3\u6784\u6e05\u6670\uff0c\u8fb9\u7f18\u9510\u5229\uff0c\u7b14\u753b\u89c4\u8303\n- **\u5783\u573e\u3001\u6bdb\u523a\u3001\u810f\u70b9**\uff1a\u901a\u5e38\u662f\u4e0d\u89c4\u5219\u3001\u7c97\u7cd9\u3001\u975e\u5b57\u4f53\u7684\u9644\u7740\n- **\u74f6\u8eab\u80cc\u666f**\uff1a\u5c3d\u91cf\u80cc\u666f\u7edf\u4e00\uff08\u7eaf\u8272\u6216\u6a21\u7cca\uff09\uff0c\u7a81\u51fa\u5370\u5237\u5c42\n\n---\n\n## 3. \u5177\u4f53\u9884\u5904\u7406\u5efa\u8bae\n\n### \uff081\uff09\u88c1\u526a\u4e0e\u5bf9\u9f50\uff08ROI\u5b9a\u4f4d\uff09\n\n- **\u56fa\u5b9a\u533a\u57df\u88c1\u526a\uff08ROI\uff09** \n \u6309\u62cd\u6444\u59ff\u52bf\uff0c\u5c06\u56fe\u50cf\u88c1\u526a\u6210\u53ea\u5305\u542b\u5370\u5237\u5b57\u4f53\u533a\u57df\uff0c\u907f\u514d\u6a21\u578b\u5b66\u4e60\u5230\u591a\u4f59\u80cc\u666f\u3002 \n \u5982\u679c\u6709\u8f7b\u5fae\u4f4d\u7f6e\u504f\u5dee\uff0c\u53ef\u4ee5\u7edf\u4e00\u7f29\u653e\u6216\u505a\u56fe\u50cf\u5bf9\u9f50\uff08\u7b80\u5355\u4eff\u5c04\u53d8\u6362\uff09\uff0c\u4fdd\u8bc1\u5b57\u4f53\u5728\u56fe\u50cf\u91cc\u5927\u81f4\u76f8\u540c\u4f4d\u7f6e\u3002\n\n- **\u7a33\u5b9a\u62cd\u6444\u6761\u4ef6** \n \u6d88\u9664\u89d2\u5ea6\u503e\u659c\u6216\u8fc7\u66dd\u533a\u57df\uff0c\u51cf\u5c11\u65e0\u6548\u4fe1\u606f\u3002\n\n### \uff082\uff09\u56fe\u50cf\u589e\u5f3a\u4e0e\u51c0\u5316\n\n- **\u8272\u5f69\u7a7a\u95f4\u8f6c\u6362** \n \u8bd5\u8bd5\u7528\u7070\u5ea6\u56fe\u6216\u8005HSV\u7684\u67d0\u4e2a\u901a\u9053\uff0c\u4f7f\u5b57\u4f53\u548c\u80cc\u666f\u7684\u5bf9\u6bd4\u5ea6\u66f4\u660e\u663e\u3002\n\n- **\u5bf9\u6bd4\u5ea6\u589e\u5f3a** \n \u5229\u7528 `cv2.equalizeHist()`\uff08\u76f4\u65b9\u56fe\u5747\u8861\u5316\uff09\u6216CLAHE\uff08\u81ea\u9002\u5e94\u5747\u8861\uff09\u589e\u5f3a\u5370\u5237\u5b57\u4f53\u8fb9\u7f18\u5bf9\u6bd4\uff0c\u7a81\u51fa\u7b14\u753b\u3002\n\n- **\u566a\u58f0\u8fc7\u6ee4** \n - \u4e2d\u503c\u6ee4\u6ce2\u53bb\u9664\u5b64\u7acb\u5c0f\u70b9\u566a\u58f0\uff08\u975e\u7f3a\u9677\u7684\u5783\u573e\uff09\n - \u5c0f\u5b54\u6d1e\u586b\u5145\uff08\u7ed3\u5408\u5f62\u6001\u5b66\u5904\u7406\uff09\u907f\u514d\u201c\u4e0d\u5b8c\u6574\u201d\u5b57\u4f53\u9020\u6210\u8bef\u5224\n\n- **\u5f62\u6001\u5b66\u64cd\u4f5c**\uff08\u4e3b\u8981\u7528\u5728\u6570\u636e\u589e\u5f3a\u9636\u6bb5/\u6837\u672c\u6e05\u7406\u9636\u6bb5\uff09 \n - \u8150\u8680\u548c\u81a8\u80c0\u8c03\u8282\u5b57\u4f53\u7c97\u7ec6\u3001\u53bb\u9664\u5c0f\u6bdb\u523a\n - \u5f00\u95ed\u8fd0\u7b97\u6e05\u7406\u566a\u58f0\n\n### \uff083\uff09\u53bb\u80cc\u666f\uff08\u53ef\u9009\uff09\n\n- \u5982\u679c\u80cc\u666f\u989c\u8272\u7a33\u5b9a\uff08\u6bd4\u5982\u7eaf\u767d\u6216\u5355\u8272\uff09\uff0c\u53ef\u4ee5\u7528\u8272\u5f69\u9608\u503c\u6216\u7b80\u5355\u80cc\u666f\u5206\u5272\uff0c\u53bb\u9664\u6216\u6a21\u7cca\u80cc\u666f\u533a\u57df\uff0c\u53ea\u4fdd\u7559\u5b57\u4f53\u548c\u74f6\u8eab\u5370\u5237\u90e8\u5206\u3002\n\n---\n\n## 4. \u5982\u4f55\u5e2e\u52a9\u6a21\u578b\u5b66\u5230\u5b57\u4f53\u548c\u6b63\u5e38\u7279\u5f81\n\n1. **\u8f93\u5165\u4e2d\u6e05\u6670\u7684\u5b57\u4f53\u7ed3\u6784** \n \u9884\u5904\u7406\u540e\u5b57\u4f53\u8fb9\u7f18\u6e05\u6670\u3001\u5bf9\u6bd4\u9ad8\uff0c\u6a21\u578b\u63d0\u53d6\u7684patch-level\u7279\u5f81\u4f1a\u805a\u7126\u5b57\u4f53\u7684\u5f62\u72b6\u548c\u7eb9\u7406\u3002\n\n2. **\u907f\u514d\u6a21\u578b\u5b66\u4e60\u80cc\u666f\u566a\u58f0** \n \u6e05\u7406\u80cc\u666f\u548c\u6742\u7269\uff0c\u51cf\u5c11\u65e0\u610f\u4e49\u4fe1\u606f\u5e72\u6270\uff0c\u51cf\u5c11\u6a21\u578b\u7406\u89e3\u504f\u5dee\u3002\n\n3. **\u4fdd\u6301\u6b63\u5e38\u6837\u672c\u95f4\u4e00\u81f4\u6027** \n \u4e00\u81f4\u7684\u9884\u5904\u7406\u4fdd\u8bc1\u6b63\u5e38\u6837\u672c\u7279\u5f81\u805a\u5408\u5728\u4e00\u4e2a\u201c\u6b63\u5e38\u5206\u5e03\u57df\u201d\uff0c\u5f02\u5e38\u6837\u672c\u4e2d\u6bdb\u523a\u3001\u6c61\u70b9\u6253\u7834\u8fd9\u79cd\u89c4\u5f8b\uff0c\u80fd\u88ab\u6a21\u578b\u8bc6\u522b\u4e3a\u5f02\u5e38\u3002\n\n4. **\u6570\u636e\u589e\u5f3a\u63d0\u5347\u6cdb\u5316**\uff08\u53ef\u9009\uff09 \n \u8f7b\u5fae\u65cb\u8f6c\u3001\u4eae\u5ea6\u53d8\u5316\uff0c\u8ba9\u6a21\u578b\u66f4\u9c81\u68d2\uff0c\u4e0d\u4f1a\u8fc7\u5ea6\u62df\u5408\u67d0\u4e00\u56fe\u50cf\u7ec6\u8282\u3002\n\n---\n\n## 5. \u9488\u5bf9\u201c\u5783\u573e\u201d\u548c\u201c\u6bdb\u523a\u201d\u8fd9\u7c7b\u7f3a\u9677\u7684\u533a\u522b\u5316\u5b66\u4e60\n\n- **\u5783\u573e\u548c\u6bdb\u523a\u7279\u5f81\u4e00\u822c\u66f4\u6742\u4e71\u65e0\u7ae0\uff0c\u7eb9\u7406\u548c\u5f62\u72b6\u6bd4\u5b57\u4f53\u66f4\u968f\u673a\u7c97\u7cd9**\uff1b\n- \u9884\u5904\u7406\u53bb\u566a\u80fd\u5f31\u5316\u7ec6\u5c0f\u5b64\u7acb\u70b9\uff0c\u4f46\u4fdd\u7559\u6574\u4f53\u7eb9\u7406\u4e0d\u660e\u663e\u4e00\u81f4\u7684\u7279\u5f81\uff1b\n- PatchCore\u901a\u8fc7\u6bd4\u8f83patch\u7279\u5f81\uff08\u591a\u5c42\u6b21\u7ec6\u8282\uff09\uff0c\u5f02\u5e38patch\u5bf9\u5e94\u7eb9\u7406\u4e0d\u7b26\u5408\u6b63\u5e38\u6837\u672c\u7684\u5178\u578b\u7ed3\u6784\uff0c\u81ea\u7136\u88ab\u6a21\u578b\u68c0\u6d4b\u5230\u3002\n\n---\n\n## 6. \u7ed3\u5408PatchCore\u7684\u6267\u884c\u6d41\u7a0b\uff08\u9884\u5904\u7406\u5982\u4f55\u8854\u63a5\uff09\n\n```\n\u6444\u50cf\u5934/\u624b\u673a\u62cd\u7167 -> \u56fe\u50cf\u9884\u5904\u7406\uff08\u88c1\u526a/\u53bb\u566a/\u589e\u5f3a\uff09 -> \u7edf\u4e00\u5c3a\u5bf8\u4e14\u5f52\u4e00\u5316 -> \u9001\u5165PatchCore\u7684backbone -> \u63d0\u53d6patch\u7279\u5f81 -> \u6784\u5efa\u6b63\u5e38\u6837\u672c\u7279\u5f81\u5e93 -> \u63a8\u7406\u65f6\u8ba1\u7b97\u76f8\u4f3c\u5ea6\u5f97\u5f02\u5e38\u70ed\u529b\u56fe -> \u627e\u5f02\u5e38\u533a\u57df -> \u753b\u6846\n```\n\n---\n\n## 7. \u63a8\u8350\u53c2\u8003\u4ee3\u7801\u7247\u6bb5\uff08\u56fe\u50cf\u9884\u5904\u7406\u90e8\u5206\uff09\n\n```python\nimport cv2\nimport numpy as np\n\ndef preprocess_image(img_path, size=(256, 256)):\n img = cv2.imread(img_path)\n \n # \u8f6c\u7070\u5ea6\u56fe\n gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n\n # \u76f4\u65b9\u56fe\u5747\u8861\u5316\u589e\u5f3a\u5bf9\u6bd4\u5ea6\n clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8))\n enhanced = clahe.apply(gray)\n\n # \u4e2d\u503c\u6ee4\u6ce2\u53bb\u566a\n denoised = cv2.medianBlur(enhanced, 3)\n\n # \u81ea\u9002\u5e94\u9608\u503c\u4e8c\u503c\u5316\u7a81\u51fa\u6587\u5b57\uff08\u53ef\u6839\u636e\u62cd\u6444\u6761\u4ef6\u8c03\u6574\uff09\n binary = cv2.adaptiveThreshold(\n denoised, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,\n cv2.THRESH_BINARY_INV, 11, 2)\n\n # \u5f62\u6001\u5b66\u5f00\u8fd0\u7b97\u53bb\u9664\u5b64\u7acb\u5c0f\u70b9\u566a\u58f0\n kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,2))\n clean = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=1)\n\n # \u7edf\u4e00\u5c3a\u5bf8\n resized = cv2.resize(clean, size)\n\n return resized\n```\n\n\u8fd9\u6bb5\u4ee3\u7801\u80fd\u8f83\u597d\u63d0\u5347\u5b57\u4f53\u5bf9\u6bd4\u5ea6\uff0c\u6291\u5236\u566a\u58f0\uff0c\u65b9\u4fbf\u6a21\u578b\u5b66\u4e60\u3002\n\n---\n\n## 8. \u540e\u7eed\u5efa\u8bae\n\n- **\u53cd\u590d\u89c2\u5bdf\u9884\u5904\u7406\u6548\u679c**\uff0c\u591a\u753b\u4e2d\u95f4\u6b65\u9aa4\u56fe\u7247\uff0c\u786e\u8ba4\u5b57\u4f53\u6e05\u6670\uff0c\u80cc\u666f\u5e72\u51c0\uff1b\n- **\u91c7\u96c6\u66f4\u591a\u6b63\u5e38\u6837\u672c\uff0c\u5f02\u6784\u6837\u672c\u6ee1\u8db3\u6a21\u578b\u6cdb\u5316**\uff1b\n- \u5982\u679c\u6761\u4ef6\u5141\u8bb8\uff0c\u7ed3\u5408\u5e26\u6807\u7b7e\u7684\u5f02\u5e38\uff08\u5c11\u91cf\uff09\u505a\u9a8c\u8bc1\u8bc4\u4f30\u548c\u5fae\u8c03\uff1b\n- \u5b66\u4e60OpenCV\u548c\u6570\u5b57\u56fe\u50cf\u5904\u7406\u57fa\u7840\uff0c\u624d\u80fd\u7075\u6d3b\u8c03\u8bd5\u9884\u5904\u7406\u65b9\u6848\uff0c\u63d0\u5347\u6a21\u578b\u6548\u679c\u3002\n\n---\n\n# \u603b\u7ed3\n\n| \u65b9\u9762 | \u91cd\u70b9\u8981\u70b9 |\n|------------------|----------------------------------------------------------------|\n| \u9884\u5904\u7406\u76ee\u6807 | \u7a81\u51fa\u5b57\u4f53\u7ed3\u6784\uff0c\u53bb\u9664\u80cc\u666f\u548c\u566a\u70b9\uff0c\u7edf\u4e00\u5c3a\u5ea6\uff0c\u589e\u5f3a\u56fe\u50cf\u5bf9\u6bd4\u5ea6 |\n| \u5b66\u5230\u7684\u6b63\u5e38\u7279\u5f81 | \u5b57\u4f53\u7684\u7b14\u753b\u5f62\u72b6\u3001\u7eb9\u7406\u8fde\u7eed\u6027\u548c\u6574\u4f53\u6392\u5e03\u4e00\u81f4\u6027\uff0c\u53bb\u7eb9\u7406\u3001\u6742\u70b9\u3001\u6bdb\u523a\u7684\u968f\u673a\u5f02\u5e38 |\n| \u5173\u952e\u5904\u7406\u65b9\u6cd5 | \u7070\u5ea6\u8f6c\u6362\u3001\u76f4\u65b9\u56fe\u5747\u8861\u3001\u6ee4\u6ce2\u964d\u566a\u3001\u81ea\u9002\u5e94\u4e8c\u503c\u5316\u3001\u5f62\u6001\u5b66\u5f00\u8fd0\u7b97\uff08\u53bb\u566a\u58f0\uff09 |\n| \u8bad\u7ec3\u6a21\u578b\u65f6\u7684\u8f93\u5165 | \u9884\u5904\u7406\u8fc7\u7684\u5355\u901a\u9053\u3001\u7edf\u4e00\u5c3a\u5bf8\u56fe\u50cf\uff0c\u4fdd\u8bc1\u591a\u5f20\u6b63\u5e38\u56fe\u201c\u4e00\u81f4\u6027\u201d |\n| \u5f02\u5e38\u68c0\u6d4b\u539f\u7406 | PatchCore\u7528\u7279\u5f81\u5339\u914d\u5dee\u5f02\u68c0\u6d4b\u5f02\u5e38\u533a\u57df\uff0c\u7f3a\u9677\u4e0e\u6b63\u5e38\u5206\u5e03\u5dee\u5f02\u5927\u5bb9\u6613\u88ab\u6807\u8bb0 |\n\n\u8fd9\u6837\uff0c\u6a21\u578b\u8bad\u7ec3\u624d\u51c6\u786e\uff0c\u5f02\u5e38\u68c0\u6d4b\u624d\u7a33\u5b9a\uff0c\u7f3a\u9677\u8bc6\u522b\u624d\u80fd\u51c6\u786e\u53ef\u9760\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u80fd\u5e2e\u4f60\u8fdb\u4e00\u6b65\u5199**\u9884\u5904\u7406+PatchCore\u8bad\u7ec3\u7684\u793a\u8303\u4ee3\u7801**\uff0c\u6216\u8005\u52a8\u6001\u8c03\u53c2\u5efa\u8bae\uff0c\u751a\u81f3\u5e2e\u4f60\u4e00\u6b65\u6b65\u8c03\u8bd5\u6570\u636e\u9884\u5904\u7406\u90e8\u5206\uff0c\u6b22\u8fce\u544a\u8bc9\u6211\uff01\nUser: \u53ef\u4ee5\u544a\u8bc9\u6211\u4e00\u4e0b\u600e\u4e48\u5199\uff0c\u6211\u7814\u7a76\u7814\u7a76\nUser: \u9700\u8981\u4e0b\u8f7d\u90a3\u4e9b\u5e93\uff0c\u5982\u4f55\u7ba1\u7406\u4f9d\u8d56\uff0c\u5b8c\u6210\u8fd9\u4e2a\u9879\u76ee\u5fc5\u987b\u8981\u4e0b\u8f7d\u7684\u5e93\u6709\u4ec0\u4e48\uff0c\u7248\u672c\u6709\u8981\u6c42\u5417\uff0c\u6559\u4e00\u4e0b\u6211\u600e\u4e48\u7528anormalib\u6765\u8bad\u7ec3\uff0c\u600e\u4e48\u5199\u4ee3\u7801\uff0c\u600e\u4e48\u8bbe\u8ba1\u601d\u8def\nUser: \u544a\u8bc9\u6211\u600e\u4e48\u5199\uff0c\u7814\u7a76\u4e00\u4e0b\nAssistant: \u597d\u7684\uff01\u6211\u7ed9\u4f60\u4e00\u4e2a\u5b8c\u6574\u4e14\u8be6\u7ec6\u7684\u6307\u5bfc\uff0c\u5e2e\u52a9\u4f60\u5feb\u901f\u4e0a\u624b\u7528 **`anomalib`** \u505a\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u9879\u76ee\uff08\u4ee5\u6d41\u6c34\u7ebf\u5370\u5237\u7f3a\u9677\u68c0\u6d4b\u4e3a\u4f8b\uff09\uff0c\u5305\u62ec\u4f9d\u8d56\u5b89\u88c5\u3001\u9879\u76ee\u8bbe\u8ba1\u601d\u8def\u548c\u793a\u8303\u4ee3\u7801\u3002\n\n---\n\n# \u4e00\u3001\u73af\u5883\u51c6\u5907\u4e0e\u4f9d\u8d56\u7ba1\u7406\n\n## 1. \u63a8\u8350Python\u7248\u672c\n- Python 3.7 - 3.9 \u4e4b\u95f4\u6bd4\u8f83\u7a33\u5b9a\uff0c\u5efa\u8bae\u7528Python 3.8\n\n## 2. \u521b\u5efa\u865a\u62df\u73af\u5883\uff08\u63a8\u8350\uff09\n\u4e3a\u4e86\u907f\u514d\u5e93\u51b2\u7a81\uff0c\u5efa\u8bae\u7528\u865a\u62df\u73af\u5883\u7ba1\u7406\u4f9d\u8d56\uff1a\n\n```bash\n# Windows\npython -m venv anomalib-env\nanomalib-env\\Scripts\\activate\n\n# macOS/Linux\npython3 -m venv anomalib-env\nsource anomalib-env/bin/activate\n```\n\n## 3. \u5b89\u88c5\u5fc5\u5907\u5e93\n- torch\uff08PyTorch\uff0canomalib\u4f9d\u8d56\uff09\n- anomalib\n- \u5176\u5b83\u57fa\u7840\u5e93\uff1aopencv-python\uff0cmatplotlib\u7b49\n\n\u76ee\u524d**anomalib\u5b98\u65b9\u5efa\u8bae\u4f9d\u8d56\uff1a**\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 # \u6839\u636e\u4f60\u7684GPU\u8c03\u6574,\u65e0GPU\u9009\u62e9cpu\u7248\u672c\npip install anomalib omegaconf hydra-core matplotlib opencv-python\n```\n\n> \u6ce8\uff1a \n> - \u8fd9\u91cc\u793a\u4f8b\u662f CUDA 11.7 \u7248\u672c\u7684 PyTorch\uff0c\u5982\u679c\u4f60\u6ca1\u6709GPU\u6216\u4e0d\u540c\u7248\u672c\uff0c\u8bf7\u8bbf\u95ee [PyTorch\u5b98\u7f51](https://pytorch.org/) \u67e5\u8be2\u5408\u9002\u547d\u4ee4\u3002 \n> - `anomalib`\u7248\u672c\u5efa\u8bae\u4f7f\u7528\u6700\u65b0\u7a33\u5b9a\u7248\u672c\uff0c2024\u5e74\u8d77\u901a\u5e38\u662f `anomalib>=1.0.0`\u3002\n\n---\n\n# \u4e8c\u3001\u9879\u76ee\u76ee\u5f55\u7ed3\u6784\u793a\u8303\n\n```\nyour_project/\n\u2502\n\u251c\u2500\u2500 data/\n\u2502 \u251c\u2500\u2500 train/\n\u2502 \u2502 \u2514\u2500\u2500 good/ # \u8bad\u7ec3\u7528\u6b63\u5e38\u6837\u672c\n\u2502 \u251c\u2500\u2500 test/\n\u2502 \u251c\u2500\u2500 good/ # \u6d4b\u8bd5\u6b63\u5e38\u56fe\uff08\u53ef\u9009\uff09\n\u2502 \u251c\u2500\u2500 defect_type_1/ # \u7f3a\u96771\u7c7b\u578b\u56fe\u7247\n\u2502 \u251c\u2500\u2500 defect_type_2/ # \u7f3a\u96772\u7c7b\u578b\u56fe\u7247\n\u2502 \u2514\u2500\u2500 ...\n\u2502\n\u251c\u2500\u2500 config.yaml # anomalib\u914d\u7f6e\u6587\u4ef6\n\u251c\u2500\u2500 train.py # \u8bad\u7ec3\u811a\u672c\n\u251c\u2500\u2500 infer.py # \u63a8\u7406\u811a\u672c\n\u2514\u2500\u2500 preprocess.py # \u9884\u5904\u7406\u793a\u4f8b\u4ee3\u7801\uff08\u53ef\u9009\uff09\n```\n\n---\n\n# \u4e09\u3001\u8bbe\u8ba1\u601d\u8def\n\n### 1. \u6570\u636e\u51c6\u5907\n- \u4e3b\u8981\u51c6\u5907\u6b63\u5e38\u6837\u672c\uff08`train/good/`\uff09\u4f5c\u4e3a\u8bad\u7ec3\u96c6\uff0c\u4e0d\u9700\u8981\u5f02\u5e38\u6807\u7b7e\uff1b\n- \u6d4b\u8bd5\u96c6\u542b\u6b63\u5e38\u548c\u5f02\u5e38\u56fe\u7247\uff0c\u7528\u4e8e\u8bc4\u4f30\u6a21\u578b\u63a8\u7406\u6548\u679c\u3002\n\n### 2. \u9884\u5904\u7406\n- \u53ef\u4ee5\u5199\u4e00\u4e2a\u5c0f\u811a\u672c\u505a\u9884\u5904\u7406\uff1a\u88c1\u526a\u3001\u5c3a\u5bf8\u7edf\u4e00\u3001\u7070\u5ea6\u8f6c\u6362\u7b49\uff0c\u51c6\u5907\u5e72\u51c0\u89c4\u8303\u7684\u8bad\u7ec3\u6570\u636e\uff1b\n- \u9884\u5904\u7406\u7ed3\u679c\u653e\u5728`data/train/good/`\u76ee\u5f55\uff0c \n- \u4e0d\u4e00\u5b9a\u975e\u8981\u5148\u9884\u5904\u7406\uff0c\u53ea\u662f\u5efa\u8bae\u5bf9\u6570\u636e\u8fdb\u884c\u8d28\u91cf\u628a\u63a7\u3002\n\n### 3. \u6a21\u578b\u8bad\u7ec3\n- \u7528`anomalib`\u5185\u7f6e\u63a5\u53e3\uff0c\u52a0\u8f7dPatchCore\u6a21\u578b\uff08\u6216\u770b\u4f60\u60f3\u7528\u7684\u5176\u4ed6\u6a21\u578b\uff09\uff1b\n- \u914d\u5408\u914d\u7f6e\u6587\u4ef6\uff0c\u8bad\u7ec3\u6b63\u5e38\u6837\u672c\uff0c\u5efa\u7acb\u6b63\u5e38\u7279\u5f81\u5e93\u3002\n\n### 4. \u6a21\u578b\u63a8\u7406\n- \u52a0\u8f7d\u8bad\u7ec3\u597d\u7684\u6a21\u578b\uff1b\n- \u5bf9\u65b0\u56fe\u50cf\u505a\u5f02\u5e38\u68c0\u6d4b\uff0c\u8f93\u51fa\u5f02\u5e38\u70ed\u529b\u56fe\u548c\u5f02\u5e38\u5206\u6570\uff1b\n- \u7ed3\u5408\u70ed\u529b\u56fe\u9608\u503c\uff0c\u63d0\u53d6\u7f3a\u9677\u533a\u57df\u5e76\u505a\u6807\u6ce8\u6846\u3002\n\n---\n\n# \u56db\u3001\u914d\u7f6e\u6587\u4ef6 `config.yaml` \u793a\u4f8b\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18 # \u4e3b\u5e72\u7f51\u7edc\uff0c\u63a8\u8350resnet18\n input_size: 256 # \u56fe\u50cf\u5c3a\u5bf8\uff0c\u548c\u9884\u5904\u7406\u4e00\u81f4\n embedding_method: random_projection\n\ntraining:\n batch_size: 8\n max_epochs: 20\n precision: 16 # \u534a\u7cbe\u5ea6\u8bad\u7ec3\uff0c\u9700GPU\u652f\u6301\n seed: 42\n save_checkpoint: True\n\ndataset:\n name: custom\n path: ./data\n input_size: 256 # \u8ddf\u6a21\u578b\u4fdd\u6301\u4e00\u81f4\n\nlogger:\n wandb:\n project: anomalib-demo # \u5982\u4e0d\u4f7f\u7528wandb\u53ef\u7559\u7a7a\n\ntrainer:\n accelerator: gpu # or \"cpu\"\n devices: 1\n max_epochs: 20\n```\n\n---\n\n# \u4e94\u3001\u8bad\u7ec3\u811a\u672c\u793a\u8303 `train.py`\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\nimport os\n\ndef train_anomalib(config_path):\n # \u52a0\u8f7d\u914d\u7f6e\n config = OmegaConf.load(config_path)\n\n # \u83b7\u53d6\u6570\u636e\u52a0\u8f7d\u5668\n train_loader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n\n # \u521d\u59cb\u5316\u6a21\u578b\n model = get_model(config.model)\n\n # \u521b\u5efa\u8bad\u7ec3\u5668\n trainer = get_trainer(config.trainer)\n\n # \u8bad\u7ec3\u6a21\u578b\n trainer.fit(model=model, train_dataloader=train_loader)\n\n # \u4fdd\u5b58\u6700\u4f18\u6a21\u578b\u6743\u91cd\n checkpoint_path = \"patchcore_best.ckpt\"\n trainer.save_checkpoint(checkpoint_path)\n print(f\"\u6a21\u578b\u4fdd\u5b58\u81f3 {checkpoint_path}\")\n\nif __name__ == \"__main__\":\n CONFIG_PATH = os.path.join(os.path.dirname(__file__), \"config.yaml\")\n train_anomalib(CONFIG_PATH)\n```\n\n---\n\n# \u516d\u3001\u63a8\u7406\u811a\u672c\u793a\u8303 `infer.py`\n\n```python\nimport os\nimport matplotlib.pyplot as plt\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\nimport torch\n\ndef infer_image(config_path, checkpoint_path, image_path):\n config = get_configurable_parameters(config_path)\n\n model = get_model(config.model)\n\n # \u52a0\u8f7d\u8bad\u7ec3\u597d\u7684\u6743\u91cd\n checkpoint = torch.load(checkpoint_path)\n model.load_state_dict(checkpoint['state_dict'])\n model.eval()\n\n # \u521b\u5efa\u63a8\u7406\u5668\n inferencer = Inferencer(config, model)\n\n results = inferencer.infer(image_path)\n\n anomaly_map = results[\"anomaly_map\"]\n score = results[\"score\"]\n\n # \u53e0\u52a0\u5f02\u5e38\u70ed\u529b\u56fe\u53ef\u89c6\u5316\n img = plt.imread(image_path)\n plt.imshow(img)\n plt.imshow(anomaly_map, cmap='jet', alpha=0.5)\n plt.colorbar()\n plt.title(f\"Anomaly score: {score:.3f}\")\n plt.axis('off')\n plt.show()\n\nif __name__ == \"__main__\":\n config_path = \"./config.yaml\"\n checkpoint_path = \"./patchcore_best.ckpt\"\n image_path = \"./data/test/defect_type_1/sample1.png\"\n\n infer_image(config_path, checkpoint_path, image_path)\n```\n\n---\n\n# \u4e03\u3001\u7b80\u8981\u8bf4\u660e\u53caTips\n\n- **\u56fe\u50cf\u9884\u5904\u7406** \n \u4f60\u53ef\u4ee5\u5199\u5355\u72ec\u811a\u672c`preprocess.py`\uff0c\u5bf9\u6240\u6709\u8bad\u7ec3\u56fe\u7247\u7edf\u4e00\u88c1\u526a\u3001\u7f29\u653e\u548c\u589e\u5f3a\uff1b`anomalib`\u9ed8\u8ba4\u4f1a\u5728\u52a0\u8f7d\u65f6\u505a\u57fa\u672c\u7684resize\u548ctensor\u8f6c\u6362\u3002\n\n- **\u6570\u636e\u91cf\u5f71\u54cd** \n \u76ee\u524d20\u5f20\u6570\u636e\u91cf\u504f\u5c11\uff0c\u5efa\u8bae\u540e\u7eed\u589e\u52a0\u62cd\u6444\u6837\u672c\u4ee5\u83b7\u5f97\u66f4\u6cdb\u5316\u7684\u6a21\u578b\u7ed3\u679c\u3002\n\n- **\u786c\u4ef6\u9700\u6c42** \n \u5982\u679c\u6709GPU\uff0c\u8bad\u7ec3\u901f\u5ea6\u66f4\u5feb\uff1b\u65e0GPU\u4e5f\u80fd\u8dd1\u4f46\u6162\u3002\n\n- **\u6a21\u578b\u66ff\u6362** \n \u53ef\u4ee5\u8bd5\u8bd5`patchcore`\u4e4b\u5916\u7684\u6a21\u578b\uff0c\u5982`padim`\uff0c\u53ea\u9700\u66f4\u6362\u914d\u7f6e\u3002\n\n---\n\n# \u516b\u3001\u603b\u7ed3\u4f60\u5fc5\u5907\u5b89\u88c5\u5305\u53ca\u7248\u672c\u53c2\u8003\n\n| \u5e93 | \u7248\u672c\u5efa\u8bae | \u4f5c\u7528 |\n|---------------|-------------|--------------------|\n| Python | 3.7 - 3.9 | \u8fd0\u884c\u73af\u5883 |\n| torch | 1.13+ | \u6df1\u5ea6\u5b66\u4e60\u6846\u67b6 |\n| torchvision | 0.14+ | \u9884\u8bad\u7ec3\u6a21\u578b\u548c\u56fe\u50cf\u64cd\u4f5c\u652f\u6301 |\n| anomalib | >= 1.0.0 | \u5f02\u5e38\u68c0\u6d4b\u6846\u67b6 |\n| omegaconf | >= 2.1.1 | \u914d\u7f6e\u7ba1\u7406 |\n| hydra-core | >= 1.1.1 | \u914d\u7f6e\u63a7\u5236 |\n| matplotlib | >= 3.5 | \u7ed3\u679c\u53ef\u89c6\u5316 |\n| opencv-python | >= 4.5 | \u56fe\u50cf\u8bfb\u53d6\u3001\u9884\u5904\u7406\u548c\u5904\u7406 |\n| requests | - | \u7f51\u7edc\u8bf7\u6c42\uff08\u5982\u6709\u9700\u8981\uff09 |\n\n---\n\n# \u4e5d\u3001\u53c2\u8003\u5b66\u4e60\u8d44\u6599\u548c\u6587\u6863\n\n- [anomalib\u5b98\u65b9GitHub](https://github.com/openvinotoolkit/anomalib)\n- [PyTorch \u5b98\u7f51](https://pytorch.org/)\n- OpenCV \u4e2d\u6587\u6559\u7a0b\uff08\u91cd\u70b9\u5b66\u4e60\u56fe\u50cf\u9884\u5904\u7406\u3001\u5f62\u6001\u5b66\u53ca\u8f6e\u5ed3\u68c0\u6d4b\uff09\n- PatchCore\u8bba\u6587\uff1a[PatchCore: Patch-Level Representation Learning for Anomaly Detection and Localization](https://arxiv.org/abs/2111.09115)\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u4e00\u6b65\u6b65\u5199**\u4ece\u6570\u636e\u9884\u5904\u7406\u5230\u8bad\u7ec3\u63a8\u7406\u7684\u5b8c\u6574\u4ee3\u7801\u793a\u8303\u5de5\u7a0b**\uff0c\u6216\u8005\u5e2e\u4f60\u8c03\u8bd5\u8bad\u7ec3\u4e2d\u7684\u95ee\u9898\u3002\n\n---\n\n# \u5feb\u901f\u542f\u52a8\u547d\u4ee4\u603b\u7ed3\n\n```bash\n# \u6fc0\u6d3b\u865a\u62df\u73af\u5883\nsource anomalib-env/bin/activate\n\n# \u5b89\u88c5\u4f9d\u8d56\npip install torch torchvision # \u7248\u672c\u6839\u636eGPU\u60c5\u51b5\u8c03\u6574\npip install anomalib omegaconf hydra-core matplotlib opencv-python\n\n# \u8bad\u7ec3\npython train.py\n\n# \u63a8\u7406\npython infer.py\n```\n\n---\n\n\u968f\u65f6\u544a\u8bc9\u6211\u4f60\u5e0c\u671b\u5e2e\u4f60\u5199\u5177\u4f53\u4ee3\u7801\u6216\u8005\u8c03\u8bd5\u4efb\u4f55\u95ee\u9898\uff01\u795d\u4f60\u9879\u76ee\u987a\nUser: \u9700\u8981\u4e0b\u8f7d\u90a3\u4e9b\u5e93\uff0c\u6559\u4e00\u4e0b\u6211\u600e\u4e48\u7528anormalib\u6765\u5199\u8bad\u7ec3\u4ee3\u7801\uff0c\u600e\u4e48\u5199\uff0c\u5982\u4f55\u7ba1\u7406\u4f9d\u8d56\nAssistant: \u597d\u7684\uff0c\u9488\u5bf9\u4f60\u7528`anomalib`\u505a\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u9879\u76ee\uff0c\u6211\u7ed9\u4f60\u4e00\u4e2a\u5c3d\u91cf\u8be6\u7ec6\u4e14\u5b9e\u64cd\u6027\u5f3a\u7684\u5165\u95e8\u6307\u5bfc\uff0c\u5305\u542b\uff1a\n\n- \u5fc5\u987b\u5b89\u88c5\u7684Python\u5e93\u4ee5\u53ca\u7248\u672c \n- \u5982\u4f55\u7ba1\u7406\u4f9d\u8d56\uff08\u63a8\u8350\u7528\u865a\u62df\u73af\u5883\u548c`requirements.txt`\uff09 \n- \u5982\u4f55\u5feb\u901f\u5199\u51fa\u4f7f\u7528`anomalib`\u7684\u8bad\u7ec3\u4ee3\u7801\u793a\u4f8b\n\n---\n\n# \u4e00\u3001\u5fc5\u987b\u5b89\u88c5\u7684\u5e93\u548c\u7248\u672c\n\n| \u5e93\u540d | \u63a8\u8350\u7248\u672c | \u8bf4\u660e |\n|-----------------|------------------|-------------------------------------|\n| python | 3.7 \u5230 3.9 | python\u7248\u672c\u5efa\u8bae3.8\u6700\u597d |\n| torch | \u4e0e\u663e\u5361\u5bf9\u5e94\u7248\u672c | \u5982\u65e0GPU\u53ef\u9009cpu\u7248\u672c, \u4f8b\u5982`1.13.1+cpu` |\n| torchvision | \u4e0etorch\u7248\u672c\u5339\u914d | \u56fe\u50cf\u9884\u5904\u7406\u53ca\u9884\u8bad\u7ec3\u6a21\u578b |\n| anomalib | >=1.0.0 | \u5f02\u5e38\u68c0\u6d4b\u6846\u67b6\uff0c\u6838\u5fc3 |\n| omegaconf | >=2.1.1 | \u914d\u7f6e\u7ba1\u7406\u5de5\u5177 |\n| hydra-core | >=1.1.1 | \u914d\u7f6e\u4f18\u5316\u4e0e\u7ba1\u7406 |\n| matplotlib | >=3.5 | \u8bad\u7ec3\u7ed3\u679c\u53ef\u89c6\u5316 |\n| opencv-python | >=4.5 | \u56fe\u50cf\u8bfb\u53d6\u3001\u9884\u5904\u7406\u3001\u5904\u7406 |\n\n---\n\n# \u4e8c\u3001\u521b\u5efa\u865a\u62df\u73af\u5883\u548c\u7ba1\u7406\u4f9d\u8d56\n\n1. **\u521b\u5efa\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883**\n\n```bash\n# Windows\npython -m venv anomalib-env\nanomalib-env\\Scripts\\activate\n\n# macOS/Linux\npython3 -m venv anomalib-env\nsource anomalib-env/bin/activate\n```\n\n2. **\u751f\u6210`requirements.txt`\u6587\u4ef6\uff08\u793a\u8303\u5185\u5bb9\uff09**\n\n```txt\ntorch==1.13.1\ntorchvision==0.14.1\nanomalib>=1.0.0\nomegaconf>=2.1.1\nhydra-core>=1.1.1\nmatplotlib>=3.5\nopencv-python>=4.5\n```\n\n3. **\u5b89\u88c5\u4f9d\u8d56**\n\n```bash\npip install -r requirements.txt\n```\n\n> \u6ce8\u610f\uff1a \n> - PyTorch\u7248\u672c\u8bf7\u6839\u636e\u4f60\u7684\u663e\u5361\u548cCUDA\u7248\u672c\u5728PyTorch\u5b98\u7f51\u751f\u6210\u5bf9\u5e94\u7684\u5b89\u88c5\u547d\u4ee4\u3002 \n> - \u5982\u679c\u65e0GPU\uff0c\u6539\u7528CPU\u7248\u672c\uff0c\u5982`pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu`\n\n---\n\n# \u4e09\u3001\u5982\u4f55\u5199\u8bad\u7ec3\u4ee3\u7801 \u7528 `anomalib` \u4e3e\u4f8b\uff08PatchCore\uff09\n\n## 1. \u914d\u7f6e\u6587\u4ef6\uff08\u4f8b\u5982\uff1a`config.yaml`\uff09\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18\n input_size: 256\n embedding_method: random_projection\n\ntraining:\n batch_size: 8\n max_epochs: 20\n precision: 16\n seed: 42\n save_checkpoint: True\n\ndataset:\n name: custom\n path: ./data\n input_size: 256\n\nlogger:\n wandb: {}\n\ntrainer:\n accelerator: gpu # \u6ca1GPU\u6539\u4e3acpu\n devices: 1\n max_epochs: 20\n```\n\n## 2. \u8bad\u7ec3\u811a\u672c\uff08`train.py`\uff09\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train(config_path: str):\n # \u8bfb\u53d6\u914d\u7f6e\n config = OmegaConf.load(config_path)\n\n # \u83b7\u53d6\u8bad\u7ec3\u96c6\u6570\u636e\u52a0\u8f7d\u5668(\u53ea\u52a0\u8f7d\u8bad\u7ec3\u65f6\u6b63\u5e38\u6837\u672c)\n train_dataloader = get_dataloader(config.dataset, split=\"train\", batch_size=config.training.batch_size)\n\n # \u521d\u59cb\u5316\u6a21\u578b\uff08PatchCore\uff09\n model = get_model(config.model)\n\n # \u521b\u5efa\u8bad\u7ec3\u5668\uff0c\u4f20\u5165\u8bad\u7ec3\u914d\u7f6e\n trainer = get_trainer(config.trainer)\n\n # \u6267\u884c\u8bad\u7ec3\n trainer.fit(model=model, train_dataloader=train_dataloader)\n\n # \u4fdd\u5b58\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u6743\u91cd\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n print(\"\u6a21\u578b\u8bad\u7ec3\u5b8c\u6210\u5e76\u4fdd\u5b58\uff01\")\n\nif __name__ == \"__main__\":\n train(\"config.yaml\")\n```\n\n---\n\n# \u56db\u3001\u603b\u7ed3\u548c\u4f7f\u7528\u6d41\u7a0b\n\n1. **\u51c6\u5907\u6570\u636e\u96c6\u76ee\u5f55\u7ed3\u6784**\n\n```\ndata/\n \u251c\u2500 train/\n \u2502 \u2514\u2500 good/ # \u6b63\u5e38\u6837\u672c\u56fe\u7247\uff0cPatchCore\u53ea\u9700\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\n \u2514\u2500 test/\n \u251c\u2500 good/\n \u251c\u2500 defect_type_1/\n \u2514\u2500 defect_type_2/\n```\n\n2. **\u5199\u597d\u914d\u7f6e\u6587\u4ef6 `config.yaml`**\n\n3. **\u5b89\u88c5\u4f9d\u8d56\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883**\n\n4. **\u7528\u4e0a\u9762`train.py`\u8bad\u7ec3\u6a21\u578b**\n\n5. \u4e4b\u540e\u5199\u63a8\u7406\u811a\u672c\u6d4b\u8bd5\uff08\u53ef\u7528`anomalib`\u7684`Inferencer`\u7c7b\uff09\n\n---\n\n# \u4e94\u3001\u63a8\u8350\u5b66\u4e60\u548c\u8c03\u8bd5\u6b65\u9aa4\n\n- \u5148\u8dd1\u901a\u5b98\u65b9\u793a\u4f8b\u7684\u6570\u636e\u96c6\uff08MVTec\u7b49\uff09\u6765\u719f\u6089`anomalib`\n- \u5b8c\u5584\u81ea\u5df1\u7684\u6570\u636e\u9884\u5904\u7406\uff0c\u5bf9\u6570\u636e\u505a\u5c3a\u5bf8\u7edf\u4e00\uff0c\u53bb\u566a\u589e\u5f3a\n- \u8c03\u6574\u914d\u7f6e\u6587\u4ef6\u53c2\u6570\u8bd5\u9a8c\u6548\u679c\uff0c\u5982`batch_size`, `max_epochs`\u7b49\n- \u5229\u7528`anomalib`\u63d0\u4f9b\u7684\u53ef\u89c6\u5316\u63a5\u53e3\u67e5\u770b\u5f02\u5e38\u56fe\u548c\u70ed\u529b\u56fe\n\n---\n\n# \u516d\u3001\u53c2\u8003\u94fe\u63a5\n\n- anomalib\u5b98\u65b9\u5730\u5740\uff1a[https://github.com/openvinotoolkit/anomalib](https://github.com/openvinotoolkit/anomalib) \n- PyTorch\u5b89\u88c5\uff1a[https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/) \n- OpenCV\u6559\u7a0b\uff1a[https://opencv-python-tutroals.readthedocs.io/en/latest/](https://opencv-python-tutroals.readthedocs.io/en/latest/)\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u5b8c\u6574\u7684\u793a\u8303\u9879\u76ee\u4ee3\u7801\u6a21\u677f\uff0c\u6216\u8005\u7ed9\u4f60\u8bb2\u89e3\u67d0\u90e8\u5206\u7ec6\u8282\uff0c\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: \u7528labelme\u600e\u4e48\u6807\u7f3a\u9677\u554a\uff0c\u53c8\u600e\u4e48\u5c06\u7f3a\u9677\u56fe\u7247\u548c\u5bf9\u5e94\u6807\u7684\u4e8c\u8fdb\u5236\u63a9\u7801\u5bf9\u5e94\u8d77\u6765\nAssistant: \u597d\u7684\uff0c\u6211\u7ed9\u4f60\u8be6\u7ec6\u8bf4\u4e00\u4e0b\u7528 **LabelMe** \u6807\u6ce8\u7f3a\u9677\u7684\u65b9\u6cd5\uff0c\u4ee5\u53ca\u5982\u4f55\u628a\u7f3a\u9677\u56fe\u7247\u548c\u5bf9\u5e94\u7684\u63a9\u7801\uff08\u4e8c\u8fdb\u5236\u63a9\u7801\uff09\u5bf9\u5e94\u8d77\u6765\uff0c\u65b9\u4fbf\u4f60\u540e\u7eed\u505a\u5f02\u5e38\u5b9a\u4f4d\u68c0\u6d4b\u548c\u53ef\u89c6\u5316\u3002\n\n---\n\n# \u4e00\u3001\u7528 LabelMe \u6807\u6ce8\u7f3a\u9677\u6b65\u9aa4\n\n1. **\u5b89\u88c5 LabelMe**\n\n```bash\npip install labelme\n```\n\u4e5f\u53ef\u4ee5\u4ece [LabelMe\u5b98\u7f51](https://github.com/wkentaro/labelme) \u4e0b\u8f7d\u684c\u9762\u7248\u672c\uff0c\u6709\u56fe\u5f62\u754c\u9762\u65b9\u4fbf\u6807\u6ce8\u3002\n\n2. **\u542f\u52a8\u6807\u6ce8\u5de5\u5177**\n\n```bash\nlabelme\n```\n\u6253\u5f00\u540e\u9009\u62e9\u4f60\u7684\u7f3a\u9677\u56fe\u7247\u6240\u5728\u7684\u6587\u4ef6\u5939\u3002\n\n3. **\u6807\u6ce8\u7f3a\u9677\u533a\u57df**\n\n- \u6253\u5f00\u4e00\u5f20\u56fe\u7247\u3002\n- \u9009\u62e9\u5de6\u4e0a\u89d2\u7684\u201cCreate Polygon\u201d\u6216\u201cCreate Rectangle\u201d\u5de5\u5177\u3002\n- \u7528\u9f20\u6807\u70b9\u51fb\uff0c\u56f4\u7ed5\u7f3a\u9677\u533a\u57df\u753b\u4e00\u4e2a\u591a\u8fb9\u5f62\uff0c\u5b8c\u6210\u540e\u5173\u95ed\u591a\u8fb9\u5f62\u3002\n- \u5728\u5f39\u51fa\u7a97\u53e3\u586b\u5199\u6807\u7b7e\u540d\uff0c\u4e00\u822c\u5199\u201cdefect\u201d\u6216\u8005\u5177\u4f53\u7684\u7f3a\u9677\u540d\u79f0\uff0c\u6bd4\u5982\u201cscratch\u201d\u3001\u201cblur\u201d\u3001\u201cink stain\u201d\u7b49\u3002\n- \u6807\u6ce8\u5b8c\u6210\u540e\u4fdd\u5b58\uff0c\u8fd9\u4f1a\u751f\u6210\u4e0e\u56fe\u7247\u540c\u540d\u4f46\u540e\u7f00`.json`\u7684\u6807\u6ce8\u6587\u4ef6\u3002\n\n4. **\u6279\u91cf\u6807\u6ce8**\n\n\u4f9d\u6b21\u6807\u6ce8\u6240\u6709\u7f3a\u9677\u56fe\u7247\uff0c\u90fd\u662f\u540c\u6837\u7684\u6d41\u7a0b\u3002\n\n---\n\n# \u4e8c\u3001\u600e\u6837\u5c06\u7f3a\u9677\u56fe\u7247\u548c\u5bf9\u5e94\u7684\u4e8c\u8fdb\u5236\u63a9\u7801\u5bf9\u5e94\u8d77\u6765\n\nLabelMe \u6807\u6ce8\u7684 `.json` \u6587\u4ef6\u4e2d\uff0c\u5b58\u50a8\u4e86\u56fe\u50cf\u4e2d\u6bcf\u4e2a\u6807\u6ce8\u533a\u57df\u7684\u70b9\u96c6\uff08\u591a\u8fb9\u5f62\u9876\u70b9\uff09\u548c\u6807\u7b7e\u540d\u5b57\u3002\u4f60\u53ef\u4ee5\u7528 `labelme` \u81ea\u5e26\u7684\u547d\u4ee4\u884c\u5de5\u5177\u751f\u6210\u5bf9\u5e94\u7684\u63a9\u7801\u56fe\u3002\n\n---\n\n## 1. \u751f\u6210\u63a9\u7801\u56fe\u547d\u4ee4\u793a\u4f8b\n\n```bash\nlabelme_json_to_dataset your_label.json -o output_folder\n```\n\n- \u8fd9\u6761\u547d\u4ee4\u4f1a\u5728 `output_folder` \u751f\u6210\u4e00\u5957\u6587\u4ef6\uff1a\n - `label.png` \u2014 \u6807\u6ce8\u533a\u57df\u7684\u63a9\u7801\u56fe\uff0c\u63a9\u7801\u662f\u4ee5\u4e0d\u540c\u989c\u8272\u6807\u8bb0\u533a\u57df\uff0c\u4e00\u822c\u4e00\u7c7b\u4e00\u4e2a\u989c\u8272\uff1b\n - `label_names.txt` \u2014 \u8bb0\u5f55\u6bcf\u4e2a\u989c\u8272\u5bf9\u5e94\u7684\u6807\u7b7e\u540d\uff1b\n - \u8fd8\u6709\u5176\u4ed6\u4fe1\u606f\u6587\u4ef6\u3002\n\n---\n\n## 2. \u7528Python\u81ea\u52a8\u6279\u91cf\u751f\u6210\u63a9\u7801\n\n\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684Python\u811a\u672c\uff0c\u6279\u91cf\u751f\u6210\u63a9\u7801\u65b9\u4fbf\u4f60\u548c\u56fe\u50cf\u4e00\u4e00\u5bf9\u5e94\uff1a\n\n```python\nimport os\nimport subprocess\n\nlabel_dir = \"./labels\" # \u5b58\u653ejson\u6587\u4ef6\u7684\u76ee\u5f55\noutput_dir = \"./masks\" # \u63a9\u7801\u4fdd\u5b58\u76ee\u5f55\nos.makedirs(output_dir, exist_ok=True)\n\nfor file in os.listdir(label_dir):\n if file.endswith(\".json\"):\n json_path = os.path.join(label_dir, file)\n name = os.path.splitext(file)[0]\n save_path = os.path.join(output_dir, name)\n os.makedirs(save_path, exist_ok=True)\n \n # \u8c03\u7528labelme_json_to_dataset\u547d\u4ee4\n cmd = f\"labelme_json_to_dataset {json_path} -o {save_path}\"\n subprocess.run(cmd, shell=True)\n \n print(f\"\u751f\u6210\u63a9\u7801\u6587\u4ef6\u5939: {save_path}\")\n```\n\n\u6bcf\u4e2a `save_path` \u4e0b\u9762\u4f1a\u6709 `label.png`\uff0c\u8fd9\u5f20\u56fe\u7247\u5c31\u662f\u4e8c\u503c\u5316\u63a9\u7801\uff08\u5982\u679c\u4f60\u53ea\u6807\u4e86\u4e00\u7c7b\u201cdefect\u201d\uff09\u6216\u8005\u591a\u7c7b\u522b\u63a9\u7801\u3002\n\n---\n\n## 3. \u8bfb\u53d6\u63a9\u7801\u793a\u4f8b\uff08Python\uff09\n\n\u4f60\u53ef\u4ee5\u7528 `opencv` \u6216 `PIL` \u6253\u5f00 `label.png`\uff0c\u751f\u6210\u4e8c\u8fdb\u5236\u63a9\u7801\uff1a\n\n```python\nimport cv2\nimport numpy as np\n\nmask_path = \"./masks/img_001/label.png\"\nmask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE) # \u7070\u5ea6\u8bfb\u5165\n\n# \u5982\u679c\u53ea\u6807\u6ce8\u4e86\u5355\u4e00\u7c7b\u522b\uff0c\u63a9\u7801\u4e0a\u7f3a\u9677\u533a\u57df\u4e00\u822c\u4e3a\u767d\u8272(255)\uff0c\u80cc\u666f\u4e3a0\nbinary_mask = np.where(mask > 0, 1, 0).astype(np.uint8)\n\nprint(binary_mask.shape)\n```\n\n\u4f60\u5c31\u80fd\u62ff\u5230\u548c\u539f\u56fe\u5927\u5c0f\u4e00\u81f4\u7684\u4e8c\u503c\uff080/1\uff09\u63a9\u7801\uff0c\u7528\u4e8e\u8bad\u7ec3\u6a21\u578b\u6216\u53ef\u89c6\u5316\u7f3a\u9677\u3002\n\n---\n\n# \u4e09\u3001\u6807\u6ce8\u6587\u4ef6\u548c\u56fe\u7247\u5982\u4f55\u5bf9\u5e94\uff1f\n\n- **\u547d\u540d\u89c4\u8303\u5f88\u91cd\u8981\uff01** \n - \u6807\u6ce8\u6587\u4ef6 `xxx.json` \u5bf9\u5e94\u7684\u56fe\u7247\u4e00\u5b9a\u662f `xxx.jpg`/`xxx.png`\u3002 \n - \u8fd9\u6837\u901a\u8fc7\u89e3\u6790 `.json` \u6587\u4ef6\u751f\u6210\u7684\u63a9\u7801\u624d\u5bf9\u5e94\u6b63\u786e\u7684\u6837\u672c\u56fe\u7247\u3002 \n- \u4f60\u91c7\u96c6\u56fe\u7247\u540e\uff0c\u6700\u597d\u5148\u7edf\u4e00\u547d\u540d\u3002\n\n---\n\n# \u56db\u3001\u5982\u4f55\u7528\u8fd9\u4e9b\u63a9\u7801\u505a\u8bad\u7ec3\uff1f\n\n- **\u4f5c\u4e3a\u76d1\u7763\u5b66\u4e60\uff08\u8bed\u4e49\u5206\u5272\uff09**\uff0c\u63a9\u7801\u544a\u8bc9\u6a21\u578b\u54ea\u4e9b\u50cf\u7d20\u662f\u7f3a\u9677\uff0c\u54ea\u4e9b\u662f\u6b63\u5e38\u3002 \n- \u5bf9\u4e8e`PatchCore`\u8fd9\u79cd\u65e0\u76d1\u7763\u6216\u5f31\u76d1\u7763\u65b9\u6cd5\uff0c\u63a9\u7801\u53ef\u4ee5\u4f5c\u4e3a\u8bc4\u4f30\u9884\u6d4b\u662f\u5426\u51c6\u786e\u7684\u201c\u771f\u5b9e\u6807\u7b7e\u201d\u3002 \n- \u4e5f\u53ef\u4ee5\u7528\u63a9\u7801\u8fdb\u884c\u7f3a\u9677\u53ef\u89c6\u5316\u53e0\u52a0\uff0c\u6f14\u793a\u68c0\u6d4b\u6548\u679c\u3002\n\n---\n\n# \u4e94\u3001\u603b\u7ed3\n\n| \u6b65\u9aa4 | \u8bf4\u660e |\n|-------------------|----------------------------------|\n| \u6807\u6ce8\u7f3a\u9677\u591a\u8fb9\u5f62 | LabelMe\u6253\u5f00\u56fe\u7247\u7528\u591a\u8fb9\u5f62\u7ed8\u5236\u7f3a\u9677\u533a\u57df |\n| \u4fdd\u5b58json | \u6bcf\u5f20\u56fe\u7247\u5bf9\u5e94json\u6587\u4ef6\u4fdd\u5b58\u6807\u6ce8\u4fe1\u606f |\n| \u8f6c\u6362\u63a9\u7801 | \u7528`labelme_json_to_dataset`\u547d\u4ee4\u751f\u6210`label.png` |\n| \u63a9\u7801\u56fe\u7684\u89e3\u6790 | \u8bfb\u53d6`label.png`\u751f\u6210\u4e8c\u8fdb\u5236\u63a9\u7801 |\n| \u63a9\u7801\u4e0e\u56fe\u7247\u5bf9\u5e94 | \u4fdd\u8bc1json\u548c\u539f\u56fe\u6587\u4ef6\u540d\u4e00\u81f4 |\n\n---\n\n### \u63a8\u8350\u8d44\u6599\n\n- LabelMe\u5b98\u65b9\u6587\u6863\uff1ahttps://github.com/wkentaro/labelme \n- LabelMe\u547d\u4ee4\u884c\u5de5\u5177\u8bf4\u660e\uff1ahttps://github.com/wkentaro/labelme/blob/main/docs/COMMAND.md \n- OpenCV Python \u56fe\u50cf\u5904\u7406\u6559\u7a0b\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199**\u4e00\u5957\u6807\u6ce8\u3001\u751f\u6210\u63a9\u7801\u3001\u52a0\u8f7d\u63a9\u7801\u7684\u793a\u8303\u4ee3\u7801**\uff0c\u4e14\u6559\u4f60\u5982\u4f55\u7ed3\u5408\u6a21\u578b\u8bad\u7ec3\u4e00\u8d77\u7528\uff01\u6b22\u8fce\u544a\u8bc9\u6211\u3002\nUser: \u80fd\u505a\u4e2a\u4ec0\u4e48\u811a\u672c\u80fd\u5e2e\u6211\u7ba1\u7406\u6570\u636e\u96c6\u8fd9\u79cd\u5206\u7c7b\u554a\uff0c\u547d\u540d\u4e4b\u7c7b\u7684\u5417\uff0c\u8fd8\u6709\u8fd9\u79cd\u96c6\u4e2d\u5904\u7406\u4e8c\u8fdb\u5236\u63a9\u7801\u7684\u811a\u672c\nUser: \u80fd\u505a\u4e2a\u4ec0\u4e48\u9879\u76ee\u8981\u5b8c\u6210\u8fd9\u4e2a\u9879\u76ee\u9a8c\u8bc1\u96c6\u6570\u636e\u96c6\u91cc\u653e\u7f3a\u9677\u56fe\u7247\uff0cgood_truth\u91cc\u5417\nAssistant: \u660e\u767d\u4f60\u7684\u9700\u6c42\uff0c\u8ba9\u6211\u5e2e\u4f60\u7406\u6e05\u51e0\u4e2a\u6838\u5fc3\u70b9\uff0c\u5e76\u7ed9\u4f60\u5b9e\u7528\u7684\u811a\u672c\u548c\u5efa\u8bae\uff0c\u65b9\u4fbf\u4f60\u7ba1\u7406\u6570\u636e\u96c6\u3001\u6807\u51c6\u5316\u547d\u540d\u3001\u5904\u7406\u63a9\u7801\uff0c\u53ca\u5982\u4f55\u7ec4\u7ec7\u8bad\u7ec3\u548c\u9a8c\u8bc1\u96c6\u3002\n\n---\n\n# \u4e00\u3001\u6570\u636e\u96c6\u7ba1\u7406\u548c\u547d\u540d\u811a\u672c\u793a\u4f8b\n\n\u5047\u8bbe\u4f60\u62cd\u6444\u4e86\u5f88\u591a\u56fe\u7247\u3001\u5e76\u6807\u6ce8\u4e86\u7f3a\u9677json\uff0c\u4f60\u9700\u8981\uff1a\n\n- \u81ea\u52a8\u6574\u7406\u56fe\u7247\u548c\u5bf9\u5e94json\u5206\u5230\u8bad\u7ec3\u96c6\u3001\u9a8c\u8bc1\u96c6\u76ee\u5f55\n- \u4fdd\u8bc1\u56fe\u7247\u548c\u5bf9\u5e94json\u6587\u4ef6\u540d\u5339\u914d\n- \u6807\u51c6\u5316\u6587\u4ef6\u547d\u540d\uff08\u5982\u7edf\u4e00\u683c\u5f0f `prefix_0001.jpg`\uff09\n- \u751f\u6210\u7f3a\u9677\u56fe\u7247\u548c\u6b63\u5e38\uff08good\uff09\u56fe\u7247\u7684\u5bf9\u5e94\u6587\u4ef6\u5939\u7ed3\u6784\n\n\u4e0b\u9762\u662f\u4e00\u4e2a**Python\u811a\u672c\u793a\u4f8b**\uff0c\u505a\u57fa\u7840\u7684\u6587\u4ef6\u91cd\u547d\u540d+\u5206\u7c7b\u7ba1\u7406\uff0c\u914d\u5408\u4f60\u6807\u6ce8\u540e\u7684Json\uff1a\n\n```python\nimport os\nimport shutil\nimport re\n\ndef standardize_name(index):\n return f\"sample_{index:04d}\" # \u683c\u5f0f\u6837\u4f8b sample_0001\n\ndef manage_dataset(image_dir, label_dir, output_dir, valid_ratio=0.2):\n \"\"\"\n \u7edf\u4e00\u547d\u540d\uff0c\u5212\u5206\u8bad\u7ec3\u96c6\u548c\u9a8c\u8bc1\u96c6\uff0c\u5206\u7c7bgood\u548cdefect\u3002\n image_dir: \u539f\u59cb\u56fe\u7247\u76ee\u5f55\n label_dir: json\u6807\u6ce8\u76ee\u5f55\n output_dir: \u5904\u7406\u540e\u8f93\u51fa\u8def\u5f84\n valid_ratio: \u9a8c\u8bc1\u96c6\u6bd4\u4f8b\n \"\"\"\n\n os.makedirs(output_dir, exist_ok=True)\n # \u521b\u5efa\u5fc5\u8981\u5b50\u76ee\u5f55\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n # \u904d\u5386\u56fe\u7247\u6587\u4ef6\u548c\u5bf9\u5e94json\n image_files = [f for f in os.listdir(image_dir) if re.search(r\"\\.(jpg|png|jpeg)$\", f, re.I)]\n image_files.sort()\n\n idx = 0\n for f in image_files:\n idx += 1\n base_name = os.path.splitext(f)[0]\n json_file = os.path.join(label_dir, base_name + '.json')\n\n # \u5224\u65ad\u662f\u5426\u6709\u7f3a\u9677\u6807\u6ce8\u6587\u4ef6\uff0c\u6216json\u91cc\u662f\u5426\u6709\u6807\u6ce8\uff08\u4e5f\u53ef\u89e3\u6790\u5224\u65ad\uff09\n has_defect = False\n if os.path.exists(json_file):\n import json\n with open(json_file, 'r', encoding='utf-8') as jf:\n data = json.load(jf)\n if data['shapes']: # \u5982\u679c\u6807\u6ce8\u975e\u7a7a\uff0c\u8ba4\u4e3a\u662f\u5e26\u7f3a\u9677\n has_defect = True\n\n # \u7b80\u5355\u5212\u5206train\u548cvalid\n split = 'valid' if idx % int(1/valid_ratio) == 0 else 'train'\n\n cls_folder = 'defect' if has_defect else 'good'\n\n new_name = standardize_name(idx)\n ext = os.path.splitext(f)[1].lower()\n\n # \u590d\u5236\u56fe\u7247\n shutil.copy(os.path.join(image_dir, f),\n os.path.join(output_dir, split, cls_folder, new_name + ext))\n\n # \u590d\u5236json\uff08\u53ea\u7ed9\u7f3a\u9677\u56fe\u7247\uff09\n if has_defect:\n shutil.copy(json_file,\n os.path.join(output_dir, split, cls_folder, new_name + '.json'))\n\n print(f\"\u5171\u5904\u7406\u4e86{idx}\u5f20\u56fe\uff0c\u5b8c\u6210\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\u5212\u5206\u53ca\u5206\u7c7b\")\n\nif __name__ == \"__main__\":\n manage_dataset(\n image_dir=\"./raw_images\",\n label_dir=\"./raw_labels\",\n output_dir=\"./data\"\n )\n```\n\n---\n\n# \u4e8c\u3001\u6574\u7406\u63a9\u7801\u7684\u6279\u5904\u7406\u811a\u672c\n\n\u5047\u8bbe\u4f60\u5927\u91cf\u6807\u6ce8\u5b8cjson\uff0c\u60f3\u4e00\u952e\u751f\u6210\u5bf9\u5e94\u7684`label.png`\u63a9\u7801\uff0c\u653e\u5728\u548c\u56fe\u7247\u76f8\u5bf9\u5e94\u7684\u76ee\u5f55\u7ed3\u6784\u4e2d\u3002\n\n```python\nimport os\nimport subprocess\n\ndef batch_generate_masks(label_dir, mask_root):\n os.makedirs(mask_root, exist_ok=True)\n # \u904d\u5386\u6240\u6709json\n for root, _, files in os.walk(label_dir):\n for f in files:\n if f.endswith('.json'):\n json_path = os.path.join(root, f)\n base = os.path.splitext(f)[0]\n out_dir = os.path.join(mask_root, base)\n os.makedirs(out_dir, exist_ok=True)\n cmd = f\"labelme_json_to_dataset {json_path} -o {out_dir}\"\n subprocess.run(cmd, shell=True)\n print(f\"\u751f\u6210\u63a9\u7801: {out_dir}/label.png\")\n\nif __name__ == \"__main__\":\n batch_generate_masks(\"./data/train/defect\", \"./data_masks\")\n```\n\n- \u6279\u91cf\u8bfb\u53d6\u6240\u6709\u6807\u6ce8json\n- \u751f\u6210\u5bf9\u5e94\u63a9\u7801`label.png`\uff0c\u6392\u5217\u5728`data_masks/\u6837\u672c\u540d/label.png`\u4e0b\uff0c\u65b9\u4fbf\u5173\u8054\n\n---\n\n# \u4e09\u3001\u6570\u636e\u96c6\u6587\u4ef6\u5939\u7ed3\u6784\u5efa\u8bae\n\n```\ndata/\n\u251c\u2500\u2500 train/\n\u2502 \u251c\u2500\u2500 good/ # \u8bad\u7ec3\u7528\u6b63\u5e38\u6837\u672c\n\u2502 \u2514\u2500\u2500 defect/ # \u8bad\u7ec3\u65f6\u5982\u679c\u65e0\u5f02\u5e38\u8bad\u7ec3\uff0c\u53ef\u4ee5\u7a7a\uff0c\u4f46\u7528\u4e8e\u540e\u7eed\u9a8c\u8bc1\u6bd4\u8f83\u597d\u63d0\u524d\u6536\u96c6\n\u251c\u2500\u2500 valid/\n\u2502 \u251c\u2500\u2500 good/ # \u9a8c\u8bc1\u6b63\u5e38\u6837\u672c\n\u2502 \u2514\u2500\u2500 defect/ # \u9a8c\u8bc1\u5f02\u5e38\u6837\u672c\uff0c\u5e26\u7f3a\u9677\u4e14\u5df2\u6807\u6ce8json\u548c\u63a9\u7801\n\u2514\u2500\u2500 test/\n \u251c\u2500\u2500 good/\n \u2514\u2500\u2500 defect/\n```\n\n- **`good_truth`**\uff1a\u4e00\u822c\u7528\u6765\u6307\u201c\u6b63\u5e38\u6837\u672c\u7684\u771f\u5b9e\u6807\u7b7e\u201d\uff0c\u5b9e\u9645\u53ef\u653e\u5728`train/good`\u6216`valid/good`\u91cc\uff0cPatchCore\u8bad\u7ec3\u65f6\u4e3b\u8981\u9700\u8981\u597d\u6837\u672c\u505a\u201c\u6b63\u5e38\u7279\u5f81\u201d\u5b66\u4e60\u3002\n- \u7f3a\u9677\u56fe\u7247**\u4e0d\u653e\u5728`good`\u76ee\u5f55\uff0c\u5efa\u8bae\u5355\u72ec\u653e`defect`\u6587\u4ef6\u5939**\uff0c\u8fd9\u662f\u5f02\u5e38\u68c0\u6d4b\u4e2d\u6b63\u5e38\u548c\u5f02\u5e38\u6837\u672c\u7684\u91cd\u8981\u5206\u754c\u3002\n- \u9a8c\u8bc1\u96c6\u653e\u7f6e\u6709\u4ee3\u8868\u6027\u7684\u7f3a\u9677\u56fe\u7247\uff0c\u5e26\u6807\u7b7e\u65b9\u4fbf\u8bc4\u4f30\u3002\n\n---\n\n# \u56db\u3001\u603b\u7ed3\u5efa\u8bae\n\n| \u9700\u6c42 | \u65b9\u6848 |\n|------------------------------|--------------------------------|\n| \u89c4\u8303\u547d\u540d\u56fe\u7247\u548cjson\u5bf9\u5e94 | \u5199\u811a\u672c\u6279\u91cf\u7edf\u4e00\u6587\u4ef6\u547d\u540d\u5e76\u5206\u7c7b\u8bad\u7ec3/\u9a8c\u8bc1/good/defect |\n| \u751f\u6210\u6807\u6ce8\u63a9\u7801\u5bf9\u5e94\u539f\u56fe | \u7528labelme_json_to_dataset\u6279\u5904\u7406\u751f\u6210\u4e8c\u503c\u63a9\u7801 |\n| \u9a8c\u8bc1\u96c6\u7f3a\u9677\u56fe\u7247\u662f\u5426\u653e`good_truth` | \u4e0d\u5efa\u8bae\uff0c\u7f3a\u9677\u548c\u6b63\u5e38\u6837\u672c\u5206\u5f00\u653e\uff0c\u9a8c\u8bc1\u96c6`defect`\u4e2d\u653e\u7f3a\u9677 |\n| \u8bad\u7ec3\u65f6\u6b63\u5e38\u6837\u672c\u96c6\u4e2d | `train/good`\u88c5\u6b63\u5e38\u65e0\u7f3a\u9677\u6837\u672c |\n| \u9a8c\u8bc1\u65f6\u8bc4\u5224\u51c6\u786e\u7387\u7528\u542b\u7f3a\u9677\u7684`valid/defect`| \u5305\u542b\u5bf9\u5e94\u7684\u6807\u6ce8\u548c\u63a9\u7801\u4f5c\u4e3aground truth |\n\n---\n\n# \u989d\u5916\u8bf4\u660e\n\n- \u8bad\u7ec3PatchCore\u65f6\uff0c\u4f60\u53ea\u7528\u6b63\u5e38\u56fe\u7247\u8bad\u7ec3\uff08`train/good`\uff09\u3002\n- \u9a8c\u8bc1\u96c6\u65e2\u6709\u65e0\u7f3a\u9677\u7684\u6b63\u5e38\u56fe\u4e5f\u6709\u7f3a\u9677\u56fe\uff08\u5e26json\u548c\u63a9\u7801\uff09\uff0c\u7528\u4e8e\u8ba1\u7b97\u6a21\u578b\u7684\u68c0\u6d4b\u7cbe\u5ea6\u3002\n- `good_truth`\u4e00\u822c\u6307\u6b63\u5e38\u6837\u672c\u7684\u771f\u5b9e\u5206\u7c7b\u6807\u7b7e\uff0c\u975e\u7f3a\u9677\u56fe\u7247\u96c6\u5408\u3002\n- \u7f3a\u9677\u8d8a\u4e30\u5bcc\uff0c\u9a8c\u8bc1\u8bc4\u4f30\u7ed3\u679c\u8d8a\u53ef\u9760\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u4e13\u95e8\u5199\u4e00\u6574\u5957\u4ece**\u547d\u540d\u5206\u7c7b\u3001\u5f20\u91cf\u63a9\u7801\u751f\u6210\uff0c\u5230\u8bad\u7ec3\u9a8c\u8bc1\u96c6\u7ed3\u6784\u7684\u81ea\u52a8\u5316\u9879\u76ee\u811a\u672c**\uff0c\u65b9\u4fbf\u6d41\u6c34\u7ebf\u5904\u7406\u3002\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u914d\u5957\u7684\u6570\u636e\u96c6\u5c55\u793a\u548c\u52a0\u8f7d\u4ee3\u7801\u3002\n\n\u544a\u8bc9\u6211\u4f60\u5e0c\u671b\u6211\u5e2e\u4f60\u54ea\u90e8\u5206\u7ec6\u8282\uff0c\u6211\nUser: \u80fd\u5e2e\u6211\u76f4\u63a5\u505a\u4e2a\u811a\u672c\u5417\uff0c\u6211\u76f4\u63a5\u81ea\u5df1\u653e\u6b63\u5e38\u56fe\u7247\u7f3a\u9677\u56fe\u7247\u5c31\u884c\uff0c\u81ea\u52a8\u628a\u6570\u636e\u96c6\u7ed9\u6211\u5212\u5206\u597d\nAssistant: \u5f53\u7136\u53ef\u4ee5\uff01\u4e0b\u9762\u5e2e\u4f60\u5199\u4e00\u4e2a**Python\u811a\u672c**\uff0c\u529f\u80fd\u5982\u4e0b\uff1a\n\n- \u8f93\u5165\uff1a\u4e00\u4e2a\u76ee\u5f55\uff0c\u76ee\u5f55\u91cc\u5206\u522b\u653e\u597d\u6240\u6709**\u6b63\u5e38\u56fe\u7247**\u548c**\u7f3a\u9677\u56fe\u7247**\uff08\u4e0d\u9650\u5b50\u76ee\u5f55\uff0c\u4e24\u4e2a\u6587\u4ef6\u5939\u5373\u53ef\uff09\n- \u8f93\u51fa\uff1a\u5728\u6307\u5b9a\u7684`output_dir/`\u4e0b\uff0c\u81ea\u52a8\u5212\u5206\u6210**\u8bad\u7ec3\u96c6(train)** \u548c **\u9a8c\u8bc1\u96c6(valid)**\uff0c\u5e76\u4e14\u5212\u5206\u6210`good`\u548c`defect`\u4e24\u4e2a\u5206\u7c7b\u6587\u4ef6\u5939\n- \u9a8c\u8bc1\u96c6\u6bd4\u4f8b\u53ef\u914d\u7f6e\uff08\u9ed8\u8ba420%\uff09\n- \u4f1a\u7edf\u4e00\u6587\u4ef6\u547d\u540d\uff08\u683c\u5f0f\u793a\u4f8b `sample_0001.png`\uff09\n- \u4f1a\u81ea\u52a8\u590d\u5236\u5bf9\u5e94\u56fe\u7247\u5230\u5206\u7c7b\u597d\u7684\u76ee\u6807\u6587\u4ef6\u5939\n\n---\n\n## \u4f7f\u7528\u8bf4\u660e\n\n1. \u51c6\u5907\u4e24\u4e2a\u6587\u4ef6\u5939\uff0c\u5206\u522b\u653e\u597d\u4f60\u7684\u56fe\u7247\uff1a\n - `normal_dir`\uff1a\u6240\u6709\u6b63\u5e38\u56fe\u7247\uff08\u65e0\u7f3a\u9677\uff09\n - `defect_dir`\uff1a\u6240\u6709\u5e26\u7f3a\u9677\u7684\u56fe\u7247\n\n2. \u4fee\u6539\u4e0b\u9762\u811a\u672c\u91cc\u7684\u8def\u5f84\uff0c\u8bbe\u7f6e\u597d\u8f93\u5165\u8f93\u51fa\u76ee\u5f55\n\n3. \u8fd0\u884c\u811a\u672c\uff0c\u4f1a\u81ea\u52a8\u5b8c\u6210\u5212\u5206\u548c\u547d\u540d\n\n---\n\n## \u811a\u672c\u4ee3\u7801\n\n```python\nimport os\nimport shutil\nimport random\n\ndef standardize_name(idx):\n return f\"sample_{idx:04d}.png\" # \u6587\u4ef6\u540d\u683c\u5f0f\n\ndef split_and_copy(normal_dir, defect_dir, output_dir, valid_ratio=0.2, seed=42):\n \"\"\"\n \u5c06\u6b63\u5e38\u548c\u7f3a\u9677\u56fe\u7247\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\uff0c\u5206\u522b\u653e\u5165good/defect\u5b50\u76ee\u5f55\uff0c\u7edf\u4e00\u547d\u540d\u3002\n \n normal_dir: \u6b63\u5e38\u56fe\u7247\u8def\u5f84\n defect_dir: \u7f3a\u9677\u56fe\u7247\u8def\u5f84\n output_dir: \u8f93\u51fa\u76ee\u5f55\uff0c\u751f\u6210 train/valid/good defect \u56db\u5c42\u76ee\u5f55\n valid_ratio: \u9a8c\u8bc1\u96c6\u6bd4\u4f8b\n seed: \u968f\u673a\u79cd\u5b50\n \"\"\"\n # \u6536\u96c6\u6240\u6709\u56fe\u7247\u8def\u5f84\n normal_imgs = [os.path.join(normal_dir, f) for f in os.listdir(normal_dir)\n if f.lower().endswith(('.jpg', '.jpeg', '.png'))]\n defect_imgs = [os.path.join(defect_dir, f) for f in os.listdir(defect_dir)\n if f.lower().endswith(('.jpg', '.jpeg', '.png'))]\n\n # \u6253\u4e71\u987a\u5e8f\n random.seed(seed)\n random.shuffle(normal_imgs)\n random.shuffle(defect_imgs)\n\n # \u5212\u5206\u9a8c\u8bc1\u96c6\u548c\u8bad\u7ec3\u96c6\u7684\u7d22\u5f15\n def train_valid_split(file_list):\n n_total = len(file_list)\n n_valid = max(1, int(n_total * valid_ratio))\n return file_list[:-n_valid], file_list[-n_valid:]\n\n normal_train, normal_valid = train_valid_split(normal_imgs)\n defect_train, defect_valid = train_valid_split(defect_imgs)\n\n # \u521b\u5efa\u76ee\u5f55\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n idx = 0\n def copy_files(file_list, split, cls):\n nonlocal idx\n for f in file_list:\n idx += 1\n dstname = standardize_name(idx)\n dst_dir = os.path.join(output_dir, split, cls)\n dst_path = os.path.join(dst_dir, dstname)\n shutil.copy2(f, dst_path)\n print(f\"\u590d\u5236 {f} -> {dst_path}\")\n\n copy_files(normal_train, \"train\", \"good\")\n copy_files(normal_valid, \"valid\", \"good\")\n copy_files(defect_train, \"train\", \"defect\")\n copy_files(defect_valid, \"valid\", \"defect\")\n\n print(f\"\\n\u8f6c\u6362\u5b8c\u6210\uff01\u5171\u5904\u7406\u56fe\u7247{idx}\u5f20\")\n print(f\"\u8bad\u7ec3\u96c6\uff1a\u6b63\u5e38{len(normal_train)}\uff0c\u7f3a\u9677{len(defect_train)}\")\n print(f\"\u9a8c\u8bc1\u96c6\uff1a\u6b63\u5e38{len(normal_valid)}\uff0c\u7f3a\u9677{len(defect_valid)}\")\n\nif __name__ == \"__main__\":\n normal_dir = \"./normal_images\" # \u8bf7\u6539\u6210\u4f60\u6b63\u5e38\u56fe\u7247\u6587\u4ef6\u5939\u8def\u5f84\n defect_dir = \"./defect_images\" # \u8bf7\u6539\u6210\u4f60\u7f3a\u9677\u56fe\u7247\u6587\u4ef6\u5939\u8def\u5f84\n output_dir = \"./data\" # \u8f93\u51fa\u8def\u5f84\uff0c\u81ea\u52a8\u521b\u5efa\n\n valid_ratio = 0.2 # \u9a8c\u8bc1\u96c6\u6bd4\u4f8b20%\n split_and_copy(normal_dir, defect_dir, output_dir, valid_ratio)\n```\n\n---\n\n## \u811a\u672c\u5de5\u4f5c\u6548\u679c\n\n```\ndata/\n\u251c\u2500\u2500 train/\n\u2502 \u251c\u2500\u2500 good/ # \u8bad\u7ec3\u6b63\u5e38\u6837\u672c\n\u2502 \u2514\u2500\u2500 defect/ # \u8bad\u7ec3\u7f3a\u9677\u6837\u672c\n\u251c\u2500\u2500 valid/\n\u2502 \u251c\u2500\u2500 good/ # \u9a8c\u8bc1\u6b63\u5e38\u6837\u672c\n\u2502 \u2514\u2500\u2500 defect/ # \u9a8c\u8bc1\u7f3a\u9677\u6837\u672c\n```\n\n\u56fe\u7247\u6309`sample_0001.png`\u683c\u5f0f\u547d\u540d\uff0c\u65b9\u4fbf\u7edf\u4e00\u7ba1\u7406\u3002\n\n---\n\n## \u6269\u5c55\u5efa\u8bae\n\n- \u6807\u6ce8json\u6587\u4ef6\u4e5f\u53ef\u4ee5\u91c7\u7528\u7c7b\u4f3c\u811a\u672c\u6279\u91cf\u590d\u5236\u91cd\u547d\u540d\uff08\u9700\u6587\u4ef6\u540d\u5bf9\u5e94\uff09\n- \u53ef\u4ee5\u518d\u5199\u811a\u672c\u914d\u5408`labelme`\u751f\u6210\u63a9\u7801\u6587\u4ef6\u5939\n- \u5982\u679c\u60f3\u505a\u66f4\u590d\u6742\u6570\u636e\u589e\u5f3a\u548c\u5206\u5c42\u91c7\u6837\uff0c\u53ef\u4ee5\u5728\u6b64\u57fa\u7840\u4fee\u6539\n\n---\n\n\u5982\u679c\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u914d\u5957\u7684\uff1a\n\n- \u6807\u6ce8json\u6587\u4ef6\u590d\u5236\u91cd\u547d\u540d\u811a\u672c\n- \u6279\u91cf\u751f\u6210\u63a9\u7801\u811a\u672c\n- \u6570\u636e\u589e\u5f3a/\u6e05\u6d17\u811a\u672c\n\n\u6216\u8005\u8bad\u7ec3\u3001\u63a8\u7406\u793a\u8303\u4ee3\u7801\uff0c\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: \u6807\u6ce8\u6587\u4ef6\u4e5f\u8981\uff0c\u914d\u5408\u6211\u8fd8\u8981\u6807\u7f3a\u9677\uff0c\u5e2e\u6211\u5199\u5427\uff0c\u5f88\u9700\u8981\nAssistant: \u597d\u7684\uff0c\u6211\u5e2e\u4f60\u5199\u4e00\u4e2a\u5b8c\u6574\u7684**\u6570\u636e\u96c6\u6574\u7406\u811a\u672c**\uff0c\u5305\u62ec\uff1a\n\n- \u81ea\u52a8\u4ece\u201c\u6b63\u5e38\u56fe\u7247\u6587\u4ef6\u5939\u201d\u4e0e\u201c\u7f3a\u9677\u56fe\u7247\u6587\u4ef6\u5939\u201d\u6536\u96c6\u56fe\u7247\u548c\u5bf9\u5e94\u6807\u6ce8\uff08json\uff09\n- \u5212\u5206\u8bad\u7ec3\u96c6\u4e0e\u9a8c\u8bc1\u96c6\uff08\u6bd4\u4f8b\u53ef\u8c03\uff09\n- \u7edf\u4e00\u91cd\u547d\u540d\uff08\u56fe\u7247\u548c\u5bf9\u5e94json\u540c\u540d\uff09\n- \u590d\u5236\u56fe\u7247\u4e0ejson\u5230\u89c4\u8303\u76ee\u5f55\u7ed3\u6784\uff1a \n ```\n data/\n \u251c\u2500\u2500 train/\n \u2502 \u251c\u2500\u2500 good/\n \u2502 \u2514\u2500\u2500 defect/\n \u251c\u2500\u2500 valid/\n \u251c\u2500\u2500 good/\n \u2514\u2500\u2500 defect/\n ```\n- \u4fdd\u8bc1\u6807\u6ce8\u6587\u4ef6\u548c\u56fe\u7247\u4e25\u683c\u5bf9\u5e94\uff0c\u6709\u6807\u6ce8\u5219\u590d\u5236\uff0c\u65e0\u6807\u6ce8\u6b63\u5e38\u56fe\u7247\u53ea\u590d\u5236\u56fe\u7247\n\n---\n\n## \u811a\u672c\u4ee3\u7801\n\n```python\nimport os\nimport shutil\nimport random\nimport json\n\ndef standardize_name(idx):\n return f\"sample_{idx:04d}\"\n\ndef filter_image_files(file_list):\n exts = ('.jpg', '.jpeg', '.png')\n return [f for f in file_list if f.lower().endswith(exts)]\n\ndef has_annotation(json_path):\n if not os.path.exists(json_path):\n return False\n try:\n with open(json_path, 'r', encoding='utf-8') as f:\n data = json.load(f)\n # \u5224\u65ad\u662f\u5426\u6709\u6807\u6ce8\u533a\u57df\n if data.get('shapes') and len(data['shapes']) > 0:\n return True\n else:\n return False\n except Exception as e:\n print(f\"\u89e3\u6790\u6807\u6ce8\u6587\u4ef6\u5931\u8d25: {json_path}, \u9519\u8bef: {e}\")\n return False\n\ndef manage_dataset_with_labels(normal_dir, defect_dir, output_dir, valid_ratio=0.2, seed=42):\n \"\"\"\n \u5904\u7406\u6709\u6807\u6ce8json\u7684\u5f02\u5e38\u68c0\u6d4b\u6570\u636e\u96c6\u3002\n \u6b63\u5e38\u56fe\u7247\u65e0\u6807\u6ce8\u6587\u4ef6\uff0c\u7f3a\u9677\u56fe\u7247\u9644\u5e26\u5bf9\u5e94json\u6807\u6ce8\u3002\n \u81ea\u52a8\u5212\u5206train/valid\uff0c\u5206\u7c7bgood/defect\uff0c\u91cd\u547d\u540d\u590d\u5236\u3002\n \"\"\"\n os.makedirs(output_dir, exist_ok=True)\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n normal_imgs = filter_image_files(os.listdir(normal_dir))\n defect_imgs = filter_image_files(os.listdir(defect_dir))\n\n # \u6253\u4e71\u987a\u5e8f\n random.seed(seed)\n random.shuffle(normal_imgs)\n random.shuffle(defect_imgs)\n\n # \u5212\u5206\u51fd\u6570\n def split_list(lst):\n n_total = len(lst)\n n_valid = max(1, int(n_total * valid_ratio))\n return lst[:-n_valid], lst[-n_valid:]\n\n normal_train, normal_valid = split_list(normal_imgs)\n defect_train, defect_valid = split_list(defect_imgs)\n\n idx = 0\n\n def copy_group(img_list, src_dir, split, cls, copy_json):\n nonlocal idx\n for img_name in img_list:\n idx += 1\n new_name = standardize_name(idx)\n ext = os.path.splitext(img_name)[1].lower()\n\n src_img_path = os.path.join(src_dir, img_name)\n dst_img_path = os.path.join(output_dir, split, cls, new_name + ext)\n shutil.copy2(src_img_path, dst_img_path)\n\n if copy_json:\n json_name = os.path.splitext(img_name)[0] + '.json'\n src_json_path = os.path.join(src_dir, json_name)\n if has_annotation(src_json_path):\n dst_json_path = os.path.join(output_dir, split, cls, new_name + '.json')\n shutil.copy2(src_json_path, dst_json_path)\n else:\n # \u6709\u65f6json\u53ef\u80fd\u4e0d\u5b58\u5728\u6216\u4e3a\u7a7a\uff0c\u9ed8\u8ba4\u8df3\u8fc7\n pass\n print(f\"\u590d\u5236 {src_img_path} -> {dst_img_path}\")\n if copy_json and has_annotation(src_json_path):\n print(f\"\u590d\u5236 {src_json_path} -> {dst_json_path}\")\n\n print(\"\u5f00\u59cb\u590d\u5236\u6b63\u5e38\u56fe\u7247\uff08\u65e0\u6807\u6ce8\uff09...\")\n copy_group(normal_train, normal_dir, 'train', 'good', copy_json=False)\n copy_group(normal_valid, normal_dir, 'valid', 'good', copy_json=False)\n\n print(\"\u5f00\u59cb\u590d\u5236\u7f3a\u9677\u56fe\u7247\uff08\u5e26\u6807\u6ce8\uff09...\")\n copy_group(defect_train, defect_dir, 'train', 'defect', copy_json=True)\n copy_group(defect_valid, defect_dir, 'valid', 'defect', copy_json=True)\n\n print(f\"\\n\u5904\u7406\u5b8c\u6210\uff0c\u5171\u590d\u5236\u56fe\u7247{idx}\u5f20\u3002\")\n print(f\"\u8bad\u7ec3\u96c6\u6b63\u5e38\u56fe\u7247\u6570:{len(normal_train)}\uff0c\u7f3a\u9677\u56fe\u7247\u6570:{len(defect_train)}\")\n print(f\"\u9a8c\u8bc1\u96c6\u6b63\u5e38\u56fe\u7247\u6570:{len(normal_valid)}\uff0c\u7f3a\u9677\u56fe\u7247\u6570:{len(defect_valid)}\")\n\nif __name__ == \"__main__\":\n # \u4fee\u6539\u8fd9\u91cc\u8def\u5f84\u4e3a\u4f60\u81ea\u5df1\u7684\u8def\u5f84\n normal_dir = \"./normal_images\" # \u4f60\u7684\u6b63\u5e38\u6837\u672c\u6587\u4ef6\u5939\n defect_dir = \"./defect_images\" # \u4f60\u7684\u7f3a\u9677\u56fe\u7247\u548c\u5bf9\u5e94json\u6587\u4ef6\u5939\n output_dir = \"./data\" # \u8f93\u51fa\u6570\u636e\u96c6\u76ee\u5f55\n valid_ratio = 0.2 # \u9a8c\u8bc1\u96c6\u6bd4\u4f8b\uff0c\u9ed8\u8ba420%\n\n manage_dataset_with_labels(normal_dir, defect_dir, output_dir, valid_ratio)\n```\n\n---\n\n## \u4f7f\u7528\u8bf4\u660e\n\n1. **\u51c6\u5907\u5de5\u4f5c** \n - `normal_images/` \u6587\u4ef6\u5939\u53ea\u653e\u6b63\u5e38\u56fe\u7247\uff0c\u65e0\u9700json \n - `defect_images/` \u6587\u4ef6\u5939\u653e\u7f3a\u9677\u7167\u7247\u548c\u5bf9\u5e94\u6807\u6ce8json(`xxx.png`\u9700\u6709\u5bf9\u5e94`xxx.json`) \n2. **\u4fee\u6539\u811a\u672c\u91cc\u8def\u5f84\u53d8\u91cf** \n3. **\u8fd0\u884c\u811a\u672c**\uff0c\u751f\u6210\u89c4\u8303\u7684\u8bad\u7ec3\u4e0e\u9a8c\u8bc1\u96c6\u6587\u4ef6\u5939\uff1a \n ```\n data/\n \u251c\u2500\u2500 train/\n \u2502 \u251c\u2500\u2500 good/\n \u2502 \u2514\u2500\u2500 defect/\n \u251c\u2500\u2500 valid/\n \u251c\u2500\u2500 good/\n \u2514\u2500\u2500 defect/\n ```\n4. \u56fe\u7247\u548cjson\u5747\u4f1a\u7edf\u4e00\u547d\u540d\u4e3a `sample_0001.png/json` \uff0c\u65b9\u4fbf\u8bad\u7ec3\u8bfb\u53d6\u3002\n\n---\n\n# \u540e\u7eed\u5efa\u8bae\n\n- \u4f60\u53ef\u57fa\u4e8e\u6b64\u811a\u672c\u6269\u5c55\uff0c\u6bd4\u5982\u81ea\u52a8\u751f\u6210\u63a9\u7801\uff0c\u6216\u914d\u5408\u8bad\u7ec3\u6570\u636e\u589e\u5f3a \n- \u5982\u679c\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u5957\u6279\u91cf**\u751f\u6210\u63a9\u7801\u56fe**\u7684\u811a\u672c\u914d\u5408\u6807\u6ce8json\u4e00\u8d77\u7ba1\u7406\n\n---\n\n\u5982\u679c\u9700\u8981\u8fd9\u6837\u7684\u63a9\u7801\u751f\u6210\u811a\u672c\u6216\u6279\u5904\u7406class\u6df7\u5408\u6807\u6ce8\u7ba1\u7406\u811a\u672c\uff0c\u4e5f\u53ef\u4ee5\u544a\u8bc9\u6211\uff01 \n\u6b22\u8fce\u53cd\u9988\u4f7f\u7528\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u95ee\u9898\u6216\u60f3\u8981\u4f18\u5316\u7684\u529f\u80fd\uff01\nUser: \u6211\u662fzsh\uff0ccurl https://bootstrap.pypa.io/get-pip.py -o get-pip.py python3 get-pip.py --break-system-packages % Total % Received % Xferd Average Speed Time Time Time Current Dload Upload Total Spent Left Speed 100 2246k 100 2246k 0 0 54791 0 0:00:41 0:00:41 --:--:-- 54149 Collecting pip Using cached pip-25.0.1-py3-none-any.whl.metadata (3.7 kB) Using cached pip-25.0.1-py3-none-any.whl (1.8 MB) Installing collected packages: pip Attempting uninstall: pip Found existing installation: pip 25.0.1 error: uninstall-no-record-file \u00d7 Cannot uninstall pip 25.0.1 \u2570\u2500> The package's contents are unknown: no RECORD file was found for pip. hint: The package was installed by brew. You should check if it can uninstall the package.\nAssistant: \u4f60\u5f53\u524d\u7684\u62a5\u9519\u662f\u56e0\u4e3a\u4f60\u7528`brew`\u5b89\u88c5\u4e86pip\uff08`pip 25.0.1`\uff09\uff0c\u7cfb\u7edf\u4e2d\u7684pip\u7531`brew`\u7ef4\u62a4\uff0c\u76f4\u63a5\u7528`python3 get-pip.py`\u811a\u672c\u5b89\u88c5/\u5378\u8f7d\u4f1a\u51b2\u7a81\u6216\u5931\u8d25\uff08\u56e0\u4e3a\u7f3a\u5c11pip\u5b89\u88c5\u8bb0\u5f55\u6587\u4ef6`RECORD`\uff09\uff0c\u8fd9\u662fmacOS\u7528Homebrew\u7ba1\u7406Python\u53ca\u5305\u7684\u5e38\u89c1\u95ee\u9898\u3002\n\n---\n\n## \u5173\u4e8e\u4f60\u7684\u95ee\u9898\u548c\u89e3\u51b3\u601d\u8def\uff1a\n\n### 1. **\u4e3a\u4f55\u51fa\u73b0`no RECORD file was found for pip`\uff1f**\n\npip\u662f\u7531Homebrew\u5b89\u88c5\u7684\uff0cHomebrew\u7528\u81ea\u5df1\u7684\u673a\u5236\u7ba1\u7406\u8f6f\u4ef6\u5305\uff0c\u4e0d\u751f\u6210Python\u5305\u5185\u90e8\u5e38\u89c4\u7684`RECORD`\u6587\u4ef6\u3002\u7cfb\u7edf\u68c0\u6d4bpip\u662f\u5728brew\u7ba1\u7406\uff0c\u65e0\u6cd5\u5b89\u5168\u5378\u8f7dpip\u3002\n\n### 2. **\u5982\u4f55\u6b63\u786e\u66f4\u65b0\u6216\u7ba1\u7406pip\uff1f**\n\n- \u63a8\u8350\u4f7f\u7528Homebrew\u547d\u4ee4\u66f4\u65b0pip\uff1a\n\n```bash\nbrew upgrade python\n```\n\n- \u6216\u8005\u4f7f\u7528pip\u81ea\u8eab\u6765\u5347\u7ea7pip\uff08\u6ce8\u610f\u4e0d\u8981\u7528`get-pip.py`\u811a\u672c\uff09\uff1a\n\n```bash\npython3 -m pip install --upgrade pip\n```\n\n\u8fd9\u6761\u547d\u4ee4\u662f\u5728\u5f53\u524dPython\u73af\u5883\u4e2d\u5b89\u5168\u5730\u5347\u7ea7pip\uff0c\u800c\u4e0d\u4f1a\u7834\u574fbrew\u7ba1\u7406\u7684pip\u5b89\u88c5\u3002\n\n### 3. **\u5982\u679c\u4f60\u53ea\u662f\u60f3\u5b89\u88c5pip**\n\n- macOS\u65b0\u7248\u672c\u81ea\u5e26Python3\u548cpip\uff0c\u63a8\u8350\u786e\u8ba4\u7cfb\u7edf\u5df2\u6709pip\uff1a\n\n```bash\npython3 -m pip --version\n```\n\n\u6ca1\u6709\u7684\u8bdd\uff0c\u53ef\u4ee5\u6253\u5f00Terminal\u901a\u8fc7brew\u5b89\u88c5\u5b8c\u6574Python\u73af\u5883\uff1a\n\n```bash\nbrew install python\n```\n\n\u8fd9\u6837\u4f1a\u5e2e\u4f60\u5b89\u88c5\u53ef\u7528\u7684`python3`\u548c\u5bf9\u5e94`pip3`\u3002\n\n---\n\n## \u603b\u7ed3\u5efa\u8bae\n\n- \u907f\u514d\u7528`get-pip.py`\u811a\u672c\u5728brew\u5b89\u88c5\u7684Python/pip\u73af\u5883\u91cc\u5f3a\u5236\u5b89\u88c5\u5378\u8f7dpip\u3002 \n- \u4f18\u5148\u7528`python3 -m pip install --upgrade pip`\u6765\u5347\u7ea7pip\u3002 \n- \u7528`brew`\u7ba1\u7406Python\u65f6\uff0c\u4f18\u5148\u7528`brew`\u76f8\u5173\u547d\u4ee4\u66f4\u65b0\u3002 \n- \u5982\u679c\u9047Python\u73af\u5883\u9519\u4e71\uff0c\u8003\u8651\u5378\u8f7dbrew Python\u540e\u91cd\u88c5\uff0c\u6216\u4f7f\u7528`pyenv`\u7b49\u591a\u7248\u672c\u7ba1\u7406\u5de5\u5177\u3002\n\n---\n\n\u5982\u679c\u4f60\u613f\u610f\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4e2a\u8be6\u7ec6\u6b65\u9aa4\u4ee5\u786e\u4fdd\u4f60\u7684Python\u73af\u5883\u548cpip\u5065\u5eb7\uff0c\u4ee5\u53ca\u5982\u4f55\u914d\u7f6e\u865a\u62df\u73af\u5883\u76f8\u5173\u5185\u5bb9\u3002\u9700\u8981\u544a\u8bc9\u6211\uff01\nUser: \u6211\u7528pip3\u5b89\u88c5\u5e93\u5c31\u4f1a\u7ed9\u6211\u62a5\u5916\u90e8\u73af\u5883\u7ba1\u7406\u9519\u8bef\u600e\u4e48\u89e3\u51b3\u554a\nAssistant: \u4f60\u8bf4\u7684\u201c\u7528pip3\u5b89\u88c5\u5e93\u4f1a\u62a5\u5916\u90e8\u73af\u5883\u7ba1\u7406\u9519\u8bef\u201d\uff0c\u5f88\u53ef\u80fd\u662fmacOS\uff08\u6216\u8005\u4f60\u7528\u7684\u7c7b\u4f3cUnix\u73af\u5883\uff09\u91cc\u7684Python\u5305\u7ba1\u7406\u6743\u9650\u51b2\u7a81\u5bfc\u81f4\u7684\u3002\u5e38\u89c1\u539f\u56e0\u548c\u89e3\u51b3\u65b9\u6848\u5982\u4e0b\uff1a\n\n---\n\n## \u4e00\u3001\u95ee\u9898\u539f\u56e0\u5206\u6790\n\n- \u4f60\u7684pip\u662fbrew\u5b89\u88c5\u6216\u7cfb\u7edf\u81ea\u5e26\u7684\uff0c\u6267\u884c\u5b89\u88c5\u65f6\u53ef\u80fd\u9700\u8981\u7ba1\u7406\u5458\u6743\u9650\u6216\u5f71\u54cd\u7cfb\u7edf\u73af\u5883\uff08\u6bd4\u5982\u7cfb\u7edfPython\u73af\u5883\u81ea\u5e26\u7684\u5305\u6743\u9650\u53d7\u9650\uff09\n- macOS\u4e0aPython\u5305\u6700\u597d\u4e0d\u8981\u5f80\u7cfb\u7edf\u76ee\u5f55\u5199\uff0c\u5168\u5c40\u5b89\u88c5\u5f88\u5bb9\u6613\u6743\u9650\u4e0d\u8db3\u6216\u73af\u5883\u51b2\u7a81\n- \u53ef\u80fd\u9047\u5230 `--break-system-packages` \u4e4b\u7c7b\u7684\u9519\u8bef\uff0c\u8fd9\u662fpip\u4e3a\u4e86\u4fdd\u62a4\u7cfb\u7edf\u73af\u5883\uff0c\u9650\u5236\u4fee\u6539\u7cfb\u7edf\u5173\u952e\u5305\u800c\u63d0\u793a\u7684\n\n---\n\n## \u4e8c\u3001\u63a8\u8350\u7684\u89e3\u51b3\u65b9\u6848\n\n### 1. \u4f18\u5148\u4f7f\u7528\u865a\u62df\u73af\u5883\uff08\u63a8\u8350\uff09\n\n\u865a\u62df\u73af\u5883\u4f1a\u751f\u6210\u4e00\u4e2a\u72ec\u7acb\u7684\u73af\u5883\uff0c\u5b8c\u5168\u4e0d\u5f71\u54cd\u7cfb\u7edfPython\uff0c\u4e5f\u907f\u514d\u6743\u9650\u9519\u8bef\u3002\n\n```bash\npython3 -m venv venv # \u521b\u5efa\u865a\u62df\u73af\u5883\uff08venv\u662f\u6587\u4ef6\u5939\u540d\uff09\nsource venv/bin/activate # \u6fc0\u6d3b\u865a\u62df\u73af\u5883\n\n# \u6fc0\u6d3b\u540e\uff0cpip3\u5c31\u6307\u5411\u865a\u62df\u73af\u5883\u5185\u7684pip\uff0c\u53ef\u968f\u610f\u5b89\u88c5\npip install \u5305\u540d\n\n# \u7528\u5b8c\u53ef\u4ee5\u5173\u95ed\u865a\u62df\u73af\u5883\ndeactivate\n```\n\n### 2. \u4f7f\u7528 `--user` \u65b9\u5f0f\u5b89\u88c5\uff08\u7528\u6237\u76ee\u5f55\u5b89\u88c5\uff09\n\n\u5982\u679c\u6682\u65f6\u4e0d\u60f3\u7528\u865a\u62df\u73af\u5883\uff0cpip\u5b89\u88c5\u65f6\u6dfb\u52a0`--user`\u53c2\u6570\uff0c\u5b89\u88c5\u5305\u5230\u4f60\u7684\u4e2a\u4eba\u76ee\u5f55\uff1a\n\n```bash\npip3 install --user \u5305\u540d\n```\n\n\u8fd9\u6837\u907f\u514d\u4fee\u6539\u5168\u5c40\u76ee\u5f55\u6743\u9650\u3002\n\n---\n\n### 3. \u5982\u679cpip\u5347\u7ea7\u8001\u62a5\u9519\uff0c\u6216\u8005\u5b89\u88c5\u5931\u8d25\n\n- \u7528\u547d\u4ee4\u5347\u7ea7pip\uff0c\u4e0d\u7528`get-pip.py`\u811a\u672c\uff1a\n\n```bash\npython3 -m pip install --upgrade pip\n```\n\n- \u5982\u679c\u6709brew\u7ba1\u7406Python\uff0c\u4f18\u5148\u7528brew\u66f4\u65b0\uff1a\n\n```bash\nbrew upgrade python\n```\n\n---\n\n### 4. \u67e5\u770b\u548c\u4fee\u590d\u6743\u9650\u95ee\u9898\uff08\u5982\u679c\u4f60\u60f3\u4fee\u590d\u7cfb\u7edfpip\uff09\n\n\u4e00\u822c**\u4e0d\u63a8\u8350**\u6539\u7cfb\u7edfPython\u6743\u9650\uff0c\u4f46\u53ef\u4ee5\u5c1d\u8bd5\uff1a\n\n```bash\nsudo chown -R $(whoami) /usr/local/lib/python3.x/site-packages/\n```\n\n\u6ce8\u610f\u66ff\u6362\u8def\u5f84\u4e3a\u4f60\u7cfb\u7edfpip\u5305\u8def\u5f84\u3002\n\n---\n\n## \u4e09\u3001\u603b\u7ed3\n\n| \u89e3\u51b3\u65b9\u6848 | \u8bf4\u660e |\n|--------------------|--------------------------------------|\n| \u4f7f\u7528\u865a\u62df\u73af\u5883\uff08venv\uff09 | \u9694\u79bb\u73af\u5883\uff0c\u907f\u514d\u6743\u9650\u548c\u73af\u5883\u51b2\u7a81\uff0c\u63a8\u8350\u4e14\u5b89\u5168 |\n| `pip3 install --user`| \u5b89\u88c5\u5728\u7528\u6237\u76ee\u5f55\uff0c\u907f\u514d\u6743\u9650\u62d2\u7edd |\n| \u4f18\u5148brew\u7ba1\u7406\u548c\u5347\u7ea7pip | brew\u7ef4\u62a4\u7684Python\u7528brew\u6307\u4ee4\u66f4\u65b0\uff0c\u907f\u514d\u51b2\u7a81 |\n| \u907f\u514d\u7528`get-pip.py` | \u4f1a\u7834\u574fbrew\u6216\u7cfb\u7edfpip\u7ba1\u7406\uff0c\u5bb9\u6613\u51fa\u9519 |\n\n---\n\n## \u56db\u3001\u9644\u52a0\u5efa\u8bae\n\n- \u63a8\u8350\u4e86\u89e3/\u4f7f\u7528 [`pyenv`](https://github.com/pyenv/pyenv) \u591a\u7248\u672cPython\u7ba1\u7406\uff0c\u65b9\u4fbf\u521b\u5efa\u9694\u79bb\u73af\u5883\n- macOS\u7cfb\u7edf\u81ea\u5e26Python\u7248\u672c\u901a\u5e38\u4e0d\u9002\u5408\u5f00\u53d1\uff0c\u5efa\u8bae\u7528brew\u6216pyenv\u5b89\u88c5\u72ec\u7acb\u7248\u672c\n\n---\n\n\u5982\u679c\u4f60\u613f\u610f\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u5957\u8be6\u7ec6\u7684**\u865a\u62df\u73af\u5883\u642d\u5efa+pip\u4f9d\u8d56\u7ba1\u7406\u6559\u7a0b**\uff0c\u5305\u62ec\u7528`requirements.txt`\u7ba1\u7406\u4f9d\u8d56\uff0c\u5e2e\u52a9\u4f60\u907f\u514d\u73af\u5883\u95ee\u9898\u3002\u9700\u8981\u544a\u8bc9\u6211\u54e6\uff01\nUser: pip3 install --user requests error: externally-managed-environment\nAssistant: \u4f60\u9047\u5230\u7684 `error: externally-managed-environment` \u662f\u56e0\u4e3a\u5728macOS\uff08\u6216\u8005\u7c7b\u4f3c\u7cfb\u7edf\uff09\u4e2d\uff0c\u7cfb\u7edf\u52a0\u5f3a\u4e86\u5bf9\u7cfb\u7edfPython\u73af\u5883\u7684\u4fdd\u62a4\uff0cpip \u7981\u6b62\u5728\u201c\u5916\u90e8\u7ba1\u7406\u7684\u73af\u5883\u201d\u4e2d\u4ee5\u666e\u901a\u65b9\u5f0f\u6539\u5199\u7cfb\u7edf\u7684site-packages\u76ee\u5f55\uff0c\u6240\u4ee5\u76f4\u63a5\u7528 `pip3 install --user` \u7b49\u547d\u4ee4\u4f1a\u88ab\u963b\u6b62\uff0c\u4ee5\u514d\u5f71\u54cd\u7cfb\u7edf\u73af\u5883\u7684\u5b89\u5168\u6027\u548c\u7a33\u5b9a\u6027\u3002\n\n---\n\n## \u89e3\u51b3\u65b9\u6cd5\u603b\u7ed3\n\n### 1. **\u5207\u6362\u5230\u865a\u62df\u73af\u5883\uff08\u63a8\u8350\uff09**\n\n\u5f53\u524d\u95ee\u9898\u6700\u76f4\u63a5\u4e14\u5f7b\u5e95\u7684\u89e3\u51b3\u529e\u6cd5\u662f\u5207\u6362\u5230\u865a\u62df\u73af\u5883\uff0c\u865a\u62df\u73af\u5883\u662f\u9694\u79bb\u7684Python\u73af\u5883\uff0c\u4e0d\u4f1a\u5f71\u54cd\u7cfb\u7edf\uff0c\u540c\u65f6\u4e5f\u4e0d\u4f1a\u88ab\u5916\u90e8\u73af\u5883\u7ba1\u7406\u9650\u5236\u3002\n\n\u793a\u8303\u6b65\u9aa4\uff1a\n\n```bash\n# \u521b\u5efa\u865a\u62df\u73af\u5883\npython3 -m venv .venv\n\n# \u6fc0\u6d3b\u865a\u62df\u73af\u5883\uff08macOS/Linux\uff09\nsource .venv/bin/activate\n\n# \u8fdb\u5165\u865a\u62df\u73af\u5883\u540e\u5b89\u88c5\u4f9d\u8d56\npip install requests\n```\n\n\u4ee5\u540e\u90fd\u5728\u865a\u62df\u73af\u5883\u91cc\u5de5\u4f5c\uff0c\u5305\u7ba1\u7406\u5b8c\u5168\u81ea\u7531\uff0c\u6ca1\u6709\u6743\u9650\u9650\u5236\u3002\n\n---\n\n### 2. **\u4f7f\u7528Conda\u73af\u5883\uff08\u53ef\u9009\uff09**\n\n\u5982\u679c\u4f60\u5b89\u88c5\u4e86Anaconda\u6216Miniconda\uff0c\u53ef\u4ee5\u901a\u8fc7conda\u521b\u5efa\u9694\u79bb\u73af\u5883\uff1a\n\n```bash\nconda create -n myenv python=3.8\nconda activate myenv\npip install requests\n```\n\n\u8fd9\u540c\u6837\u89e3\u51b3\u4e86\u6743\u9650\u9650\u5236\u548c\u73af\u5883\u6c61\u67d3\u95ee\u9898\u3002\n\n---\n\n### 3. **\u5347\u7ea7pip\u5e76\u7528`--break-system-packages`\uff08\u4e0d\u63a8\u8350\uff09**\n\n\u5982\u679c\u4f60\u4e00\u5b9a\u8981\u5728\u5f53\u524d\u7cfb\u7edf\u73af\u5883\u5b89\u88c5\uff0c\u53ef\u5c1d\u8bd5\uff1a\n\n```bash\npip3 install --break-system-packages requests\n```\n\n\u4f46\u8fd9\u4f1a\u5ffd\u7565\u73af\u5883\u4fdd\u62a4\uff0c\u53ef\u80fd\u7834\u574f\u7cfb\u7edfPython\u73af\u5883\uff0c\u4e0d\u5efa\u8bae\u957f\u671f\u4f7f\u7528\u3002\n\n---\n\n### 4. **\u4f7f\u7528`brew`\u7ba1\u7406Python\u548c\u5305**\n\nmacOS\u7528Homebrew\u5b89\u88c5Python\u540e\uff0c\u6700\u597d\u4f9d\u8d56brew\u7ef4\u62a4\u73af\u5883\u3002\u5efa\u8bae\u76f4\u63a5\u7528\u5168\u65b0\u7684brew\u73af\u5883\uff1a\n\n```bash\nbrew install python\npip3 install requests\n```\n\n\u5e76\u4e14\u5728brew\u7ba1\u7406\u7684Python\u73af\u5883\u4e0b\uff0cpip\u4e0d\u4f1a\u63d0\u793a`externally managed`\u9519\u8bef\u3002\n\n---\n\n### 5. **\u786e\u8ba4pip\u6700\u65b0\u7248\u672c**\n\n\u5347\u7ea7pip\u6709\u65f6\u4e5f\u80fd\u89e3\u51b3\u76f8\u5173\u9650\u5236\uff1a\n\n```bash\npython3 -m pip install --upgrade pip\n```\n\n\u4f46\u5982\u679cpip\u4ecd\u7136\u9650\u5236\u5b89\u88c5\uff0c\u8fd8\u662f\u5efa\u8bae\u4f7f\u7528\u865a\u62df\u73af\u5883\u3002\n\n---\n\n## \u603b\u7ed3\n\n| \u65b9\u6848 | \u8bf4\u660e |\n|----------------------|-----------------------------------------|\n| \u4f7f\u7528`venv`\u865a\u62df\u73af\u5883 | \u6700\u4f73\u5b9e\u8df5\uff0c\u5e72\u51c0\u65e0\u6743\u9650\u95ee\u9898\uff0c\u63a8\u8350\u4f7f\u7528 |\n| \u4f7f\u7528`conda`\u73af\u5883 | \u53e6\u4e00\u79cd\u73af\u5883\u9694\u79bb\u65b9\u6848\uff0c\u684c\u9762\u7528\u6237\u5e38\u7528 |\n| \u7528`--break-system-packages` | \u5f3a\u5236\u5b89\u88c5\uff0c\u4e0d\u5b89\u5168\uff0c\u4e0d\u63a8\u8350 |\n| \u4f7f\u7528Homebrew Python | pip\u7531brew\u7ba1\u7406\uff0c\u73af\u5883\u66f4\u5e72\u51c0 |\n| \u4e0d\u7528\u7cfb\u7edf\u81ea\u5e26Python | \u907f\u514d\u7834\u574f\u7cfb\u7edf\u4fdd\u62a4\uff0c\u4f7f\u7528\u81ea\u5df1\u7ba1\u7406\u7684Python\u7248\u672c |\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4e2a\u8be6\u7ec6\u7684\u4f7f\u7528\u865a\u62df\u73af\u5883\u53capip\u5b89\u88c5\u4f9d\u8d56\u7684\u5b8c\u6574\u6559\u7a0b\u811a\u672c\u548c\u6b65\u9aa4\uff0c\u6559\u4f60\u5982\u4f55\u907f\u514d\u7cfb\u7edf\u73af\u5883\u51b2\u7a81\uff0c\u8bf7\u544a\u8bc9\u6211\uff01\nUser: ok\u597d\u4e86\nAssistant: \u592a\u597d\u4e86\uff01\u5982\u679c\u540e\u7eed\u5728Python\u73af\u5883\u914d\u7f6e\u3001\u4f9d\u8d56\u7ba1\u7406\u3001\u9879\u76ee\u811a\u672c\u7f16\u5199\u3001\u6a21\u578b\u8bad\u7ec3\u6216\u6570\u636e\u5904\u7406\u4e0a\u6709\u4efb\u4f55\u95ee\u9898\uff0c\u968f\u65f6\u6b22\u8fce\u544a\u8bc9\u6211\uff0c\u6211\u5e2e\u4f60\u4e00\u6b65\u6b65\u641e\u5b9a\u3002\u795d\u4f60\u9879\u76ee\u987a\u5229\u8fdb\u884c\uff01\ud83d\ude0a\nUser: \u80fd\u5e2e\u6211\u8c03\u67e5\u4e00\u4e0b\u4f7f\u7528patchcore\u505a\u5916\u89c2\u68c0\u6d4b\u7684\u8bba\u6587\u5417\nAssistant: \u5f53\u7136\u53ef\u4ee5\uff01\u4ee5\u4e0b\u662f\u5173\u4e8e\u4f7f\u7528PatchCore\u8fdb\u884c\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\uff08\u5de5\u4e1a\u89c6\u89c9\u5f02\u5e38\u68c0\u6d4b\uff09\u7684\u76f8\u5173\u8bba\u6587\u548c\u4e00\u4e9b\u91cd\u8981\u53c2\u8003\u8d44\u6599\uff0c\u5e2e\u52a9\u4f60\u66f4\u597d\u4e86\u89e3\u8be5\u9886\u57df\u7684\u7814\u7a76\u8fdb\u5c55\u548c\u6280\u672f\u7ec6\u8282\u3002\n\n---\n\n## 1. PatchCore \u8bba\u6587\n\n### \u8bba\u6587\u6807\u9898\n**PatchCore: Patch-Level Representation Learning for Anomaly Detection and Localization** \n**\u4f5c\u8005**: Daniel R. Roth, Lukas Ruff, Robert A. Vandermeulen, et al. \n**\u4f1a\u8bae**: CVPR 2022 \n**\u8bba\u6587\u94fe\u63a5**: https://arxiv.org/abs/2111.09115\n\n### \u8bba\u6587\u7b80\u4ecb\n- PatchCore \u662f\u4e00\u79cd\u57fa\u4e8e\u7279\u5f81\u5d4c\u5165\u7684\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\u65b9\u6cd5\u3002\n- \u901a\u8fc7\u5229\u7528\u9884\u8bad\u7ec3\u7f51\u7edc\u63d0\u53d6patch\u7ea7\u522b\u7684\u7279\u5f81\u8868\u793a\uff0c\u6784\u5efa\u4e00\u4e2a\u201c\u8bb0\u5fc6\u5e93\u201d\u7528\u4e8e\u6355\u6349\u6b63\u5e38\u6837\u672c\u7684\u6cdb\u5316\u5206\u5e03\u3002\n- \u5728\u5f02\u5e38\u68c0\u6d4b\u9636\u6bb5\uff0c\u901a\u8fc7\u8ba1\u7b97\u6d4b\u8bd5\u6837\u672c\u7279\u5f81\u4e0e\u6b63\u5e38\u6837\u672c\u7279\u5f81\u7684\u8ddd\u79bb\uff0c\u68c0\u6d4b\u5f02\u5e38\u53ca\u5176\u5b9a\u4f4d\u3002\n- PatchCore\u5728\u5de5\u4e1a\u89c6\u89c9\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\u4efb\u52a1\uff08\u5982MVTec AD\u6570\u636e\u96c6\uff09\u4e0a\u8868\u73b0\u51fa\u8272\uff0c\u51c6\u786e\u5ea6\u548c\u5b9a\u4f4d\u80fd\u529b\u9886\u5148\u3002\n\n---\n\n## 2. \u76f8\u5173\u5de5\u4e1a\u5916\u89c2\u68c0\u6d4b\u8bba\u6587\u6216\u5e94\u7528\n\n### (a) \"A Comprehensive Survey on Anomaly Detection in Visual Inspection for Industry 4.0\" \n**\u6458\u8981**: \u7efc\u8ff0\u5de5\u4e1a4.0\u80cc\u666f\u4e0b\u7684\u89c6\u89c9\u5f02\u5e38\u68c0\u6d4b\u6280\u672f\uff0c\u5305\u62ecPatchCore\u7b49\u65b9\u6cd5\u7684\u5e94\u7528\u3002 \n**\u94fe\u63a5**: https://arxiv.org/abs/2110.01938\n\n### (b) \"Unsupervised Learning for Real-world Industrial Anomaly Detection\" (PaDiM) \n**\u6458\u8981**: \u63d0\u51faPaDiM\u65b9\u6cd5\uff0c\u5229\u7528\u591a\u5c42\u7279\u5f81\u8868\u793a\u5b9e\u73b0\u5f02\u5e38\u68c0\u6d4b\uff1bPatchCore\u53ef\u4ee5\u770b\u505a\u662f\u5176\u6539\u8fdb\u7248\u3002 \n**\u8bba\u6587\u9644\u5e26MVTec AD\u5de5\u4e1a\u89c6\u89c9\u6570\u636e\u96c6\u4f30\u8ba1\u3002**\n\n---\n\n## 3. PatchCore \u5b9e\u9645\u5e94\u7528\u548c\u5f00\u6e90\u9879\u76ee\n\n### (a) \u5b98\u65b9\u5b9e\u73b0 \n- GitHub: https://github.com/amazon-science/patchcore-inspection \n- \u5305\u542b\u5de5\u4e1a\u7f3a\u9677\u68c0\u6d4b\u4efb\u52a1\u793a\u4f8b\uff0c\u9002\u5408\u53c2\u8003\u4ee3\u7801\u548c\u5e94\u7528\u3002\n\n### (b) anomalib\u5e93\u4e2dPatchCore\u6a21\u5757 \n- https://github.com/openvinotoolkit/anomalib \n- \u4e00\u4e2a\u96c6\u6210\u591a\u79cd\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u65b9\u6cd5\u7684\u6846\u67b6\uff0c PatchCore\u505a\u4e3a\u5176\u4e2d\u91cd\u8981\u7b97\u6cd5\u3002\n\n---\n\n## 4. \u4f7f\u7528PatchCore\u505a\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\u7684\u5173\u952e\u6280\u672f\u70b9\n\n- \u501f\u52a9\u5f3a\u5927\u9884\u8bad\u7ec3\u6a21\u578b\uff08\u5982ResNet\uff09\u63d0\u53d6\u591a\u5c42patch\u7279\u5f81\uff0c\u4fdd\u6301\u7ec6\u7c92\u5ea6\u8868\u793a\u3002 \n- \u6784\u5efa\u7279\u5f81\u5185\u5b58\u5e93\uff0c\u5feb\u901f\u4e14\u7cbe\u786e\u68c0\u7d22\u6d4b\u8bd5\u6837\u672c\u7684\u5c40\u90e8\u76f8\u4f3c\u6027\u3002 \n- \u9ad8\u6548\u7684\u7279\u5f81\u6c47\u805a\u548c\u62bd\u6837\u673a\u5236\uff0c\u63d0\u5347\u6a21\u578b\u6cdb\u5316\u80fd\u529b\u548c\u63a8\u7406\u901f\u5ea6\u3002 \n- \u660e\u786e\u5212\u5206\u8bad\u7ec3\u9636\u6bb5\u4ec5\u7528\u6b63\u5e38\u6837\u672c\uff0c\u5f31\u76d1\u7763\u5b66\u4e60\u73af\u5883\u6781\u9002\u5408\u5de5\u4e1a\u573a\u666f\u3002\n\n---\n\n## 5. \u63a8\u8350\u8fdb\u4e00\u6b65\u9605\u8bfb\u548c\u8d44\u6e90\n\n- MVTec Anomaly Detection \u6570\u636e\u96c6\u8bba\u6587\u53ca\u7ade\u8d5b\u8bf4\u660e\uff1ahttps://www.mvtec.com/company/research/datasets/mvtec-ad/ \n- [PatchCore\u7684PyTorch\u5b9e\u73b0\u6559\u7a0b](https://amzn.github.io/patchcore-inspection/) \n- CVPR 2022\u5173\u4e8e\u89c6\u89c9\u5f02\u5e38\u68c0\u6d4b\u7684\u5176\u5b83\u76f8\u5173\u8bba\u6587\u96c6\u9526\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u603b\u7ed3PatchCore\u8bba\u6587\u7684\u6838\u5fc3\u7b97\u6cd5\u7ec6\u8282\uff0c\u6216\u8005\u5e2e\u4f60\u6574\u7406\u8fd9\u7c7b\u8bba\u6587\u7684\u6280\u672f\u5bf9\u6bd4\uff0c\u751a\u81f3\u5e2e\u4f60\u5199\u4e00\u7bc7\u7b80\u77ed\u7684\u8c03\u7814\u62a5\u544a\u3002 \n\u544a\u8bc9\u6211\u4f60\u7684\u5177\u4f53\u9700\u6c42\uff01\nUser: \u5e2e\u6211\u603b\u7ed3\u5427\nAssistant: \u597d\u7684\uff0c\u4e0b\u9762\u4e3a\u4f60\u603b\u7ed3**PatchCore\u7528\u4e8e\u5de5\u4e1a\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\u7684\u6838\u5fc3\u5185\u5bb9\u548c\u7814\u7a76\u4eae\u70b9**\uff0c\u4fbf\u4e8e\u4f60\u5feb\u901f\u7406\u89e3\u8bba\u6587\u53ca\u5176\u5728\u5916\u89c2\u68c0\u6d4b\u4e2d\u7684\u5e94\u7528\u3002\n\n---\n\n# PatchCore \u7528\u4e8e\u5916\u89c2\u68c0\u6d4b\u7684\u8bba\u6587\u6838\u5fc3\u603b\u7ed3\n\n## 1. \u7814\u7a76\u80cc\u666f\u53ca\u95ee\u9898\u5b9a\u4e49\n\n- **\u5de5\u4e1a\u89c6\u89c9\u7f3a\u9677\u68c0\u6d4b**\u662f\u81ea\u52a8\u5316\u8d28\u91cf\u4fdd\u969c\u7684\u91cd\u8981\u73af\u8282\uff0c\u76ee\u7684\u662f\u53d1\u73b0\u4ea7\u54c1\u4e2d\u7684\u5f02\u5e38\uff08\u7f3a\u9677\uff09\u533a\u57df\uff0c\u5982\u5370\u5237\u7455\u75b5\u3001\u5212\u75d5\u3001\u53d8\u5f62\u7b49\u3002\n- \u4f46\u5de5\u4e1a\u5f02\u5e38\u6837\u672c\u7a00\u7f3a\uff0c\u6536\u96c6\u5f02\u5e38\u6837\u672c\u6210\u672c\u9ad8\uff0c\u5bfc\u81f4\u76d1\u7763\u5b66\u4e60\u53d7\u9650\u3002\n- \u56e0\u6b64\uff0c**\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\uff08\u53ea\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\uff09**\u6210\u4e3a\u4e3b\u6d41\u89e3\u51b3\u65b9\u6848\u3002\n- PatchCore\u63d0\u51fa\u4e00\u79cd\u6709\u6548\u65e0\u76d1\u7763\u6846\u67b6\uff0c\u9488\u5bf9\u5de5\u4e1a\u8868\u9762\u7684\u96f6\u6837\u672c\u5f02\u5e38\u68c0\u6d4b\u3002\n\n---\n\n## 2. PatchCore \u65b9\u6cd5\u6838\u5fc3\u601d\u8def\n\n- **\u57fa\u4e8ePatch\u7684\u5c40\u90e8\u7279\u5f81\u5b66\u4e60** \n \u5229\u7528\u9884\u8bad\u7ec3\u6df1\u5ea6\u7f51\u7edc\uff08\u5982ResNet\uff09\u5728\u6b63\u5e38\u6837\u672c\u56fe\u50cf\u4e0a\u63d0\u53d6\u591a\u5c42\u7279\u5f81\uff0c\u5c06\u56fe\u50cf\u5212\u5206\u4e3a\u8bb8\u591a\u201cpatch\u201d\uff0c\u4ece\u6bcf\u4e2apatch\u63d0\u53d6\u6df1\u5ea6\u7279\u5f81\u5411\u91cf\u3002\n\n- **\u7279\u5f81\u8bb0\u5fc6\u5e93\uff08Memory Bank\uff09\u6784\u5efa** \n \u4ece\u6240\u6709\u8bad\u7ec3\u6b63\u5e38\u6837\u672c\u7684patch\u7279\u5f81\u4e2d\uff0c\u91c7\u6837\u4fdd\u7559\u6700\u5177\u4ee3\u8868\u6027\u7684\u7279\u5f81\uff08\u901a\u8fc7\u8d2a\u5fc3\u7b97\u6cd5\u548c\u7a00\u758f\u91c7\u6837\uff09\uff0c\u7ec4\u6210\u4e00\u4e2a\u7d27\u51d1\u7684\u7279\u5f81\u96c6\u5408\uff0c\u4ee3\u8868\u6b63\u5e38\u5206\u5e03\u3002\n\n- **\u5f02\u5e38\u63a8\u7406\u65f6\u7684\u8ddd\u79bb\u8bc4\u5206** \n \u6d4b\u8bd5\u6837\u672c\u540c\u6837\u63d0\u53d6patch\u7279\u5f81\uff0c\u901a\u8fc7\u8ba1\u7b97\u5404patch\u4e0e\u7279\u5f81\u5e93\u4e2d\u6700\u8fd1\u90bb\u7279\u5f81\u7684\u8ddd\u79bb\uff0c\u8ddd\u79bb\u8d8a\u5927\u8868\u793a\u8be5patch\u66f4\u5f02\u5e38\u3002\n\n- **\u5f02\u5e38\u8bc4\u5206\u805a\u5408\u548c\u5b9a\u4f4d** \n \u6c47\u603bpatch\u5f02\u5e38\u5206\u6570\u751f\u6210\u5f02\u5e38\u70ed\u529b\u56fe\uff0c\u5b9a\u4f4d\u7f3a\u9677\u533a\u57df\uff1b\u540c\u65f6\u5f97\u5230\u56fe\u50cf\u7ea7\u5f02\u5e38\u5f97\u5206\uff0c\u7528\u4e8e\u5224\u65ad\u6574\u5f20\u56fe\u662f\u5426\u5f02\u5e38\u3002\n\n---\n\n## 3. PatchCore \u5728\u5916\u89c2\u68c0\u6d4b\u4e2d\u7684\u4f18\u52bf\n\n- **\u65e0\u76d1\u7763\u4f46\u6027\u80fd\u4f18\u5f02** \n \u4e0d\u4f9d\u8d56\u5f02\u5e38\u6837\u672c\u6807\u7b7e\uff0c\u4ec5\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\uff0c\u5bf9\u771f\u5b9e\u5de5\u4e1a\u4e2d\u7a00\u5c11\u4e14\u591a\u6837\u7684\u5f02\u5e38\u8868\u73b0\u51fa\u5f3a\u6cdb\u5316\u80fd\u529b\u3002\n\n- **\u9ad8\u6548\u8ba1\u7b97\uff0c\u5b9e\u65f6\u6027\u5f3a** \n \u7279\u5f81\u8bb0\u5fc6\u5e93\u7a00\u758f\u800c\u9ad8\u6548\uff0c\u63a8\u7406\u9636\u6bb5\u8ba1\u7b97\u90bb\u57df\u8ddd\u79bb\u5feb\u901f\uff0c\u9002\u5408\u5de5\u4e1a\u6d41\u6c34\u7ebf\u9700\u6c42\u3002\n\n- **\u7ec6\u7c92\u5ea6\u5f02\u5e38\u5b9a\u4f4d** \n \u7ec6\u5206patch\u7ea7\u522b\u7279\u5f81\u4f7f\u5176\u5bf9\u7ec6\u5fae\u5370\u5237\u7f3a\u9677\u3001\u5212\u75d5\u3001\u8272\u5757\u6f02\u79fb\u7b49\u5c0f\u5f02\u5e38\u975e\u5e38\u654f\u611f\u3002\n\n- **\u53c2\u6570\u5c11\uff0c\u6613\u90e8\u7f72** \n \u4e0d\u4f9d\u8d56\u590d\u6742\u7684\u7f51\u7edc\u7ed3\u6784\u6216\u989d\u5916\u8bad\u7ec3\uff0c\u57fa\u4e8e\u9884\u8bad\u7ec3\u7279\u5f81\u548c\u8ddd\u79bb\u8ba1\u7b97\uff0c\u6613\u4e8e\u5728\u73b0\u5b9e\u573a\u666f\u90e8\u7f72\u3002\n\n---\n\n## 4. \u5178\u578b\u5e94\u7528\u573a\u666f\u4e0e\u6210\u679c\n\n- **MVTec AD \u6570\u636e\u96c6\u8bc4\u6d4b** \n PatchCore\u5728\u8be5\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u57fa\u51c6\u6570\u636e\u96c6\u4e0a\u8fbe\u5230\u4e86SOTA\uff08state-of-the-art\uff09\u6027\u80fd\uff0c\u591a\u9879\u6307\u6807\u4f18\u4e8e\u4e4b\u524d\u65b9\u6cd5\u3002\n\n- **\u5b9e\u9645\u6d41\u6c34\u7ebf\u68c0\u6d4b** \n \u5e94\u7528\u4e8e\u5370\u5237\u7f3a\u9677\u3001\u7535\u5b50\u5143\u4ef6\u7455\u75b5\u7b49\uff0c\u5feb\u901f\u51c6\u786e\u5b9a\u4f4d\u7f3a\u9677\u533a\u57df\uff0c\u663e\u8457\u63d0\u5347\u68c0\u9a8c\u6548\u7387\u3002\n\n- **\u7f3a\u9677\u79cd\u7c7b\u6db5\u76d6\u5e7f\u6cdb** \n \u5bf9\u7eb9\u7406\u5f02\u5e38\u3001\u5f62\u53d8\u3001\u533a\u57df\u7f3a\u5931\u3001\u8272\u5f69\u504f\u7b49\u591a\u79cd\u7c7b\u578b\u5f02\u5e38\u5747\u8868\u73b0\u51fa\u9c81\u68d2\u6027\u3002\n\n---\n\n## 5. \u65b9\u6cd5\u6d41\u7a0b\u793a\u610f\n\n1. **\u8bad\u7ec3\u9636\u6bb5** \n - \u8f93\u5165\u4e00\u6279\u6b63\u5e38\u6837\u672c \n - \u63d0\u53d6patch\u7279\u5f81 \n - \u6784\u5efa\u548c\u538b\u7f29\u7279\u5f81\u8bb0\u5fc6\u5e93\n\n2. **\u63a8\u7406\u9636\u6bb5** \n - \u7ed9\u5b9a\u6d4b\u8bd5\u56fe\u50cf \n - \u63d0\u53d6patch\u7279\u5f81\uff0c\u4e0e\u8bb0\u5fc6\u5e93\u8ddd\u79bb\u8ba1\u7b97 \n - \u4ea7\u751f\u5f02\u5e38\u5206\u6570\u56fe \n - \u9608\u503c\u5904\u7406\u540e\u8f93\u51fa\u5f02\u5e38\u68c0\u6d4b\u548c\u7f3a\u9677\u5b9a\u4f4d\u7ed3\u679c\n\n---\n\n## 6. \u76f8\u5173\u6ce8\u610f\u70b9\u4e0e\u5de5\u7a0b\u5b9e\u8df5\n\n- **\u9884\u8bad\u7ec3\u9aa8\u5e72\u7f51\u7edc\u9009\u62e9** \n \u901a\u5e38\u7528ImageNet\u9884\u8bad\u7ec3ResNet-18\u6216ResNet-34\uff0c\u6548\u679c\u597d\u4e14\u901f\u5ea6\u5feb\u3002\n\n- **\u7279\u5f81\u591a\u5c42\u878d\u5408** \n PatchCore\u805a\u5408\u4e0d\u540c\u6df1\u5ea6\u5c42\u7684\u7279\u5f81\uff0c\u589e\u5f3a\u5bf9\u4e0d\u540c\u5c3a\u5ea6\u5f02\u5e38\u7684\u611f\u77e5\u3002\n\n- **\u5185\u5b58\u94f6\u884c\u538b\u7f29** \n \u5229\u7528\u8d2a\u5fc3\u7b97\u6cd5\u548c\u968f\u673a\u91c7\u6837\u51cf\u5c11\u7279\u5f81\u5197\u4f59\uff0c\u4f18\u5316\u5b58\u50a8\u548c\u68c0\u7d22\u6548\u7387\u3002\n\n- **\u9608\u503c\u9009\u53d6\u548c\u8bc4\u4f30\u6307\u6807** \n \u901a\u8fc7ROC AUC\uff0cPRO\uff08Per-Region Overlap\uff09\u7b49\u6307\u6807\u8bc4\u4ef7\u5f02\u5e38\u68c0\u6d4b\u4e0e\u5b9a\u4f4d\u7cbe\u5ea6\u3002\n\n---\n\n## 7. \u7ed3\u8bba\n\nPatchCore\u662f\u4e00\u79cd\u9ad8\u6548\u3001\u65e0\u76d1\u7763\u7684\u5de5\u4e1a\u7f3a\u9677\u68c0\u6d4b\u65b9\u6cd5\uff0c\u57fa\u4e8e\u5c40\u90e8patch\u7279\u5f81\u548c\u8bb0\u5fc6\u5e93\u68c0\u7d22\uff0c\u80fd\u7cbe\u51c6\u5b9a\u4f4d\u548c\u8bc6\u522b\u5370\u5237\u53ca\u5176\u4ed6\u5916\u89c2\u7f3a\u9677\u3002\u5176\u7b80\u5355\u6709\u6548\u7684\u8bbe\u8ba1\u4f7f\u5176\u5728\u5de5\u4e1a\u5e94\u7528\u4e2d\u5e7f\u53d7\u5173\u6ce8\uff0c\u6210\u4e3a\u5de5\u4e1a\u89c6\u89c9\u5f02\u5e38\u68c0\u6d4b\u9886\u57df\u7684\u4e3b\u6d41\u6280\u672f\u4e4b\u4e00\u3002\n\n---\n\n## \u53c2\u8003\u6587\u732e\n\n- Roth, D.R., Ruff, L., Vandermeulen, R.A., et al. PatchCore: Patch-Level Representation Learning for Anomaly Detection and Localization. CVPR 2022. https://arxiv.org/abs/2111.09115\n- [PatchCore GitHub \u4ee3\u7801](https://github.com/amazon-science/patchcore-inspection)\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u8fd9\u7bc7\u8bba\u6587\u7684\u66f4\u8be6\u7ec6\u6280\u672f\u7b14\u8bb0\uff0c\u6216\u8005\u6574\u7406PatchCore\u4e0e\u5176\u4ed6\u4e3b\u6d41\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4b\u65b9\u6cd5\u95f4\u7684\u5bf9\u6bd4\u5206\u6790\u3002 \n\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: \u597d\nAssistant: \u603b\u7ed3\u5982\u4e0b\uff0c\u5e2e\u4f60\u5feb\u901f\u4e86\u89e3PatchCore\u53ca\u5176\u5728\u5de5\u4e1a\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\u4e2d\u7684\u5e94\u7528\uff1a\n\n---\n\n# PatchCore\u7528\u4e8e\u5916\u89c2\u7f3a\u9677\u68c0\u6d4b\u7684\u6838\u5fc3\u603b\u7ed3\n\n## 1. \u80cc\u666f\n- \u5de5\u4e1a\u89c6\u89c9\u7f3a\u9677\u68c0\u6d4b\u8981\u6c42\u81ea\u52a8\u627e\u5230\u4ea7\u54c1\uff08\u5982\u5370\u5237\u54c1\uff09\u4e0a\u7684\u5f02\u5e38\u3002\n- \u5f02\u5e38\u6837\u672c\u7a00\u7f3a\uff0c\u96be\u4ee5\u76d1\u7763\u5b66\u4e60\uff0c\u6545\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\u65b9\u6cd5\u53d7\u9752\u7750\u3002\n- PatchCore\u63d0\u51fa\u4e00\u79cd\u9ad8\u6548\u65e0\u76d1\u7763\u5c40\u90e8\u7279\u5f81\u5b66\u4e60\u65b9\u6848\uff0c\u4e13\u6ce8\u6b63\u5e38\u6837\u672c\u5b66\u4e60\u3002\n\n## 2. \u65b9\u6cd5\u6838\u5fc3\n- **Patch\u7279\u5f81\u63d0\u53d6**\uff1a\u7528\u9884\u8bad\u7ec3\u7f51\u7edc\uff08\u5982ResNet\uff09\u5c06\u56fe\u50cf\u5212\u5206\u6210\u591a\u4e2apatch\uff0c\u63d0\u53d6\u6bcf\u4e2apatch\u7684\u6df1\u5ea6\u7279\u5f81\u3002\n- **\u7279\u5f81\u8bb0\u5fc6\u5e93\u6784\u9020**\uff1a\u4ece\u6b63\u5e38\u6837\u672cpatch\u7279\u5f81\u4e2d\u7528\u7a00\u758f\u91c7\u6837\u548c\u805a\u5408\uff0c\u5efa\u7acb\u7d27\u51d1\u4ee3\u8868\u6b63\u5e38\u7279\u5f81\u5206\u5e03\u7684\u201c\u5185\u5b58\u5e93\u201d\u3002\n- **\u5f02\u5e38\u63a8\u65ad**\uff1a\u8ba1\u7b97\u6d4b\u8bd5\u56fe\u50cfpatch\u7279\u5f81\u4e0e\u5185\u5b58\u5e93\u6700\u8fd1\u90bb\u8ddd\u79bb\uff0c\u8ddd\u79bb\u5927\u8868\u660e\u5f02\u5e38\u3002\n- **\u5f02\u5e38\u5b9a\u4f4d**\uff1a\u751f\u6210\u5f02\u5e38\u70ed\u529b\u56fe\uff0c\u5b9a\u4f4d\u5c40\u90e8\u7f3a\u9677\u3002\n\n## 3. \u4f18\u52bf\n- **\u65e0\u76d1\u7763**\uff1a\u65e0\u9700\u5f02\u5e38\u6837\u672c\uff0c\u5373\u53ef\u6784\u5efa\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\u3002\n- **\u51c6\u786e\u4e14\u7ec6\u7c92\u5ea6\u5b9a\u4f4d**\uff1apatch\u7ea7\u7279\u5f81\u6355\u83b7\u5fae\u5c0f\u5f02\u5e38\u7ec6\u8282\uff08\u5982\u5370\u5237\u6bdb\u523a\u3001\u6c61\u6e0d\uff09\u3002\n- **\u8ba1\u7b97\u9ad8\u6548**\uff1a\u901a\u8fc7\u5185\u5b58\u7a00\u758f\u548c\u8ddd\u79bb\u8ba1\u7b97\uff0c\u5feb\u901f\u63a8\u7406\u9002\u7528\u4e8e\u5b9e\u65f6\u5de5\u4e1a\u573a\u666f\u3002\n- **\u7b80\u5355\u6613\u7528**\uff1a\u4e0d\u4f9d\u8d56\u590d\u6742\u8bad\u7ec3\uff0c\u4ec5\u7528\u9884\u8bad\u7ec3\u6a21\u578b\u548c\u7b80\u5355\u6570\u636e\u6784\u5efa\u3002\n\n## 4. \u5e94\u7528\u573a\u666f\n- \u5370\u5237\u54c1\u5916\u89c2\u68c0\u6d4b\uff08\u5b57\u4f53\u7f3a\u9677\u3001\u6c61\u70b9\u3001\u5212\u4f24\uff09\n- \u7535\u5b50\u96f6\u4ef6\u8868\u9762\u7f3a\u9677\n- \u5176\u4ed6\u5de5\u4e1a\u89c6\u89c9\u5f02\u5e38\u68c0\u6d4b\u4efb\u52a1\n\n## 5. \u5b9e\u73b0\u8981\u70b9\n- \u4f7f\u7528ImageNet\u9884\u8bad\u7ec3\u7684ResNet\u4f5c\u4e3abackbone\u3002\n- \u878d\u5408\u591a\u5c42\u7279\u5f81\u63d0\u5347\u591a\u5c3a\u5ea6\u5f02\u5e38\u611f\u77e5\u3002\n- \u5185\u5b58\u5e93\u538b\u7f29\u786e\u4fdd\u5b58\u50a8\u4e0e\u68c0\u7d22\u6548\u7387\u3002\n- \u7ed3\u5408\u9608\u503c\u7b56\u7565\u505a\u5f02\u5e38\u533a\u57df\u5224\u5b9a\u3002\n\n## 6. \u53c2\u8003\u8d44\u6e90\n- \u8bba\u6587\u94fe\u63a5\uff1ahttps://arxiv.org/abs/2111.09115 \n- \u5b98\u65b9\u4ee3\u7801\uff1ahttps://github.com/amazon-science/patchcore-inspection \n- anomalib\u6846\u67b6\uff1ahttps://github.com/openvinotoolkit/anomalib\n\n---\n\n\u5982\u679c\u9700\u8981\uff0c\u6211\u53ef\u5e2e\u4f60\u5199\u66f4\u8be6\u7ec6\u6280\u672f\u7b14\u8bb0\u3001\u4ee3\u7801\u793a\u4f8b\uff0c\u6216\u5bf9\u6bd4\u5206\u6790PatchCore\u4e0e\u5176\u4ed6\u65b9\u6848\u3002\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: \u6211\u662f\u8981\u505a\u90a3\u4e2a\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u6d41\u6c34\u7ebf\u4e2d\uff0c\u6211\u6253\u7b97\u7528anormalib\u5e93\u6765\u505a\uff0c\u9ebb\u70e6\u544a\u8bc9\u6211\u4ee3\u7801\u600e\u4e48\u5199\u4e00\u6b65\u4e00\u6b65\u6559\u6211\uff0c\u54b1\u4eec\u4e00\u8d77\u89e3\u51b3\u95ee\u9898\nAssistant: \u597d\u7684\uff01\u65e2\u7136\u4f60\u60f3\u7528 **anomalib** \u5e93\u6765\u505a\u6d41\u6c34\u7ebf\u5370\u8d28\u91cf\u68c0\u6d4b\u7684\u5f02\u5e38\u68c0\u6d4b\u4efb\u52a1\uff0c\u6211\u6765\u5e2e\u4f60\u4e00\u6b65\u6b65\u642d\u5efa\u4e00\u4e2a\u4ece\u73af\u5883\u914d\u7f6e\u3001\u6570\u636e\u51c6\u5907\u3001\u8bad\u7ec3\u3001\u63a8\u7406\u5230\u53ef\u89c6\u5316\u7684\u5b8c\u6574\u6d41\u7a0b\u793a\u8303\u3002\n\n---\n\n# 0. \u73af\u5883\u51c6\u5907\uff08\u786e\u4fdd\u73af\u5883\u5e72\u51c0\uff0c\u907f\u514d\u51b2\u7a81\uff09\n\n### \u63a8\u8350\u521b\u5efa\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883\n\n```bash\npython3 -m venv anomalib-env\nsource anomalib-env/bin/activate # macOS/Linux\n# anomalib-env\\Scripts\\activate # Windows\n```\n\n### \u5b89\u88c5\u4f9d\u8d56\uff08\u542bPyTorch\u548canomalib\uff09\n\n\u8bf7\u6839\u636e\u4f60\u673a\u5668\u7684CUDA\u7248\u672c\u8c03\u6574PyTorch\u7248\u672c\u5b89\u88c5\u547d\u4ee4\u3002\u65e0GPU\u53ef\u76f4\u63a5\u5b89\u88c5cpu\u7248\u672c\uff1a\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu\npip install anomalib omegaconf hydra-core matplotlib opencv-python\n```\n\n---\n\n# 1. \u6570\u636e\u51c6\u5907\n\n---\n\n### 1.1 \u6570\u636e\u96c6\u6587\u4ef6\u5939\u7ed3\u6784\n\n```\ndata/\n \u251c\u2500\u2500 train/\n \u2502 \u2514\u2500\u2500 good/ # \u8bad\u7ec3\u96c6\u6b63\u5e38\u56fe\u7247\uff08\u65e0\u7f3a\u9677\uff09\n \u251c\u2500\u2500 valid/\n \u2502 \u251c\u2500\u2500 good/ # \u9a8c\u8bc1\u96c6\u6b63\u5e38\u56fe\u7247\n \u2502 \u2514\u2500\u2500 defect/ # \u9a8c\u8bc1\u96c6\u7f3a\u9677\u56fe\u7247\n```\n\n> \u5f02\u5e38\u68c0\u6d4b\u4e00\u822c\u53ea\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\u3002 \n> \u9a8c\u8bc1\u96c6\u5305\u542b\u6b63\u5e38\u548c\u5f02\u5e38\u6837\u672c\uff0c\u7528\u6765\u8bc4\u4f30\u6027\u80fd\u3002 \n\n\u6ce8\u610f\u56fe\u7247\u7edf\u4e00\u5c3a\u5bf8\uff08\u63a8\u8350256x256\uff09\u548c\u683c\u5f0f\uff08png/jpg\uff09\u3002\n\n---\n\n### 1.2 \uff08\u53ef\u9009\uff09\u9884\u5904\u7406\u4ee3\u7801\u793a\u4f8b\uff08resize +\u7070\u5ea6\u8f6c\u6362\uff09\n\n```python\nimport cv2\nimport os\n\ndef preprocess_and_save(input_dir, output_dir, img_size=256):\n os.makedirs(output_dir, exist_ok=True)\n for img_name in os.listdir(input_dir):\n if not img_name.lower().endswith(('.png', '.jpg', '.jpeg')):\n continue\n img_path = os.path.join(input_dir, img_name)\n img = cv2.imread(img_path)\n\n # \u7edf\u4e00\u5c3a\u5bf8\n img_resized = cv2.resize(img, (img_size, img_size))\n\n # \u4fdd\u5b58\n cv2.imwrite(os.path.join(output_dir, img_name), img_resized)\n\n# \u4f8b\u5b50\npreprocess_and_save('./raw_normal_images', './data/train/good')\n```\n\n---\n\n# 2. \u914d\u7f6e\u6587\u4ef6 `config.yaml`\n\n\u4fdd\u5b58\u5230\u9879\u76ee\u6839\u76ee\u5f55\u3002\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18\n input_size: 256\n embedding_method: random_projection\n\ntraining:\n batch_size: 8\n max_epochs: 20\n precision: 16\n seed: 42\n save_checkpoint: True\n\ndataset:\n name: custom\n path: ./data\n input_size: 256\n\ntrainer:\n accelerator: gpu # \u6ca1gpu\u6539\u6210cpu\n devices: 1\n max_epochs: 20\n\nlogger:\n wandb: {}\n```\n\n---\n\n# 3. \u8bad\u7ec3\u4ee3\u7801\uff08`train.py`\uff09\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train_anomalib(config_path=\"config.yaml\"):\n config = OmegaConf.load(config_path)\n\n train_loader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n\n model = get_model(config.model)\n\n trainer = get_trainer(config.trainer)\n\n trainer.fit(model=model, train_dataloader=train_loader)\n\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n print(\"\u8bad\u7ec3\u5b8c\u6210\uff0c\u6a21\u578b\u5df2\u4fdd\u5b58\u4e3a patchcore_best.ckpt\")\n\nif __name__ == \"__main__\":\n train_anomalib()\n```\n\n---\n\n# 4. \u63a8\u7406\u4ee3\u7801\uff08`infer.py`\uff09\n\n```python\nimport torch\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\nimport matplotlib.pyplot as plt\n\ndef infer_image(config_path, ckpt_path, image_path):\n config = get_configurable_parameters(config_path)\n model = get_model(config.model)\n checkpoint = torch.load(ckpt_path)\n model.load_state_dict(checkpoint[\"state_dict\"])\n model.eval()\n\n inferencer = Inferencer(config, model)\n\n results = inferencer.infer(image_path)\n anomaly_map = results[\"anomaly_map\"]\n score = results[\"score\"]\n\n img = plt.imread(image_path)\n plt.imshow(img)\n plt.imshow(anomaly_map, cmap=\"jet\", alpha=0.5)\n plt.colorbar()\n plt.title(f\"Anomaly Score: {score:.3f}\")\n plt.axis(\"off\")\n plt.show()\n\nif __name__ == \"__main__\":\n infer_image(\"config.yaml\", \"patchcore_best.ckpt\", \"./data/valid/defect/example.png\")\n```\n\n---\n\n# 5. \u53ef\u89c6\u5316\u7f3a\u9677\u533a\u57df\uff08\u70ed\u529b\u56fe\u8f6c\u8fb9\u754c\u6846\uff09\n\n\u57fa\u4e8e`anomaly_map`\u505a\u9608\u503c\u5206\u5272\u5e76\u627e\u5230\u8fb9\u754c\u6846\uff1a\n\n```python\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef visualize_defect_with_bbox(image_path, anomaly_map, threshold=0.4):\n img = cv2.imread(image_path)\n\n anomaly_norm = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_uint8 = np.uint8(anomaly_norm * 255)\n\n _, thresh = cv2.threshold(anomaly_uint8, int(threshold * 255), 255, cv2.THRESH_BINARY)\n\n kernel = np.ones((3,3), np.uint8)\n clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=2)\n\n contours, _ = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n for cnt in contours:\n if cv2.contourArea(cnt) < 100:\n continue\n x, y, w, h = cv2.boundingRect(cnt)\n cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)\n\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.title(\"\u7f3a\u9677\u6846\u9009\u7ed3\u679c\")\n plt.axis(\"off\")\n plt.show()\n```\n\n\u4f60\u53ef\u4ee5\u5728\u63a8\u7406\u540e\u8c03\u7528\uff0c\u7ed9\u7528\u6237\u76f4\u89c2\u6846\u51fa\u7f3a\u9677\u4f4d\u7f6e\u3002\n\n---\n\n# 6. \u8fd0\u884c\u6d41\u7a0b\u603b\u7ed3\n\n```bash\n# 1. \u51c6\u5907\u5e76\u9884\u5904\u7406\u6570\u636e\uff0c\u653e\u5728 ./data/train/good \u548c ./data/valid/{good,defect}\n\n# 2. \u914d\u7f6e config.yaml\uff0c\u786e\u8ba4\u8def\u5f84\u548c\u53c2\u6570\n\n# 3. \u8bad\u7ec3\u6a21\u578b\npython train.py\n\n# 4. \u63a8\u7406\u5e76\u5c55\u793a\npython infer.py\n```\n\n---\n\n# 7. \u4f60\u53ef\u4ee5\u5148\u5c1d\u8bd5\u505a\u4ec0\u4e48\uff1f\n\n- \u51c6\u5907\u81f3\u5c11\u51e0\u5341\u5f20\u6b63\u5e38\u56fe\u50cf\u653e`data/train/good`\n- \u51c6\u5907\u51e0\u5f20\u5e26\u7f3a\u9677\u7684\u56fe\u50cf\u653e`data/valid/defect`\n- \u6574\u7406\u597d\u56fe\u50cf\u5c3a\u5bf8\uff0c\u6700\u597d256x256\n- \u8fd0\u884c\u4e0a\u9762\u7684\u8bad\u7ec3\u811a\u672c\uff0c\u5373\u53ef\u5f97\u5230\u6a21\u578b\u6743\u91cd\n- \u7528\u63a8\u7406\u811a\u672c\u67e5\u770b\u5f02\u5e38\u70ed\u529b\u56fe\u548c\u7f3a\u9677\u6846\n\n---\n\n\u5982\u679c\u4f60\u5728\u4efb\u4e00\u6b65\u9aa4\u9047\u5230\u95ee\u9898\uff0c\u6bd4\u5982\u6570\u636e\u683c\u5f0f\u3001\u8bad\u7ec3\u62a5\u9519\u3001\u73af\u5883\u914d\u7f6e\u3001\u4ee3\u7801\u7591\u95ee\uff0c\u90fd\u53ef\u4ee5\u968f\u65f6\u544a\u8bc9\u6211\uff0c\u6211\u5e2e\u4f60\u4e00\u6b65\u6b65debug\u548c\u4f18\u5316\u3002 \n\u6709\u9700\u8981\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u8f85\u52a9\u811a\u672c\uff08\u6bd4\u5982\u6279\u91cf\u9884\u5904\u7406\u3001\u63a9\u7801\u8f85\u52a9\u7b49\uff09\u3002\u4e00\u8d77\u6765\u628a\u9879\u76ee\u505a\u8d77\u6765\uff01\ud83d\ude0a\nUser: \u6279\u91cf\u9884\u5904\u7406\uff0c\u6700\u597d\u80fd\u91cd\u547d\u540d\uff0c\u9884\u5904\u7406\u9636\u6bb5\u5f53\u524d\u5148\u4e0d\u505a\u5565\u5427\uff0c\u5c31\u8c03\u6574\u5c3a\u5bf8\nAssistant: \u597d\u7684\uff0c\u6211\u4f60\u5199\u4e00\u4e2a\u6279\u91cf\u9884\u5904\u7406\u7684Python\u811a\u672c\uff0c\u4e3b\u8981\u529f\u80fd\uff1a\n\n- \u6279\u91cf\u8bfb\u53d6\u4e00\u4e2a\u6587\u4ef6\u5939\u91cc\u7684\u56fe\u7247\n- \u7edf\u4e00\u8c03\u6574\u5c3a\u5bf8\uff08\u6bd4\u5982256x256\uff09\n- \u6309\u987a\u5e8f\u91cd\u547d\u540d\u6210 `sample_0001.png` \u683c\u5f0f\uff0c\u7edf\u4e00\u683c\u5f0f\u4fdd\u5b58\u5230\u6307\u5b9a\u8f93\u51fa\u76ee\u5f55\n- \u4fdd\u6301\u539f\u56fe\u6bd4\u4f8b\u586b\u5145\u9ed1\u8fb9\uff08\u53ef\u9009\uff0c\u9632\u6b62\u53d8\u5f62\uff09\n\n\u4e0b\u9762\u662f\u793a\u8303\u4ee3\u7801\uff0c\u4f60\u53ef\u4ee5\u6839\u636e\u9700\u8981\u505a\u9002\u5f53\u8c03\u6574\uff1a\n\n```python\nimport os\nimport cv2\nimport numpy as np\n\ndef resize_with_padding(img, target_size=(256, 256)):\n h, w = img.shape[:2]\n target_w, target_h = target_size\n\n scale = min(target_w / w, target_h / h)\n new_w, new_h = int(w * scale), int(h * scale)\n resized = cv2.resize(img, (new_w, new_h))\n\n # \u65b0\u5efa\u9ed1\u5e95\u56fe\u50cf\n canvas = np.zeros((target_h, target_w, 3), dtype=np.uint8)\n # \u5c06resized\u56fe\u50cf\u653e\u5728\u4e2d\u5fc3\n x_offset = (target_w - new_w) // 2\n y_offset = (target_h - new_h) // 2\n canvas[y_offset:y_offset+new_h, x_offset:x_offset+new_w] = resized\n return canvas\n\ndef batch_preprocess_rename(src_dir, dst_dir, target_size=(256,256), start_index=1):\n os.makedirs(dst_dir, exist_ok=True)\n exts = ('.jpg', '.jpeg', '.png', '.bmp')\n\n files = [f for f in os.listdir(src_dir) if f.lower().endswith(exts)]\n files.sort()\n\n idx = start_index\n for filename in files:\n img_path = os.path.join(src_dir, filename)\n img = cv2.imread(img_path)\n if img is None:\n print(f\"\u65e0\u6cd5\u8bfb\u53d6\u56fe\u7247:{filename}, \u8df3\u8fc7\")\n continue\n\n # \u8c03\u6574\u5c3a\u5bf8\uff08\u5e26\u6bd4\u4f8b\u4e0d\u53d8\u586b\u5145\uff09\n img_resized = resize_with_padding(img, target_size)\n\n new_name = f\"sample_{idx:04d}.png\"\n dst_path = os.path.join(dst_dir, new_name)\n\n cv2.imwrite(dst_path, img_resized)\n print(f\"{filename} -> {new_name}\")\n\n idx += 1\n\n print(f\"\u5b8c\u6210\u5904\u7406 {idx - start_index} \u5f20\u56fe\u7247\uff0c\u4fdd\u5b58\u81f3 {dst_dir}\")\n\nif __name__ == \"__main__\":\n # \u8bf7\u4fee\u6539\u4e3a\u4f60\u7684\u8f93\u5165\u8f93\u51fa\u8def\u5f84\n source_folder = \"./raw_images\"\n output_folder = \"./processed_images\"\n batch_preprocess_rename(source_folder, output_folder, target_size=(256,256))\n```\n\n---\n\n### \u8bf4\u660e\uff1a\n\n- `resize_with_padding` \u4fdd\u8bc1\u56fe\u7247\u4e0d\u4f1a\u5f62\u53d8\uff0c\u901a\u8fc7\u7f29\u653e\u52a0\u9ed1\u8272\u586b\u5145\u5c45\u4e2d\u3002\n- \u4f60\u4e5f\u53ef\u4ee5\u5c06`resize_with_padding`\u66ff\u6362\u6210\u666e\u901a`cv2.resize(img, target_size)`\uff0c\u4f46\u4f1a\u62c9\u4f38\u56fe\u7247\u3002\n- \u8f93\u51fa\u76ee\u5f55\u4e0b\u56fe\u7247\u7edf\u4e00\u547d\u540d\u4e3a `sample_0001.png`\uff0c\u65b9\u4fbf\u7ba1\u7406\u548c\u540e\u7eed\u8bad\u7ec3\u3002\n\n---\n\n\u4f60\u53ea\u9700\u8981\u628a\u56fe\u7247\u653e\u5230`source_folder`\u76ee\u5f55\uff0c\u8fd0\u884c\u811a\u672c\uff0c\u5c31\u80fd\u5f97\u5230\u7edf\u4e00\u5c3a\u5bf8\u4e14\u89c4\u8303\u547d\u540d\u7684\u56fe\u7247\u7528\u4e8e\u8bad\u7ec3\u3002\n\n\u5982\u679c\u540e\u7eed\u9700\u8981\u66f4\u591a\u9884\u5904\u7406\u6b65\u9aa4\u6216\u6279\u91cf\u5904\u7406\u6807\u6ce8\u6587\u4ef6\uff0c\u4e5f\u53ef\u4ee5\u544a\u8bc9\u6211\uff0c\u6211\u5e2e\u4f60\u6539\u8fdb\u3002\nUser: \u6211\u9700\u8981\u51c6\u5907\u6279\u6ce8\u6587\u4ef6\u5417\nAssistant: \u4f60\u7528 `anomalib` \u505a\u5de5\u4e1a\u7f3a\u9677\u68c0\u6d4b\uff0c**\u6279\u6ce8\u6587\u4ef6\uff08\u6807\u6ce8\u6587\u4ef6\uff09\u4e00\u822c\u4e0d\u662f\u5fc5\u987b\u7684**\uff0c\u56e0\u4e3aPatchCore\u8fd9\u7c7b\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\u65b9\u6cd5**\u53ea\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3\uff0c\u4e0d\u9700\u8981\u7f3a\u9677\u7684\u6807\u6ce8\u4fe1\u606f**\u3002\u4f46\u662f\uff0c\u6279\u6ce8\u6587\u4ef6\uff08\u5982 LabelMe \u751f\u6210\u7684\u7f3a\u9677\u533a\u57df\u6807\u6ce8\u6216\u63a9\u7801\uff09**\u5728\u4ee5\u4e0b\u573a\u666f\u975e\u5e38\u6709\u7528**\uff1a\n\n---\n\n## \u4ec0\u4e48\u65f6\u5019\u9700\u8981\u51c6\u5907\u6279\u6ce8\u6587\u4ef6\uff1f\n\n1. **\u505a\u8bc4\u4f30\uff08\u9a8c\u8bc1\u96c6\uff09\u65f6** \n - \u6709\u7f3a\u9677\u6837\u672c\u7684\u6807\u6ce8\uff0c\u65b9\u4fbf\u8ba1\u7b97\u5b9a\u4f4d\u51c6\u786e\u7387\uff08\u6bd4\u5982\u8ba1\u7b97\u70ed\u529b\u56fe\u548c\u63a9\u7801\u7684\u5339\u914d\u5ea6\uff09 \n - \u53ef\u6839\u636e\u6807\u6ce8\u9a8c\u8bc1\u6a21\u578b\u662f\u5426\u51c6\u786e\u6846\u5b9a\u7f3a\u9677\u533a\u57df\uff0c\u5bf9\u6a21\u578b\u6548\u679c\u505a\u5b9a\u91cf\u5206\u6790\n\n2. **\u8bad\u7ec3\u534a\u76d1\u7763\u6216\u76d1\u7763\u6a21\u578b\u65f6** \n - \u67d0\u4e9b\u5f02\u5e38\u68c0\u6d4b\u6a21\u578b\u6216\u8bed\u4e49\u5206\u5272\u6a21\u578b\u9700\u8981\u7f3a\u9677\u533a\u57df\u7684\u50cf\u7d20\u7ea7\u6807\u6ce8\u4f5c\u4e3aGT\n\n3. **\u8f85\u52a9\u53ef\u89c6\u5316\u548c\u7ed3\u679c\u5c55\u793a** \n - \u5bf9\u6bd4\u9884\u6d4b\u5f02\u5e38\u533a\u57df\u548c\u771f\u5b9e\u7f3a\u9677\u4f4d\u7f6e\uff0c\u751f\u6210\u66f4\u76f4\u89c2\u7684\u62a5\u544a\u6216\u6f14\u793a\n\n---\n\n## \u4f60\u76ee\u524d\u7684\u573a\u666f\u5efa\u8bae\n\n- **\u8bad\u7ec3\u9636\u6bb5**\uff1a\u53ea\u9700\u8981\u6536\u96c6\u5927\u91cf\u7684\u6b63\u5e38\u56fe\u7247\uff0c\u65e0\u9700\u6807\u6ce8\u6216\u6279\u6ce8\u3002 \n- **\u9a8c\u8bc1\u9636\u6bb5**\uff1a\u5efa\u8bae\u51c6\u5907\u4e00\u4e9b\u7f3a\u9677\u6837\u672c\u7684\u6807\u6ce8\uff08\u6279\u6ce8\uff09\u4f5c\u4e3a\u5730\u9762\u771f\u503c\uff0c\u7528\u6765\u8bc4\u4f30\u548c\u8c03\u8bd5\u6a21\u578b\u3002 \n- **\u90e8\u7f72\u9636\u6bb5**\uff1a\u4e0d\u5f3a\u5236\u9700\u8981\u6807\u6ce8\uff0c\u53ea\u8981\u6a21\u578b\u68c0\u6d4b\u5f97\u51fa\u5f02\u5e38\u533a\u57df\u5373\u53ef\u3002\n\n---\n\n## \u5982\u4f55\u505a\u6279\u6ce8\uff08\u7b80\u5355\u6d41\u7a0b\uff09\n\n- \u4f7f\u7528LabelMe\u6807\u6ce8\u7f3a\u9677\u4f4d\u7f6e\uff0c\u751f\u6210`.json`\u6587\u4ef6 \n- \u5229\u7528`labelme_json_to_dataset`\u547d\u4ee4\u8f6c\u6362\u6210\u63a9\u7801\u6587\u4ef6 \n- \u5c06\u6b63\u5e38\u6837\u672c\u548c\u7f3a\u9677\u6837\u672c\uff08\u9644\u5e26\u63a9\u7801\uff09\u5206\u5f00\u653e\u5728\u9a8c\u8bc1\u96c6\u76ee\u5f55\n\n---\n\n## \u603b\u7ed3\n\n| \u9636\u6bb5 | \u662f\u5426\u9700\u8981\u6279\u6ce8\u6587\u4ef6\uff1f | \u4f5c\u7528 |\n|------------|---------------------------------|-----------------------|\n| \u8bad\u7ec3 | \u5426 | \u65e0\u76d1\u7763\u53ea\u7528\u6b63\u5e38\u6837\u672c |\n| \u9a8c\u8bc1/\u6d4b\u8bd5 | \u5efa\u8bae\u6709 | \u8bc4\u4f30\u5b9a\u4f4d\u6027\u80fd\uff0c\u6307\u5bfc\u4f18\u5316\u6a21\u578b |\n| \u7ed3\u679c\u5c55\u793a | \u53ef\u9009 | \u76f4\u89c2\u5bf9\u6bd4\u9884\u6d4b\u548c\u771f\u503c |\n\n---\n\n\u5982\u679c\u4f60\u8fd8\u6ca1\u6709\u6807\u6ce8\u5de5\u5177\u6216\u6279\u6ce8\u6d41\u7a0b\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u5957\u4ece\u6807\u6ce8\u5230\u63a9\u7801\u751f\u6210\uff0c\u518d\u5230\u4e0e\u6a21\u578b\u8bc4\u4f30\u914d\u5408\u7684**\u5b8c\u6574\u6d41\u7a0b\u548c\u4ee3\u7801\u793a\u4f8b**\uff0c\u8ba9\u4f60\u7cfb\u7edf\u6027\u7ba1\u7406\u6279\u6ce8\u6587\u4ef6\u548c\u5bf9\u5e94\u56fe\u50cf\u3002\n\n---\n\n\u9700\u8981\u7684\u8bdd\uff0c\u544a\u8bc9\u6211\uff1a\n- \u662f\u5426\u9700\u8981\u6807\u6ce8\u5de5\u5177\u53ca\u6559\u7a0b\n- \u662f\u5426\u9700\u8981\u6279\u6ce8\u548c\u63a9\u7801\u6587\u4ef6\u6279\u5904\u7406\u811a\u672c\n- \u662f\u5426\u60f3\u7528\u63a9\u7801\u505a\u6a21\u578b\u8bc4\u6d4b\u7684\u793a\u4f8b\u4ee3\u7801\n\n\u6211\u5e2e\u4f60\u4e00\u5957\u65b9\u6848\u505a\u4e0b\u6765\uff01\nUser: \u4e00\u5957\u505a\u4e0b\u6765\u5427\nAssistant: \u660e\u767d\uff01\u6211\u5e2e\u4f60\u4ece\u5934\u5230\u5c3e\u5199\u4e00\u5957\u5b8c\u6574\u7684\u6d41\u7a0b\u793a\u8303\uff0c\u5305\u62ec\uff1a\n\n- **\u7528LabelMe\u505a\u7f3a\u9677\u6807\u6ce8** \n- **\u6279\u91cf\u751f\u6210\u5bf9\u5e94\u63a9\u7801\uff08\u4e8c\u8fdb\u5236\u63a9\u7801\uff09** \n- **\u7ba1\u7406\u548c\u89c4\u8303\u56fe\u7247+\u6807\u6ce8\u6587\u4ef6\u547d\u540d\u4e0e\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6** \n- **\u7528anomalib\u8bad\u7ec3PatchCore\u6a21\u578b\uff08\u53ea\u7528\u6b63\u5e38\u6837\u672c\uff09** \n- **\u7528\u6807\u6ce8\u63a9\u7801\u505a\u9a8c\u8bc1\u96c6\u5f02\u5e38\u5b9a\u4f4d\u8bc4\u4f30\u793a\u8303** \n- **\u6700\u7ec8\u63a8\u7406\u4e0e\u5f02\u5e38\u533a\u57df\u53ef\u89c6\u5316\uff08\u542b\u8fb9\u754c\u6846\uff09**\n\n---\n\n# \u4e00\u3001\u7f3a\u9677\u6807\u6ce8\uff08LabelMe\uff09\n\n1. \u5b89\u88c5LabelMe\uff1a\n```bash\npip install labelme\n```\n\n2. \u542f\u52a8\u6807\u6ce8\u5de5\u5177\uff1a\n```bash\nlabelme\n```\n\n3. \u6253\u5f00\u542b\u7f3a\u9677\u7684\u56fe\u7247\uff0c\u9009\u62e9\u201cCreate Polygon\u201d\uff0c\u56f4\u7ed5\u7f3a\u9677\u753b\u591a\u8fb9\u5f62\uff0c\u8f93\u5165\u6807\u7b7e\uff08\u5982\u201cdefect\u201d\uff09\uff0c\u4fdd\u5b58\u540e\u4f1a\u751f\u6210`.json`\u6587\u4ef6\u3002\n\n4. \u6807\u6ce8\u5b8c\u6210\u540e\uff0c\u4fdd\u5b58\u548c\u7ba1\u7406`json`\u6587\u4ef6\uff0c\u4fdd\u8bc1`.json`\u4e0e\u5bf9\u5e94\u56fe\u7247\u6587\u4ef6\u540d\u4e00\u81f4\u3002\n\n---\n\n# \u4e8c\u3001\u6279\u91cf\u751f\u6210\u63a9\u7801\u811a\u672c\uff08labelme_json_to_dataset\uff09\n\n\u5efa\u4e00\u4e2a\u811a\u672c`generate_masks.py`\uff0c\u6279\u91cf\u4ee5`labelme_json_to_dataset`\u5c06json\u8f6c\u6210\u63a9\u7801\uff1a\n\n```python\nimport os\nimport subprocess\n\ndef batch_generate_masks(label_dir, mask_output_dir):\n os.makedirs(mask_output_dir, exist_ok=True)\n for json_file in os.listdir(label_dir):\n if not json_file.endswith(\".json\"):\n continue\n json_path = os.path.join(label_dir, json_file)\n base_name = os.path.splitext(json_file)[0]\n output_path = os.path.join(mask_output_dir, base_name)\n os.makedirs(output_path, exist_ok=True)\n\n cmd = f\"labelme_json_to_dataset {json_path} -o {output_path}\"\n subprocess.run(cmd, shell=True)\n print(f\"\u5df2\u751f\u6210\u63a9\u7801: {output_path}/label.png\")\n\nif __name__ == \"__main__\":\n label_dir = \"./defect_images\" # json\u6240\u5728\u76ee\u5f55\n mask_output = \"./masks\"\n batch_generate_masks(label_dir, mask_output)\n```\n\n--- \n\u8fd0\u884c\uff1a\n```bash\npython generate_masks.py\n```\n\u751f\u6210\u7684`label.png`\u5373\u4e3a\u7f3a\u9677\u63a9\u7801\uff08\u5f69\u8272\u7684\uff0c\u4e00\u822c\u5206\u7c7b\u5c11\u53ef\u4ee5\u5f53\u4e8c\u503c\u63a9\u7801\u7528\uff09\u3002\n\n---\n\n# \u4e09\u3001\u6570\u636e\u96c6\u6574\u7406\u4e0e\u5212\u5206\uff08\u56fe\u7247+json\u91cd\u547d\u540d+\u5206\u7c7b\uff09\n\n\u5199\u6570\u636e\u7ba1\u7406\u811a\u672c`manage_dataset.py`\uff0c\u81ea\u52a8\u5bf9\u6b63\u5e38\u56fe\u7247\u3001\u7f3a\u9677\u56fe\u7247\u53cajson\u91cd\u547d\u540d\u3001\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\uff1a\n\n```python\nimport os\nimport shutil\nimport random\nimport json\n\ndef standard_name(idx):\n return f\"sample_{idx:04d}\"\n\ndef filter_images(lst):\n exts = (\".png\", \".jpg\", \".jpeg\")\n return [f for f in lst if f.lower().endswith(exts)]\n\ndef has_annotations(json_path):\n if not os.path.exists(json_path):\n return False\n try:\n with open(json_path, \"r\", encoding=\"utf-8\") as f:\n data = json.load(f)\n return bool(data.get(\"shapes\"))\n except:\n return False\n\ndef manage_dataset(normal_dir, defect_dir, output_dir, val_ratio=0.2, seed=42):\n os.makedirs(output_dir, exist_ok=True)\n for split in [\"train\", \"valid\"]:\n for cls in [\"good\", \"defect\"]:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n normal_imgs = filter_images(os.listdir(normal_dir))\n defect_imgs = filter_images(os.listdir(defect_dir))\n\n random.seed(seed)\n random.shuffle(normal_imgs)\n random.shuffle(defect_imgs)\n\n def split(lst): # train/valid\u5212\u5206\n n = len(lst)\n n_val = max(1, int(n * val_ratio))\n return lst[:-n_val], lst[-n_val:]\n\n normal_train, normal_val = split(normal_imgs)\n defect_train, defect_val = split(defect_imgs)\n\n idx = 0\n\n def copy_files(lst, src_dir, spl, cls, with_json):\n nonlocal idx\n for img_name in lst:\n idx += 1\n new_name = standard_name(idx)\n ext = os.path.splitext(img_name)[1].lower()\n dst_img = os.path.join(output_dir, spl, cls, new_name + ext)\n shutil.copy2(os.path.join(src_dir, img_name), dst_img)\n print(f\"{img_name} => {dst_img}\")\n\n if with_json:\n json_name = os.path.splitext(img_name)[0] + \".json\"\n src_json = os.path.join(src_dir, json_name)\n if has_annotations(src_json):\n dst_json = os.path.join(output_dir, spl, cls, new_name + \".json\")\n shutil.copy2(src_json, dst_json)\n print(f\"{json_name} => {dst_json}\")\n\n print(\"\u590d\u5236\u6b63\u5e38\u56fe\u7247...\")\n copy_files(normal_train, normal_dir, \"train\", \"good\", False)\n copy_files(normal_val, normal_dir, \"valid\", \"good\", False)\n\n print(\"\u590d\u5236\u7f3a\u9677\u56fe\u7247\u53ca\u6807\u6ce8...\")\n copy_files(defect_train, defect_dir, \"train\", \"defect\", True)\n copy_files(defect_val, defect_dir, \"valid\", \"defect\", True)\n\n print(\"\u6570\u636e\u96c6\u6574\u7406\u5b8c\u6210\uff01\")\n\nif __name__ == \"__main__\":\n manage_dataset(\n normal_dir=\"./normal_images\",\n defect_dir=\"./defect_images\",\n output_dir=\"./data\",\n val_ratio=0.2\n )\n```\n\n---\n\n# \u56db\u3001\u8bad\u7ec3\u6a21\u578b\uff08anomalib\uff09\n\n1. \u51c6\u5907\u597d`data/train/good`\u548c`data/valid/{good,defect}`\u3002 \n2. \u914d\u7f6e`config.yaml`\uff08\u53c2\u8003\u524d\u9762\u793a\u8303\uff0c\u4e3b\u5e72\u7528resnet18\uff0c\u8f93\u5165256x256\uff09\u3002 \n3. \u8bad\u7ec3\u811a\u672c\u5982\u4e4b\u524d\u6559\u4f60\u7684`train.py`\u3002\n\n---\n\n# \u4e94\u3001\u9a8c\u8bc1\u96c6\u5b9a\u4f4d\u8bc4\u4f30\u793a\u4f8b\uff08\u7528\u63a9\u7801\uff09\n\n\u5199\u4e2a\u7b80\u5355\u811a\u672c`eval_locate.py`\u793a\u8303\u5982\u4f55\u57fa\u4e8e\u6a21\u578b\u9884\u6d4b\u7684\u5f02\u5e38\u70ed\u529b\u56fe\u548c\u771f\u5b9e\u63a9\u7801\u8ba1\u7b97\u7b80\u5355\u7684\u5b9a\u4f4d\u51c6\u786e\u7387\uff08\u5982IoU\uff09\uff1a\n\n```python\nimport cv2\nimport numpy as np\n\ndef load_binary_mask(mask_path):\n mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)\n return (mask > 0).astype(np.uint8)\n\ndef binarize_anomaly_map(anomaly_map, threshold=0.4):\n norm_map = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n return (norm_map > threshold).astype(np.uint8)\n\ndef compute_iou(mask_gt, mask_pred):\n intersection = np.logical_and(mask_gt, mask_pred).sum()\n union = np.logical_or(mask_gt, mask_pred).sum()\n if union == 0:\n return 1.0 if intersection == 0 else 0.0\n return intersection / union\n\n# \u5e94\u7528\u793a\u8303\uff1a\ngt_mask = load_binary_mask(\"./masks/sample_0001/label.png\")\npred_mask = binarize_anomaly_map(anomaly_map, 0.4)\niou = compute_iou(gt_mask, pred_mask)\nprint(f\"IoU\u5b9a\u4f4d\u51c6\u786e\u7387: {iou:.3f}\")\n```\n\n> \u7528\u6b64\u65b9\u5f0f\u5728\u9a8c\u8bc1\u96c6\u5faa\u73af\u8ba1\u7b97\u5373\u53ef\u5f97\u5230\u5b9a\u4f4d\u6027\u80fd\u53c2\u8003\u3002\n\n---\n\n# \u516d\u3001\u63a8\u7406\u4e0e\u53ef\u89c6\u5316\n\n\u548c\u4e4b\u524d\u6559\u7684\u4ee3\u7801\u4e00\u6837\uff0c\u7528`Inferencer`\u505a\u63a8\u7406\uff0c\u53e0\u52a0\u5f02\u5e38\u70ed\u529b\u56fe\uff0c\u5e76\u57fa\u4e8e\u9608\u503c\u627e\u5230\u8fde\u901a\u533a\u57df\u505a\u8fb9\u754c\u6846\uff0c\u5c55\u793a\u7ed9\u7528\u6237\u3002\n\n---\n\n# \u4e03\u3001\u603b\u7ed3\n\n| \u6b65\u9aa4 | \u5185\u5bb9 |\n|---------------------|-----------------------------------------|\n| 1. \u6807\u6ce8\u7f3a\u9677 | \u7528LabelMe\u591a\u8fb9\u5f62\u6807\u6ce8\u7f3a\u9677\uff0c\u751f\u6210json |\n| 2. \u6279\u91cf\u751f\u6210\u63a9\u7801 | \u7528`labelme_json_to_dataset`\u6216\u811a\u672c\u6279\u5904\u7406\u751f\u6210\u63a9\u7801 |\n| 3. \u6570\u636e\u96c6\u7ba1\u7406 | \u81ea\u52a8\u91cd\u547d\u540d\u5e76\u5212\u5206\u4e3a\u8bad\u7ec3\u96c6\uff08\u6b63\u5e38\uff09\u3001\u9a8c\u8bc1\u96c6\uff08\u6b63\u5e38+\u7f3a\u9677\uff09 |\n| 4. \u6a21\u578b\u8bad\u7ec3 | \u7528`anomalib` PatchCore\uff0c\u4ec5\u7528\u6b63\u5e38\u6837\u672c\u8bad\u7ec3 |\n| 5. \u9a8c\u8bc1\u96c6\u5b9a\u4f4d\u8bc4\u4f30 | \u7528\u63a9\u7801\u5bf9\u6bd4\u9884\u6d4b\u5f02\u5e38\u70ed\u529b\u56fe\uff0c\u8ba1\u7b97IoU\u7b49\u6307\u6807 |\n| 6. \u63a8\u7406\u7f3a\u9677\u5c55\u793a | \u5f02\u5e38\u70ed\u529b\u56fe\u53e0\u52a0\u539f\u56fe\uff0c\u505a\u9608\u503c\u5206\u5272\uff0c\u6846\u9009\u5f02\u5e38\u533a\u57df |\n\n---\n\n# \u5982\u679c\u4f60\u9700\u8981\uff1a\n\n- \u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u6240\u6709\u76f8\u5173\u7684\u8f85\u52a9\u811a\u672c \n- \u7ed9\u4f60\u5199\u4e00\u4e2a\u5b8c\u6574\u7684Demo\u6559\u7a0b\uff08\u4ece\u6807\u6ce8\u3001\u63a9\u7801\u3001\u6570\u636e\u96c6\u5230\u8bad\u7ec3\u63a8\u7406\uff09 \n- \u5e2e\u4f60\u8c03\u8bd5\u8bad\u7ec3\u6216\u63a8\u7406\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u4efb\u4f55\u95ee\u9898\n\n\u968f\u65f6\u544a\u8bc9\u6211\uff0c\u6211\u5e2e\u4f60\u628a\u6574\u4e2a\u6d41\u6c34\u7ebf\u642d\u8d77\u6765\uff0c\u4e00\u6b65\u4e00\u6b65\u5b8c\u6210\uff01\nUser: \u9884\u5904\u7406\u9636\u6bb5\u8981\u6ce8\u610f\u4ec0\u4e48\u5417\uff0c\u6211\u4e0d\u662f\u505a\u74f6\u5b50\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\uff0cdemo\u6559\u7a0b\u5427\uff0c\u4e0d\u9700\u8981\u70ed\u529b\u56fe\u5c55\u793a\uff0c\u9700\u8981\u6846\u51fa\u7f3a\u9677\u533a\u57df\nAssistant: \u660e\u767d\u4e86\uff01\u4f60\u60f3\u505a\u7684\u662f\u4e00\u4e2a**\u4e13\u6ce8\u4e8e\u74f6\u5b50\u5370\u5237\u8d28\u91cf\u68c0\u6d4b**\u7684\u5de5\u4e1a\u5f02\u5e38\u68c0\u6d4bDemo\uff0c\u91cd\u70b9\u662f\uff1a\n\n- \u9884\u5904\u7406\u9636\u6bb5\u5982\u4f55\u5904\u7406\u56fe\u7247\u63d0\u9ad8\u6a21\u578b\u6548\u679c\n- \u4f7f\u7528`anomalib`\u642d\u5efa\u8bad\u7ec3\u548c\u63a8\u7406\u6d41\u7a0b\n- **\u4e0d\u9700\u8981\u5f02\u5e38\u70ed\u529b\u56fe\u5c55\u793a\uff0c\u53ea\u9700\u8981\u76f4\u63a5\u5728\u539f\u56fe\u4e0a\u6846\u51fa\u7f3a\u9677\u533a\u57df**\n\n\u4e0b\u9762\u6211\u7ed9\u4f60\u6309\u6b65\u9aa4\u5199\u4e00\u4e2a\u57fa\u4e8e`anomalib`\u7684**\u5b9e\u7528Demo\u6559\u7a0b**\uff0c\u5305\u542b\u9884\u5904\u7406\u5173\u952e\u70b9\u3001\u8bad\u7ec3\u4ee3\u7801\u3001\u63a8\u7406\u53ca\u7f3a\u9677\u533a\u57df\u6846\u51fa\u793a\u8303\u3002\n\n---\n\n# \u4e00\u3001\u9884\u5904\u7406\u9636\u6bb5\u8981\u6ce8\u610f\u7684\u5173\u952e\u70b9\n\n1. **\u56fe\u50cf\u5c3a\u5bf8\u7edf\u4e00** \n - \u7edf\u4e00\u8c03\u6574\u4e3a\u6a21\u578b\u8f93\u5165\u5c3a\u5bf8\uff08\u4f8b\uff1a256\u00d7256\u6216512\u00d7512\uff09 \n - \u5efa\u8bae\u5728\u8c03\u6574\u65f6\u4fdd\u6301\u539f\u56fe\u6bd4\u4f8b\uff0c\u4f7f\u7528\u586b\u5145\u9ed1\u8fb9\u6216\u767d\u8fb9\uff0c\u907f\u514d\u56fe\u50cf\u53d8\u5f62\u5bfc\u81f4\u7279\u5f81\u9519\u4e71\u3002\n\n2. **\u56fe\u50cf\u8d28\u91cf\u4fdd\u969c** \n - \u5149\u7ebf\u5747\u5300\uff0c\u907f\u514d\u5f3a\u70c8\u9634\u5f71\u6216\u53cd\u5149 \n - \u4fdd\u6301\u7126\u70b9\u6e05\u6670\uff0c\u51cf\u5c11\u6a21\u7cca\n\n3. **\u80cc\u666f\u7b80\u6d01\u4e0e\u88c1\u526a** \n - \u91c7\u96c6\u65f6\u5c3d\u91cf\u8ba9\u80cc\u666f\u7b80\u5355\u4e00\u81f4\uff0c\u51cf\u5c11\u5e72\u6270 \n - \u53ef\u4ee5\u901a\u8fc7\u88c1\u526a\u6216ROI\u5b9a\u4f4d\u53ea\u4fdd\u7559\u5370\u5237\u533a\u57df\uff0c\u51cf\u5c11\u80cc\u666f\u5f71\u54cd\n\n4. **\u8272\u5f69\u7a7a\u95f4\u9009\u62e9** \n - RGB\u5f69\u8272\u8f93\u5165\u5373\u53ef\uff0c\u82e5\u5b57\u4f53\u5bf9\u6bd4\u5ea6\u4f4e\uff0c\u7070\u5ea6\u589e\u5f3a\uff08\u5982\u76f4\u65b9\u56fe\u5747\u8861\uff09\u53ef\u8f85\u52a9 \n - \u9884\u5904\u7406\u65f6\u4e0d\u5efa\u8bae\u8fc7\u5ea6\u8c03\u6574\uff0c\u4ee5\u514d\u6539\u53d8\u5b57\u4f53\u76f8\u5bf9\u7279\u5f81\n\n5. **\u6570\u636e\u589e\u5f3a\uff08\u53ef\u9009\uff0c\u540e\u7eed\u53ef\u52a0\uff09** \n - \u8f7b\u5fae\u65cb\u8f6c\u3001\u5e73\u79fb\u3001\u4eae\u5ea6\u53d8\u5316\u53ef\u589e\u5f3a\u6a21\u578b\u6cdb\u5316 \n - \u8bad\u7ec3\u524d\u505a\u597d\u89c4\u8303\u540e\u518d\u8003\u8651\u589e\u5f3a\uff08demo\u9636\u6bb5\u5148\u4e0d\u505a\uff09\n\n6. **\u6587\u4ef6\u547d\u540d\u548c\u683c\u5f0f\u7edf\u4e00** \n - \u7edf\u4e00\u547d\u540d\u65b9\u4fbf\u6279\u91cf\u52a0\u8f7d \n - \u4fdd\u5b58\u6210\u65e0\u635f\u683c\u5f0f\uff08png\u63a8\u8350\uff09\n\n---\n\n# \u4e8c\u3001\u793a\u8303\u9884\u5904\u7406\u811a\u672c\uff08\u7b80\u5355\u8c03\u6574\u5c3a\u5bf8\uff09\n\n```python\nimport os\nimport cv2\nimport numpy as np\n\ndef resize_and_pad(img, size=(256, 256)):\n h, w = img.shape[:2]\n scale = min(size[0]/w, size[1]/h)\n new_w, new_h = int(w*scale), int(h*scale)\n resized = cv2.resize(img, (new_w, new_h))\n canvas = np.zeros((size[1], size[0], 3), dtype=np.uint8)\n x_offset = (size[0] - new_w)//2\n y_offset = (size[1] - new_h)//2\n canvas[y_offset:y_offset+new_h, x_offset:x_offset+new_w] = resized\n return canvas\n\ndef preprocess_folder(input_dir, output_dir, target_size=(256,256)):\n os.makedirs(output_dir, exist_ok=True)\n files = sorted([f for f in os.listdir(input_dir) if f.lower().endswith(('.png','.jpg','.jpeg'))])\n \n for idx, fname in enumerate(files, 1):\n img_path = os.path.join(input_dir, fname)\n img = cv2.imread(img_path)\n if img is None:\n print(f\"\u65e0\u6cd5\u8bfb\u53d6: {fname}\")\n continue\n img_proc = resize_and_pad(img, target_size)\n out_name = f\"sample_{idx:04d}.png\"\n cv2.imwrite(os.path.join(output_dir, out_name), img_proc)\n print(f\"{fname} \u5904\u7406\u5b8c\u6210 -> {out_name}\")\n\nif __name__ == \"__main__\":\n preprocess_folder(\"./raw_images\", \"./processed_images\", (256,256))\n```\n\n---\n\n# \u4e09\u3001\u4f7f\u7528`anomalib`\u8bad\u7ec3PatchCore\u6a21\u578b\n\n1. \u51c6\u5907\u6570\u636e\u96c6\uff0c\u5982\u4e0b\u7ed3\u6784\uff1a\n\n```\ndata/\n\u251c\u2500\u2500 train/\n\u2502 \u2514\u2500\u2500 good/ # \u6b63\u5e38\u6837\u672c\uff0c\u9884\u5904\u7406\u540e\u653e\u8fd9\u91cc\n\u251c\u2500\u2500 valid/\n\u2502 \u251c\u2500\u2500 good/ # \u9a8c\u8bc1\u6b63\u5e38\u6837\u672c\n\u2502 \u2514\u2500\u2500 defect/ # \u9a8c\u8bc1\u7f3a\u9677\u6837\u672c\n```\n\n2. \u914d\u7f6e\u6587\u4ef6`config.yaml`\uff1a\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18\n input_size: 256\n embedding_method: random_projection\n\ntraining:\n batch_size: 8\n max_epochs: 20\n precision: 16\n seed: 42\n save_checkpoint: True\n\ndataset:\n name: custom\n path: ./data\n input_size: 256\n\ntrainer:\n accelerator: gpu # \u6ca1GPU\u6539\u6210cpu\n devices: 1\n max_epochs: 20\n\nlogger:\n wandb: {}\n```\n\n3. \u8bad\u7ec3\u811a\u672c`train.py`\uff1a\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train(config_path=\"config.yaml\"):\n config = OmegaConf.load(config_path)\n train_loader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n model = get_model(config.model)\n trainer = get_trainer(config.trainer)\n trainer.fit(model=model, train_dataloader=train_loader)\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n print(\"\u8bad\u7ec3\u5b8c\u6210\uff0c\u6a21\u578b\u5df2\u4fdd\u5b58 patchcore_best.ckpt\")\n\nif __name__ == \"__main__\":\n train()\n```\n\n---\n\n# \u56db\u3001\u63a8\u7406\u53ca\u76f4\u63a5\u6846\u51fa\u7f3a\u9677\u533a\uff08\u65e0\u70ed\u529b\u56fe\u5c55\u793a\uff09\n\n```python\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport torch\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\n\ndef visualize_defects_with_boxes(image_path, anomaly_map, threshold=0.4):\n img = cv2.imread(image_path)\n norm_map = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_uint8 = (norm_map * 255).astype(np.uint8)\n\n _, binary_map = cv2.threshold(anomaly_uint8, int(threshold*255), 255, cv2.THRESH_BINARY)\n kernel = np.ones((3,3), np.uint8)\n clean = cv2.morphologyEx(binary_map, cv2.MORPH_OPEN, kernel, iterations=1)\n\n contours, _ = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n for cnt in contours:\n if cv2.contourArea(cnt) < 100: # \u8fc7\u6ee4\u5c0f\u566a\u58f0\n continue\n x, y, w, h = cv2.boundingRect(cnt)\n cv2.rectangle(img, (x, y), (x+w, y+h), (0,0,255), 2)\n\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.title(\"\u7f3a\u9677\u533a\u57df\u6846\u9009\")\n plt.axis(\"off\")\n plt.show()\n\ndef infer_and_visualize(config_path, ckpt_path, image_path):\n config = get_configurable_parameters(config_path)\n model = get_model(config.model)\n checkpoint = torch.load(ckpt_path)\n model.load_state_dict(checkpoint[\"state_dict\"])\n model.eval()\n\n inferencer = Inferencer(config, model)\n results = inferencer.infer(image_path)\n\n anomaly_map = results[\"anomaly_map\"]\n visualize_defects_with_boxes(image_path, anomaly_map)\n\nif __name__ == \"__main__\":\n infer_and_visualize(\"config.yaml\", \"patchcore_best.ckpt\", \"./data/valid/defect/sample_0001.png\")\n```\n\n---\n\n# \u4e94\u3001\u5b8c\u6574\u6d41\u7a0b\u5efa\u8bae\n\n1. **\u539f\u56fe\u6279\u91cf\u8fd0\u884c\u9884\u5904\u7406\u811a\u672c\uff0c\u4fdd\u6301\u5c3a\u5bf8\u7edf\u4e00+\u91cd\u547d\u540d** \n2. **\u51c6\u5907\u597d\u8bad\u7ec3\u96c6\u6b63\u5e38\u6837\u672c(`train/good/`)\u548c\u9a8c\u8bc1\u96c6(\u5305\u542b\u6b63\u5e38\u548c\u7f3a\u9677)** \n3. **\u7f16\u8f91\u548c\u786e\u8ba4`config.yaml`\u6587\u4ef6** \n4. **\u8fd0\u884c`train.py`\u8fdb\u884c\u8bad\u7ec3** \n5. **\u7528`infer_and_visualize`\u51fd\u6570\u8fd0\u884c\u9a8c\u8bc1\u96c6\u7f3a\u9677\u56fe\uff0c\u67e5\u770b\u7f3a\u9677\u6846\u6548\u679c** \n\n---\n\n\u5982\u679c\u4f60\u6709\u73af\u5883\u6216\u4ee3\u7801\u4efb\u4f55\u95ee\u9898\u90fd\u53ef\u4ee5\u968f\u65f6\u63d0\uff0c\u6211\u5e2e\u4f60\u6392\u67e5\u3002 \n\u4e5f\u53ef\u4ee5\u5e2e\u4f60\u5199\u6279\u91cf\u9884\u5904\u7406\u6807\u6ce8\u6587\u4ef6\u3001\u63a9\u7801\u751f\u6210\u811a\u672c\u3001\u6a21\u578b\u8bc4\u6d4b\u6307\u6807\u4ee3\u7801\u7b49\u3002 \n\u4e00\u8d77\u628a\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u68c0\u505a\u6210\u4e13\u4e1a\u3001\u9ad8\u6548\u7684\u7cfb\u7edf\uff01\ud83d\ude80\nUser: \u4f60\u89c9\u5f97\u5728\u5f53\u524ddemo\u9636\u6bb5\uff0c\u9884\u5904\u7406\u5148\u600e\u4e48\u505a\uff0c\u5e2e\u6211\u628a\u8f85\u52a9\u811a\u672c\u90fd\u505a\u4e86\u5427\uff0c\u8bb2\u8bb2\u600e\u4e48\u7528\nAssistant: \u660e\u767d\uff01\u9488\u5bf9\u4f60\u5f53\u524d**\u9636\u6bb5\u7684\u9700\u6c42**\uff08\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u68c0\uff0c\u5148\u505a\u7b80\u5355\u9884\u5904\u7406\uff0c\u65b9\u4fbf\u8bad\u7ec3\u548c\u63a8\u7406\uff09\uff0c\u6211\u5e2e\u4f60\u6574\u7406\u4e86\u6700\u5b9e\u7528\u7684**\u8f85\u52a9\u811a\u672c\u5408\u96c6**\uff0c\u5e76\u9644\u8be6\u7ec6\u8bf4\u660e\u5982\u4f55\u7528\u3002\n\n---\n\n# 1. \u9884\u5904\u7406\u811a\u672c \u2014 \u7edf\u4e00\u5c3a\u5bf8 + \u91cd\u547d\u540d\uff08\u6838\u5fc3\uff09\n\n\u4fdd\u8bc1\u6240\u6709\u56fe\u50cf\u5c3a\u5bf8\u4e00\u81f4\u3001\u547d\u540d\u89c4\u8303\uff0c\u975e\u5e38\u5173\u952e\uff0c\u65b9\u4fbf\u540e\u7eed\u7528 `anomalib` \u8bad\u7ec3\u3002\n\n```python\nimport os\nimport cv2\nimport numpy as np\n\ndef resize_with_padding(img, target_size=(256, 256)):\n h, w = img.shape[:2]\n target_w, target_h = target_size\n\n scale = min(target_w / w, target_h / h)\n new_w, new_h = int(w * scale), int(h * scale)\n resized = cv2.resize(img, (new_w, new_h))\n\n canvas = np.zeros((target_h, target_w, 3), dtype=np.uint8)\n x_offset = (target_w - new_w) // 2\n y_offset = (target_h - new_h) // 2\n canvas[y_offset:y_offset + new_h, x_offset:x_offset + new_w] = resized\n return canvas\n\ndef batch_preprocess_rename(src_dir, dst_dir, target_size=(256, 256), start_index=1):\n os.makedirs(dst_dir, exist_ok=True)\n exts = ('.jpg', '.jpeg', '.png', '.bmp')\n\n files = sorted([f for f in os.listdir(src_dir) if f.lower().endswith(exts)])\n\n idx = start_index\n for filename in files:\n img_path = os.path.join(src_dir, filename)\n img = cv2.imread(img_path)\n if img is None:\n print(f\"\u8df3\u8fc7\u65e0\u6cd5\u8bfb\u53d6\u56fe\u50cf: {filename}\")\n continue\n\n img_resized = resize_with_padding(img, target_size)\n new_name = f\"sample_{idx:04d}.png\"\n dst_path = os.path.join(dst_dir, new_name)\n cv2.imwrite(dst_path, img_resized)\n print(f\"{filename} -> {new_name}\")\n\n idx += 1\n\n print(f\"\u5b8c\u6210 {idx - start_index} \u5f20\u56fe\u7247\u9884\u5904\u7406\uff0c\u4fdd\u5b58\u81f3 {dst_dir}\")\n\nif __name__ == \"__main__\":\n source_folder = \"./raw_images\" # \u539f\u59cb\u56fe\u7247\u5939\uff0c\u653e\u5f85\u5904\u7406\u56fe\n output_folder = \"./processed_images\" # \u9884\u5904\u7406\u540e\u4fdd\u5b58\u5939\n batch_preprocess_rename(source_folder, output_folder, target_size=(256, 256))\n```\n\n---\n\n# 2. \u6570\u636e\u96c6\u6574\u7406\uff08\u5206\u7c7b\u547d\u540d+\u5212\u5206\u8bad\u7ec3\u9a8c\u8bc1\u96c6\uff09\n\n\u5047\u8bbe\u4f60\u6709\u4e24\u4e2a\u6587\u4ef6\u5939\uff1a\n\n- `normal_images/`\uff08\u6b63\u5e38\u65e0\u7f3a\u9677\u56fe\uff09\n- `defect_images/`\uff08\u5e26\u7f3a\u9677\u56fe + \u53ef\u9009\u5bf9\u5e94json\u6807\u6ce8\uff09\n\n\u811a\u672c\u81ea\u52a8\u628a\u5b83\u4eec\u5212\u5206\u5230\u7edf\u4e00`data/train/good`, `data/valid/good`, `data/train/defect`, `data/valid/defect`\u76ee\u5f55\uff0c\u4e14\u56fe\u7247\u548cjson\u7edf\u4e00\u547d\u540d\u3002\n\n```python\nimport os\nimport shutil\nimport random\nimport json\n\ndef standard_name(idx):\n return f\"sample_{idx:04d}\"\n\ndef filter_images(files):\n return [f for f in files if f.lower().endswith(('.png', '.jpg', '.jpeg'))]\n\ndef has_annotation(json_path):\n if not os.path.exists(json_path):\n return False\n try:\n with open(json_path, 'r', encoding='utf-8') as f:\n data = json.load(f)\n return bool(data.get(\"shapes\"))\n except:\n return False\n\ndef manage_dataset(normal_dir, defect_dir, output_dir, val_ratio=0.2, seed=42):\n os.makedirs(output_dir, exist_ok=True)\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n normal_imgs = filter_images(os.listdir(normal_dir))\n defect_imgs = filter_images(os.listdir(defect_dir))\n\n random.seed(seed)\n random.shuffle(normal_imgs)\n random.shuffle(defect_imgs)\n\n def split_list(lst):\n n = len(lst)\n n_val = max(1, int(n * val_ratio))\n return lst[:-n_val], lst[-n_val:]\n\n normal_train, normal_val = split_list(normal_imgs)\n defect_train, defect_val = split_list(defect_imgs)\n\n idx = 0\n def copy_group(img_list, src_dir, split, cls, with_json):\n nonlocal idx\n for img_name in img_list:\n idx += 1\n new_name = standard_name(idx)\n ext = os.path.splitext(img_name)[1].lower()\n\n src_img_path = os.path.join(src_dir, img_name)\n dst_img_path = os.path.join(output_dir, split, cls, new_name + ext)\n shutil.copy2(src_img_path, dst_img_path)\n\n if with_json:\n json_name = os.path.splitext(img_name)[0] + '.json'\n src_json_path = os.path.join(src_dir, json_name)\n if has_annotation(src_json_path):\n dst_json_path = os.path.join(output_dir, split, cls, new_name + '.json')\n shutil.copy2(src_json_path, dst_json_path)\n print(f\"\u590d\u5236 {img_name} -> {dst_img_path}\")\n\n print(\"\u590d\u5236\u6b63\u5e38\u56fe\u7247...\")\n copy_group(normal_train, normal_dir, 'train', 'good', False)\n copy_group(normal_val, normal_dir, 'valid', 'good', False)\n\n print(\"\u590d\u5236\u7f3a\u9677\u56fe\u7247\u53ca\u6807\u6ce8...\")\n copy_group(defect_train, defect_dir, 'train', 'defect', True)\n copy_group(defect_val, defect_dir, 'valid', 'defect', True)\n\n print(f\"\u6570\u636e\u96c6\u6574\u7406\u5b8c\u6210\uff0c\u5171\u5904\u7406 {idx} \u5f20\u56fe\u7247\u3002\")\n\nif __name__ == \"__main__\":\n manage_dataset(\n normal_dir=\"./processed_normal\", # \u9884\u5904\u7406\u540e\u6b63\u5e38\u56fe\u8def\u5f84\n defect_dir=\"./processed_defect\", # \u9884\u5904\u7406\u540e\u7f3a\u9677\u56fe\u8def\u5f84\uff08\u542bjson\u6807\u6ce8\uff09\n output_dir=\"./data\", # \u76ee\u6807\u8f93\u51fa\u76ee\u5f55\n val_ratio=0.2\n )\n```\n\n---\n\n# 3. \u6807\u6ce8\u63a9\u7801\u6279\u91cf\u751f\u6210\u811a\u672c\n\n\u6807\u6ce8\u7528LabelMe\u4fdd\u5b58.json\u540e\uff0c\u8fd0\u884c\u6b64\u811a\u672c\u6279\u91cf\u751f\u6210\u5bf9\u5e94\u63a9\u7801\uff0c\u5e76\u653e\u5230\u7ed3\u6784\u5bf9\u5e94\u76ee\u5f55\uff1a\n\n```python\nimport os\nimport subprocess\n\ndef batch_generate_masks(label_dir, mask_root):\n os.makedirs(mask_root, exist_ok=True)\n for f in os.listdir(label_dir):\n if f.endswith('.json'):\n json_path = os.path.join(label_dir, f)\n base_name = os.path.splitext(f)[0]\n output_dir = os.path.join(mask_root, base_name)\n os.makedirs(output_dir, exist_ok=True)\n cmd = f\"labelme_json_to_dataset {json_path} -o {output_dir}\"\n subprocess.run(cmd, shell=True)\n print(f\"\u751f\u6210\u63a9\u7801: {output_dir}/label.png\")\n\nif __name__ == \"__main__\":\n batch_generate_masks(\"./data/valid/defect\", \"./data/masks\")\n```\n\n---\n\n# 4. \u8bad\u7ec3 PatchCore \u7684\u4e3b\u8981\u4ee3\u7801\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train_anomalib(config_path=\"config.yaml\"):\n config = OmegaConf.load(config_path)\n train_loader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n model = get_model(config.model)\n trainer = get_trainer(config.trainer)\n trainer.fit(model=model, train_dataloader=train_loader)\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n print(\"\u8bad\u7ec3\u5b8c\u6210\uff0c\u6a21\u578b\u4fdd\u5b58\u81f3 patchcore_best.ckpt\")\n\nif __name__ == \"__main__\":\n train_anomalib()\n```\n\n---\n\n# 5. \u63a8\u7406 + \u7f3a\u9677\u533a\u57df\u6807\u6ce8\uff08\u76f4\u63a5\u753b\u6846\uff0c\u65e0\u70ed\u529b\u56fe\uff09\n\n```python\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport torch\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\n\ndef visualize_defect_boxes(image_path, anomaly_map, threshold=0.4):\n img = cv2.imread(image_path)\n norm_map = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_uint8 = (norm_map * 255).astype(np.uint8)\n\n _, binary = cv2.threshold(anomaly_uint8, int(threshold * 255), 255, cv2.THRESH_BINARY)\n kernel = np.ones((3,3), np.uint8)\n clean = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=1)\n\n contours, _ = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n for c in contours:\n if cv2.contourArea(c) < 100:\n continue\n x, y, w, h = cv2.boundingRect(c)\n cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)\n\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.title(\"\u7f3a\u9677\u533a\u57df\u6846\u51fa\")\n plt.axis('off')\n plt.show()\n\ndef inference_and_visualize(config_path, ckpt_path, image_path):\n config = get_configurable_parameters(config_path)\n model = get_model(config.model)\n checkpoint = torch.load(ckpt_path)\n model.load_state_dict(checkpoint['state_dict'])\n model.eval()\n\n inferencer = Inferencer(config, model)\n results = inferencer.infer(image_path)\n\n visualize_defect_boxes(image_path, results['anomaly_map'])\n\nif __name__ == \"__main__\":\n inference_and_visualize(\"config.yaml\", \"patchcore_best.ckpt\", \"./data/valid/defect/sample_0001.png\")\n```\n\n---\n\n# 6. \u4f7f\u7528\u6b65\u9aa4\u6c47\u603b\n\n1. \u51c6\u5907\u539f\u59cb\u56fe\u7247\uff0c\u8fd0\u884c **\u9884\u5904\u7406\u811a\u672c** \u7edf\u4e00\u5927\u5c0f\u548c\u547d\u540d\u3002 \n2. \u7528 **\u6570\u636e\u96c6\u6574\u7406\u811a\u672c** \u5c06\u6b63\u5e38\u548c\u7f3a\u9677\u6570\u636e\u5206\u7c7b\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\u3002 \n3. \u5982\u6709\u7f3a\u9677\u6807\u6ce8\uff0c\u7528 **\u63a9\u7801\u751f\u6210\u811a\u672c** \u6279\u91cf\u751f\u6210\u63a9\u7801\uff08\u9a8c\u8bc1\u9636\u6bb5\u8f85\u52a9\u8bc4\u4f30\u7528\uff09\u3002 \n4. \u4fee\u6539\u5e76\u786e\u8ba4 `config.yaml` \u914d\u7f6e\uff0c\u51c6\u5907\u8bad\u7ec3\u3002 \n5. \u8fd0\u884c\u8bad\u7ec3\u811a\u672c\u8bad\u7ec3PatchCore\u6a21\u578b\u3002 \n6. \u7528\u63a8\u7406\u811a\u672c\u68c0\u6d4b\u7f3a\u9677\uff0c\u76f4\u63a5\u8f93\u51fa\u6807\u6ce8\u6846\u53ef\u89c6\u5316\u3002 \n\n---\n\n\u5982\u679c\u4f60\u60f3\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\uff1a\n\n- \u5199**\u4e00\u4efd\u5b8c\u6574\u7684demo\u9879\u76ee\u793a\u8303**\uff0c\u542b\u76ee\u5f55\u7ed3\u6784\u3001\u6240\u6709\u811a\u672c\u548c\u793a\u8303\u6570\u636e\n- \u5e2e\u4f60\u8c03\u8bd5\u73af\u5883\u6216\u8fd0\u884c\u65f6\u9047\u5230\u7684\u9519\u8bef\uff0c\u966a\u4f60\u4e00\u6b65\u6b65\u505a\u5b8c\u6574\u4e2a\u6d41\u7a0b\n\n\u6b22\u8fce\u544a\u8bc9\u6211\u4f60\u7684\u6700\u65b0\u8fdb\u5ea6\u6216\u9047\u5230\u7684\u96be\u70b9\uff0c\u6211\u4eec\u4e00\u8d77\u641e\u5b9a\uff01\nUser: \u53ef\u4ee5\uff0c\u4f60\u89c9\u5f97\u9884\u5904\u7406demo\u9636\u6bb5\u600e\u4e48\u505a\u597d\nAssistant: \u9884\u5904\u7406\u5728demo\u9636\u6bb5\u7684\u4e3b\u8981\u76ee\u6807\u662f\u4fdd\u8bc1\u6570\u636e\u89c4\u8303\u3001\u7b80\u6d01\uff0c\u5c3d\u91cf\u51cf\u5c11\u5bf9\u6a21\u578b\u8bad\u7ec3\u7684\u5e72\u6270\u4e3a\u540e\u7eed\u7684\u5f02\u5e38\u68c0\u6d4b\u6253\u4e0b\u826f\u597d\u57fa\u7840\u3002\u7ed3\u5408\u4f60\u505a\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u7684\u9700\u6c42\uff0c\u6211\u7ed9\u4f60\u51e0\u70b9\u9488\u5bf9demo\u9636\u6bb5\u7684\u5b9e\u7528\u5efa\u8bae\u548c\u505a\u6cd5\uff1a\n\n---\n\n## \u4e00\u3001Demo\u9636\u6bb5\u9884\u5904\u7406\u4e3b\u8981\u76ee\u6807\u548c\u539f\u5219\n\n1. **\u5c3a\u5bf8\u7edf\u4e00** \n - \u786e\u4fdd\u6240\u6709\u56fe\u50cf\u90fd\u8f6c\u6362\u6210\u76f8\u540c\u5927\u5c0f\uff08\u5982256x256\uff09\uff0c\u65b9\u4fbf\u6279\u91cf\u8bad\u7ec3\u3002 \n - \u63a8\u8350\u4fdd\u6301\u539f\u56fe\u6bd4\u4f8b\u4e0d\u53d8\u3001\u505a\u9ed1\u8fb9\uff08padding\uff09\u586b\u5145\uff0c\u907f\u514d\u62c9\u4f38\u5bfc\u81f4\u5b57\u4f53\u53d8\u5f62\uff0c\u5f71\u54cd\u7279\u5f81\u8868\u8fbe\u3002 \n\n2. **\u4fdd\u8bc1\u56fe\u50cf\u8d28\u91cf** \n - \u8981\u6c42\u62cd\u6444\u56fe\u6e05\u6670\u3001\u805a\u7126\u51c6\u786e\uff0c\u4e0d\u6a21\u7cca\u3002 \n - \u7531\u4e8edemo\u9636\u6bb5\u6570\u636e\u91cf\u4e0d\u5927\uff0c\u5c3d\u91cf\u9009\u7528\u6e05\u6670\u91c7\u96c6\u7684\u56fe\u50cf\uff0c\u907f\u514d\u566a\u70b9\u3001\u9634\u5f71\u592a\u5927\u7b49\u574f\u6837\u3002\n\n3. **\u80cc\u666f\u7b80\u6d01** \n - \u91c7\u96c6\u65f6\u80cc\u666f\u5c3d\u91cf\u5e72\u51c0\u3001\u7edf\u4e00\uff0c\u907f\u514d\u51fa\u73b0\u590d\u6742\u5e72\u6270\u7269\u3002 \n - \u53ef\u901a\u8fc7\u88c1\u526a\u91cd\u70b9\u5370\u5237\u533a\u57df\uff0c\u51cf\u5c11\u65e0\u5173\u533a\u57df\u5e72\u6270\u3002\n\n4. **\u6587\u4ef6\u547d\u540d\u89c4\u8303** \n - \u7edf\u4e00\u6587\u4ef6\u547d\u540d\uff0c\u65b9\u4fbf\u6279\u91cf\u52a0\u8f7d\u548c\u6570\u636e\u5212\u5206\u3002 \n - \u63a8\u8350\u5982 `sample_0001.png` \u8fd9\u79cd\u8fde\u7eed\u683c\u5f0f\u3002\n\n5. **\u9884\u5904\u7406\u4fdd\u6301\u7b80\u5355** \n - \u6682\u65f6\u65e0\u9700\u5bf9\u6bd4\u5ea6\u589e\u5f3a\u3001\u566a\u58f0\u6ee4\u6ce2\u7b49\u590d\u6742\u56fe\u50cf\u5904\u7406\uff0c\u4e4b\u540e\u6839\u636e\u6a21\u578b\u8868\u73b0\u9010\u6b65\u4f18\u5316\u3002 \n - \u5c06\u91cd\u70b9\u653e\u5728\u6d41\u7a0b\u5b8c\u6574\u6027\u548c\u8bad\u7ec3\u8fd0\u884c\u4e0a\u3002\n\n---\n\n## \u4e8c\u3001\u5177\u4f53\u53ef\u5b9e\u65bd\u9884\u5904\u7406\u65b9\u6848\uff08\u9002\u5408Demo\uff09\n\n- **\u8bfb\u53d6\u539f\u59cb\u56fe\u50cf** \n- **\u7f29\u653e\u56fe\u50cf\uff0c\u4f7f\u77ed\u8fb9\u6216\u957f\u8fb9\u9002\u914d256x256\u4e4b\u7c7b\u5c3a\u5bf8\uff0c\u4fdd\u6301\u5bbd\u9ad8\u6bd4** \n- **\u5728\u4e0d\u8db3\u8fb9\u7f18\u7528\u9ed1\u8272\u586b\u5145\uff0c\u751f\u6210\u56fa\u5b9a\u5c3a\u5bf8\u6b63\u65b9\u5f62\u56fe\u50cf** \n- **\u4fdd\u5b58\u6210\u7edf\u4e00\u683c\u5f0f\uff08png\uff09\u548c\u7edf\u4e00\u547d\u540d\uff0c\u5b58\u653e\u6307\u5b9a\u6587\u4ef6\u5939**\n\n\u8fd9\u6837\u8f93\u5165\u8fdb\u5165PatchCore\u6a21\u578b\u65f6\uff0c\u6bcf\u4e2apatch\u90fd\u80fd\u4fdd\u6301\u6b63\u5e38\u7684\u5b57\u4f53\u7279\u5f81\u7eb9\u7406\u5206\u5e03\uff0c\u4e0d\u88ab\u53d8\u5f62\u3001\u62c9\u4f38\u5e72\u6270\u3002\n\n---\n\n## \u4e09\u3001\u4e3a\u4ec0\u4e48\u4e0d\u5efa\u8baeDemo\u9636\u6bb5\u590d\u6742\u9884\u5904\u7406\uff1f\n\n- \u7b80\u5355\u9884\u5904\u7406\u907f\u514d\u8fc7\u62df\u5408\u548c\u8bef\u5bfc\u6a21\u578b\u5b66\u4e60\u65e0\u5173\u7279\u5f81\u3002 \n- \u8fc7\u591a\u56fe\u50cf\u589e\u5f3a\u548c\u6ee4\u6ce2\uff0c\u53ef\u80fd\u7834\u574f\u5370\u5237\u5b57\u4f53\u7ec6\u8282\uff0c\u5bfc\u81f4\u6a21\u578b\u65e0\u6cd5\u51c6\u786e\u63d0\u53d6\u6b63\u5e38\u7684\u7279\u5f81\u7801\u3002 \n- Demo\u9636\u6bb5\u76ee\u6807\u662f\u8dd1\u901a\u6d41\u7a0b\uff0c\u5c55\u793a\u6838\u5fc3\u529f\u80fd\uff0c\u590d\u6742\u8fc7\u7a0b\u653e\u540e\u7eed\u8fed\u4ee3\u3002\n\n---\n\n## \u56db\u3001\u9884\u5904\u7406demo\u793a\u8303\u811a\u672c\u8bf4\u660e\uff08\u57fa\u4e8e\u4f60\u5df2\u6709\u811a\u672c\uff09\n\n- \u4ec5\u505aresize+padding\u4fdd\u8bc1\u56fe\u50cf\u5927\u5c0f\u7edf\u4e00 \n- \u91cd\u547d\u540d\u56fe\u7247\u65b9\u4fbf\u6570\u636e\u7ba1\u7406 \n- \u8f93\u51fa\u8def\u5f84\u660e\u786e\uff0c\u65b9\u4fbf\u540e\u7eed\u8bad\u7ec3\u76f4\u63a5\u7528\n\n> \u6211\u524d\u9762\u7ed9\u4f60\u5199\u7684\u9884\u5904\u7406\u811a\u672c\u5c31\u662f\u57fa\u4e8e\u8fd9\u4e2a\u601d\u8def\uff0c\u5efa\u8bae\u4f60\u57fa\u4e8e\u90a3\u4e2a\u76f4\u63a5\u7528\u5373\u53ef\u3002\n\n---\n\n## \u4e94\u3001\u540e\u7eed\u4f18\u5316\u9884\u5904\u7406\u65b9\u5411\uff08\u975edemo\u7d27\u6025\uff0c\u53ef\u6309\u9700\u6269\u5c55\uff09\n\n1. **\u57fa\u4e8e\u5370\u5237\u5b57\u4f53\u7684\u5bf9\u6bd4\u5ea6\u589e\u5f3a**\uff08\u5982CLAHE\uff09 \n2. **\u53bb\u566a\u6ee4\u6ce2\uff08\u4e2d\u503c\u6ee4\u6ce2\uff09\u51cf\u5c11\u5b64\u7acb\u5c0f\u70b9/\u6bdb\u523a\u566a\u58f0** \n3. **\u81ea\u52a8ROI\u88c1\u526a\u5b9a\u4f4d\uff0c\u5254\u9664\u65e0\u5173\u80cc\u666f** \n4. **\u57fa\u4e8e\u989c\u8272\u7a7a\u95f4\u7684\u80cc\u666f\u53bb\u9664\u6216\u589e\u5f3a** \n5. **\u6570\u636e\u589e\u5f3a\u7b56\u7565\uff08\u65cb\u8f6c\u3001\u7ffb\u8f6c\u3001\u4eae\u5ea6\u8c03\u6574\uff09\u63d0\u5347\u6cdb\u5316\u6027**\n\n---\n\n## \u516d\u3001\u603b\u7ed3\u5efa\u8bae\n\n| \u9636\u6bb5 | \u9884\u5904\u7406\u91cd\u70b9 | \u5907\u6ce8 |\n|------------|------------------------------------|-------------------------|\n| Demo\u9636\u6bb5 | \u7edf\u4e00\u5c3a\u5bf8\u3001\u4fdd\u6301\u9ad8\u8d28\u91cf\u3001\u7edf\u4e00\u547d\u540d | \u5148\u8dd1\u901a\u8bad\u7ec3\u6d41\u7a0b\uff0c\u5c55\u793a\u6548\u679c |\n| \u540e\u7eed\u8fed\u4ee3\u9636\u6bb5 | \u9002\u5f53\u56fe\u50cf\u589e\u5f3a\u3001\u53bb\u566a\u3001\u80cc\u666f\u5904\u7406\u7b49 | \u63d0\u5347\u6a21\u578b\u9c81\u68d2\u6027\u548c\u51c6\u786e\u7387 |\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\uff1a\n\n- \u76f4\u63a5\u6574\u7406\u4e00\u5957\u5b8c\u6574\u7684**Demo\u9884\u5904\u7406+\u8bad\u7ec3+\u63a8\u7406+\u7f3a\u9677\u6846\u51fa**\u7684\u4e00\u4f53\u5316\u4ee3\u7801\u811a\u672c \n- \u8bb2\u89e3\u5982\u4f55\u8c03\u8bd5\u9884\u5904\u7406\u53c2\u6570\u89c2\u5bdf\u5bf9\u6a21\u578b\u6548\u679c\u7684\u5f71\u54cd \n- \u540e\u7eed\u5e2e\u4f60\u5199\u590d\u6742\u9884\u5904\u7406\u548c\u6570\u636e\u589e\u5f3a\u811a\u672c \n\n\u6b22\u8fce\u544a\u8bc9\u6211\u4f60\u540e\u7eed\u60f3\u91cd\u70b9\u7a81\u7834\u54ea\u5757\uff0c\u54b1\u4eec\u914d\u5408\u5feb\u51c6\u72e0\u628ademo\u505a\u51fa\u6765\uff01\nUser: \u80cc\u666f\u7b80\u6d01\u53ef\u4ee5\uff0c\u53ea\u8ba9\u6b63\u5e38\u56fe\u7247\u53ea\u51fa\u73b0\u4e2a\u74f6\u5b50\u5427\nAssistant: \u660e\u767d\u4f60\u7684\u9700\u6c42\uff1a**\u5728\u9636\u6bb5\uff0c\u62cd\u6444\u548c\u51c6\u5907\u7684\u6b63\u5e38\u56fe\u7247\u80cc\u666f\u5c3d\u91cf\u7b80\u6d01\uff0c\u53ea\u51fa\u73b0\u74f6\u5b50\u4e3b\u4f53**\uff0c\u8fd9\u6837\u5229\u4e8e\u6a21\u578b\u4e13\u6ce8\u5b66\u4e60\u74f6\u5b50\u7684\u6b63\u5e38\u7279\u5f81\uff0c\u907f\u514d\u80cc\u666f\u566a\u58f0\u5e72\u6270\u3002\n\n---\n\n# \u5982\u4f55\u505a\u5230\u201c\u80cc\u666f\u7b80\u6d01\uff0c\u53ea\u51fa\u73b0\u74f6\u5b50\u201d\u7684\u5b9e\u64cd\u548c\u5efa\u8bae\n\n### 1. \u62cd\u6444\u9636\u6bb5\n\n- **\u7eaf\u8272\u6216\u5355\u8272\u80cc\u666f**\uff1a \u7528\u6d45\u8272\u3001\u7eaf\u8272\u5e03\u6599\u3001\u7eb8\u5f20\u6216\u80cc\u666f\u677f\u62cd\u6444\u74f6\u5b50\uff0c\u51cf\u5c11\u80cc\u666f\u82b1\u7eb9\u548c\u6742\u4e71\u7269\u3002\n- **\u7edf\u4e00\u5149\u7ebf\u6761\u4ef6**\uff1a\u907f\u514d\u5f3a\u5149\u9634\u5f71\u548c\u53cd\u5c04\uff0c\u62cd\u6444\u73af\u5883\u5c3d\u91cf\u5747\u5300\u4eae\u5ea6\u3002\n- **\u74f6\u5b50\u4f4d\u7f6e\u56fa\u5b9a**\uff1a\u62cd\u6444\u65f6\u5c3d\u91cf\u4fdd\u8bc1\u74f6\u5b50\u5728\u753b\u9762\u4e2d\u592e\uff0c\u5927\u5c0f\u5408\u9002\uff0c\u4e0d\u51fa\u73b0\u8fb9\u7f18\u622a\u65ad\u3002\n- **\u907f\u514d\u6742\u7269\u5165\u955c**\uff1a\u786e\u4fdd\u73b0\u573a\u65e0\u5176\u4ed6\u7269\u4f53\u5f71\u54cd\u753b\u9762\u3002\n\n---\n\n### 2. \u540e\u671f\u5904\u7406\u9636\u6bb5\uff08\u53ef\u9009\uff09\n\n- **\u88c1\u526aROI**\uff1a\u5982\u679c\u62cd\u6444\u65f6\u80cc\u666f\u4ecd\u7a0d\u590d\u6742\uff0c\u53ef\u4ee5\u7528\u7b80\u5355\u5de5\u5177\u88c1\u526a\u53ea\u4fdd\u7559\u74f6\u5b50\u90e8\u5206\u3002Demo\u9636\u6bb5\u53ef\u7528\u624b\u52a8\u6216\u7b80\u5355\u56fe\u5f62\u88c1\u526a\u5b9e\u73b0\u3002\n\n- **\u57fa\u4e8e\u989c\u8272\u9608\u503c\u7b80\u6613\u5206\u5272**\uff1a \n \u4f8b\u5982\u7eaf\u767d\u80cc\u666f\u53ef\u7528opencv\u505a\u7070\u5ea6\u6216HSV\u9608\u503c\u8fc7\u6ee4\uff0c\u62a0\u51fa\u74f6\u5b50\u8f6e\u5ed3\u3002\u5177\u4f53\u65b9\u6848\u4f9d\u636e\u62cd\u6444\u73af\u5883\u786e\u5b9a\u3002\n\n- **\u6a21\u7cca\u6216\u6de1\u5316\u80cc\u666f**\uff1a\u4e0d\u5f71\u54cd\u74f6\u5b50\u7ec6\u8282\uff0c\u53bb\u9664\u9ad8\u9891\u6742\u4e71\u80cc\u666f\u3002\n\n---\n\n### 3. \u9884\u5904\u7406\u811a\u672c\u4e2d\u4e5f\u53ef\u4ee5\u52a0\u5165\u7b80\u5355\u88c1\u526a\uff08Demo\u53ef\u9009\uff09\n\n\u5047\u8bbe\u4f60\u7684\u74f6\u5b50\u6bd4\u8f83\u5c45\u4e2d\uff0c\u53ef\u4ee5\u622a\u53d6\u4e2d\u95f4\u56fa\u5b9a\u5927\u5c0f\u533a\u57df\uff0c\u6bd4\u5982256\u00d7256\uff0c\u907f\u514d\u80cc\u666f\u8fb9\u89d2\u5e72\u6270\u3002\n\n```python\ndef crop_center(img, crop_size=(256, 256)):\n h, w = img.shape[:2]\n crop_w, crop_h = crop_size\n x_start = max(0, w//2 - crop_w//2)\n y_start = max(0, h//2 - crop_h//2)\n return img[y_start:y_start+crop_h, x_start:x_start+crop_w]\n\n# \u8fd0\u884c\u65f6\u66ff\u6362resize\u51fd\u6570\u4e3a\u88c1\u526a\u51fd\u6570\u6216\u5148\u88c1\u526a\u518dresize\u3002\n```\n\n---\n\n### 4. \u51e0\u70b9\u5b9e\u7528\u5efa\u8bae\n\n- **\u52a1\u5fc5\u4fdd\u6301\u8bad\u7ec3\u56fe\u50cf\u80cc\u666f\u5c3d\u91cf\u4e00\u81f4**\uff0c\u907f\u514d\u6a21\u578b\u628a\u80cc\u666f\u8bef\u5224\u4e3a\u5f02\u5e38\u3002\n- \u9884\u5904\u7406\u65f6\u4e0d\u8981\u5927\u6539\u74f6\u5b50\u672c\u8eab\u7684\u7ec6\u8282\uff0c\u5c24\u5176\u662f\u5370\u5237\u5b57\u4f53\u7eb9\u7406\u3002\n- \u968f\u7740\u9879\u76ee\u63a8\u8fdb\uff0c\u53ef\u5c1d\u8bd5\u7528\u56fe\u50cf\u5206\u5272\u7b97\u6cd5\u81ea\u52a8\u5206\u79bb\u74f6\u5b50\u533a\u57df\uff0c\u4fdd\u969c\u7edf\u4e00\u6027\u3002\n\n---\n\n# \u603b\u7ed3\n\n| \u73af\u8282 | \u5efa\u8bae | \u4f5c\u7528 |\n|----------|----------------------------|------------------------|\n| \u62cd\u6444\u73af\u5883 | \u7eaf\u8272\u3001\u5355\u8272\u80cc\u666f\uff0c\u5149\u7ebf\u5747\u5300\uff0c\u74f6\u5b50\u5c45\u4e2d | \u964d\u4f4e\u80cc\u666f\u590d\u6742\u5ea6\uff0c\u51cf\u5c11\u6a21\u578b\u5e72\u6270 |\n| \u540e\u671f\u88c1\u526a | \u624b\u52a8\u6216\u6279\u91cf\u88c1\u526a\u74f6\u5b50\u4e3b\u4f53\u533a\u57df | \u53bb\u9664\u591a\u4f59\u80cc\u666f\uff0c\u89c4\u6574\u8bad\u7ec3\u6570\u636e |\n| \u9884\u5904\u7406\u9636\u6bb5 | \u53ef\u7b80\u5355\u88c1\u526a+resize\uff0c\u4fdd\u6301\u7ec6\u8282\u5b8c\u6574 | \u7edf\u4e00\u5c3a\u5bf8\uff0c\u4fbf\u4e8e\u6a21\u578b\u8bad\u7ec3 |\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4e2a**\u542b\u4e2d\u5fc3\u88c1\u526a+\u5c3a\u5bf8\u7edf\u4e00\u7684\u9884\u5904\u7406\u811a\u672c**\uff0c\u540c\u65f6\u5e2e\u4f60\u51c6\u5907\u6279\u91cf\u88c1\u526a\u3001\u6279\u91cf\u91cd\u547d\u540d\u3001\u6574\u7406\u6570\u636e\u96c6\u7684\u5168\u5957\u6d41\u7a0b\u3002 \n\n\u6216\u8005\u5e2e\u4f60\u8bbe\u8ba1\u7b80\u5355\u7684\u201c\u80cc\u666f\u53bb\u9664\u201d\u51fd\u6570\uff0c\u7ed3\u5408\u989c\u8272\u9608\u503c\u5206\u5272\u8fdb\u884c\u81ea\u52a8\u74f6\u5b50\u62a0\u56fe\u3002\n\n\u968f\u65f6\u544a\u8bc9\u6211\u9700\u8981\uff0c\u6211\u5e2e\u4f60\u5feb\u901f\u843d\u5730\uff01\nUser: \u597d\u90fd\u6765\nAssistant: \u597d\u7684\uff0c\u6211\u6765\u5e2e\u4f60\u4e00\u6b21\u6027\u642d\u5efa\u4e00\u5957\u5b8c\u6574\u7684\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u7684 **Demo\u9884\u5904\u7406\u4e0e\u8bad\u7ec3\u63a8\u7406\u5168\u6d41\u7a0b\u811a\u672c**\u5305\u542b\uff1a\n\n- **\u6279\u91cf\u9884\u5904\u7406\u811a\u672c**\uff08\u5305\u62ec\u4e2d\u5fc3\u88c1\u526a\u3001\u5c3a\u5bf8\u7edf\u4e00\u3001\u91cd\u547d\u540d\uff09\n- **\u6570\u636e\u96c6\u6574\u7406\u811a\u672c**\uff08\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\uff0c\u5206\u7c7b\u91cd\u547d\u540d\uff0c\u5904\u7406json\u6807\u6ce8\uff09\n- **\u6279\u91cf\u6807\u6ce8\u63a9\u7801\u751f\u6210\u811a\u672c**\uff08\u57fa\u4e8e LabelMe json\uff09\n- **\u8bad\u7ec3\u811a\u672c**\uff08\u4f7f\u7528 anomalib \u8bad\u7ec3 PatchCore\uff09\n- **\u63a8\u7406\u811a\u672c**\uff08\u63a8\u65ad\u7f3a\u9677\uff0c\u76f4\u63a5\u6846\u9009\u7f3a\u9677\u533a\u57df\uff0c\u65e0\u70ed\u529b\u56fe\u53ef\u89c6\u5316\uff09\n- **README\u6d41\u7a0b\u8bf4\u660e**\n\n---\n\n# 1. \u9884\u5904\u7406\u811a\u672c\uff1a\u4e2d\u5fc3\u88c1\u526a+\u5c3a\u5bf8\u7edf\u4e00+\u91cd\u547d\u540d\n\n```python\nimport os\nimport cv2\nimport numpy as np\n\ndef crop_center(img, crop_size=(256, 256)):\n h, w = img.shape[:2]\n crop_w, crop_h = crop_size\n x_start = max(0, w // 2 - crop_w // 2)\n y_start = max(0, h // 2 - crop_h // 2)\n cropped = img[y_start:y_start + crop_h, x_start:x_start + crop_w]\n return cropped\n\ndef resize_with_padding(img, size=(256, 256)):\n h, w = img.shape[:2]\n target_w, target_h = size\n scale = min(target_w / w, target_h / h)\n new_w, new_h = int(w * scale), int(h * scale)\n resized = cv2.resize(img, (new_w, new_h))\n canvas = np.zeros((target_h, target_w, 3), dtype=np.uint8)\n x_offset = (target_w - new_w) // 2\n y_offset = (target_h - new_h) // 2\n canvas[y_offset:y_offset + new_h, x_offset:x_offset + new_w] = resized\n return canvas\n\ndef batch_preprocess(input_dir, output_dir, crop_size=(256, 256), final_size=(256, 256)):\n os.makedirs(output_dir, exist_ok=True)\n exts = ('.jpg', '.jpeg', '.png', '.bmp')\n files = sorted([f for f in os.listdir(input_dir) if f.lower().endswith(exts)])\n for idx, file in enumerate(files, 1):\n path_in = os.path.join(input_dir, file)\n img = cv2.imread(path_in)\n if img is None:\n print(f\"\u8df3\u8fc7\u65e0\u6cd5\u8bfb\u53d6 {file}\")\n continue\n # \u4e2d\u5fc3\u88c1\u526a\n img_cropped = crop_center(img, crop_size)\n # \u5c3a\u5bf8\u7edf\u4e00\u586b\u5145\n img_resized = resize_with_padding(img_cropped, final_size)\n # \u4fdd\u5b58\u91cd\u547d\u540d\n out_name = f\"sample_{idx:04d}.png\"\n path_out = os.path.join(output_dir, out_name)\n cv2.imwrite(path_out, img_resized)\n print(f\"{file} -> {out_name}\")\n print(f\"\u5b8c\u6210 {len(files)} \u5f20\u56fe\u7684\u9884\u5904\u7406\")\n\nif __name__ == '__main__':\n batch_preprocess('./raw_images', './processed_images')\n```\n\n---\n\n# 2. \u6570\u636e\u96c6\u7ba1\u7406\u811a\u672c\uff1a\u5206\u7c7b\u5212\u5206+\u91cd\u547d\u540d+\u540c\u6b65\u590d\u5236json\u6807\u6ce8\n\n```python\nimport os\nimport shutil\nimport random\nimport json\n\ndef standard_name(idx):\n return f\"sample_{idx:04d}\"\n\ndef filter_images(files):\n return [f for f in files if f.lower().endswith(('.png', '.jpg', '.jpeg'))]\n\ndef has_valid_annotation(json_path):\n if not os.path.exists(json_path):\n return False\n try:\n with open(json_path, \"r\", encoding=\"utf-8\") as f:\n data = json.load(f)\n return bool(data.get(\"shapes\"))\n except Exception:\n return False\n\ndef manage_dataset(normal_dir, defect_dir, output_dir, val_ratio=0.2, seed=42):\n os.makedirs(output_dir, exist_ok=True)\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n norm_imgs = filter_images(os.listdir(normal_dir))\n defect_imgs = filter_images(os.listdir(defect_dir))\n\n random.seed(seed)\n random.shuffle(norm_imgs)\n random.shuffle(defect_imgs)\n\n def split_list(lst):\n n = len(lst)\n n_val = max(1, int(n * val_ratio))\n return lst[:-n_val], lst[-n_val:]\n\n norm_train, norm_val = split_list(norm_imgs)\n defect_train, defect_val = split_list(defect_imgs)\n\n idx = 0\n\n def copy_files(files, src_dir, split, cls, copy_json):\n nonlocal idx\n for f in files:\n idx += 1\n ext = os.path.splitext(f)[1].lower()\n new_name = standard_name(idx)\n src_img = os.path.join(src_dir, f)\n dst_img = os.path.join(output_dir, split, cls, new_name + ext)\n shutil.copy2(src_img, dst_img)\n\n if copy_json:\n json_name = os.path.splitext(f)[0] + '.json'\n src_json = os.path.join(src_dir, json_name)\n if has_valid_annotation(src_json):\n dst_json = os.path.join(output_dir, split, cls, new_name + '.json')\n shutil.copy2(src_json, dst_json)\n print(f\"\u590d\u5236 {src_img} -> {dst_img}\")\n\n print(\"\u5f00\u59cb\u590d\u5236\u6b63\u5e38\u56fe...\")\n copy_files(norm_train, normal_dir, 'train', 'good', False)\n copy_files(norm_val, normal_dir, 'valid', 'good', False)\n\n print(\"\u5f00\u59cb\u590d\u5236\u7f3a\u9677\u56fe\u53ca\u6807\u6ce8...\")\n copy_files(defect_train, defect_dir, 'train', 'defect', True)\n copy_files(defect_val, defect_dir, 'valid', 'defect', True)\n\n print(f\"\u6570\u636e\u6574\u7406\u5b8c\u6210\uff0c\u5171\u5904\u7406 {idx} \u5f20\u56fe\u7247\u3002\")\n\nif __name__ == '__main__':\n manage_dataset(\n normal_dir='./processed_normal',\n defect_dir='./processed_defect',\n output_dir='./data',\n val_ratio=0.2\n )\n```\n\n---\n\n# 3. \u6279\u91cf\u751f\u6210\u63a9\u7801\u811a\u672c\n\n```python\nimport os\nimport subprocess\n\ndef generate_masks(label_dir, output_root):\n os.makedirs(output_root, exist_ok=True)\n for file in os.listdir(label_dir):\n if not file.endswith('.json'):\n continue\n json_path = os.path.join(label_dir, file)\n base = os.path.splitext(file)[0]\n output_dir = os.path.join(output_root, base)\n os.makedirs(output_dir, exist_ok=True)\n cmd = f\"labelme_json_to_dataset {json_path} -o {output_dir}\"\n subprocess.run(cmd, shell=True)\n print(f\"\u751f\u6210\u63a9\u7801: {output_dir}/label.png\")\n\nif __name__ == '__main__':\n generate_masks('./data/valid/defect', './data/masks')\n```\n\n---\n\n# 4. \u8bad\u7ec3\u811a\u672c `train.py`\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train(config_path='config.yaml'):\n config = OmegaConf.load(config_path)\n train_loader = get_dataloader(config.dataset, 'train', config.training.batch_size)\n model = get_model(config.model)\n trainer = get_trainer(config.trainer)\n trainer.fit(model=model, train_dataloader=train_loader)\n trainer.save_checkpoint('patchcore_best.ckpt')\n print(\"\u8bad\u7ec3\u5b8c\u6210\uff0c\u6a21\u578b\u4fdd\u5b58\u4e3a patchcore_best.ckpt\")\n\nif __name__ == '__main__':\n train()\n```\n\n---\n\n# 5. \u63a8\u7406\u811a\u672c\uff08\u76f4\u63a5\u6846\u7f3a\u9677\uff09\n\n```python\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport torch\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\n\ndef draw_defect_boxes(image_path, anomaly_map, threshold=0.4, min_area=100):\n img = cv2.imread(image_path)\n norm_map = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_uint8 = (norm_map * 255).astype(np.uint8)\n\n _, binary_mask = cv2.threshold(anomaly_uint8, int(threshold * 255), 255, cv2.THRESH_BINARY)\n kernel = np.ones((3,3), np.uint8)\n binary_mask = cv2.morphologyEx(binary_mask, cv2.MORPH_OPEN, kernel, iterations=1)\n\n contours, _ = cv2.findContours(binary_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n\n for cnt in contours:\n if cv2.contourArea(cnt) < min_area:\n continue\n x, y, w, h = cv2.boundingRect(cnt)\n cv2.rectangle(img, (x,y), (x+w,y+h), (0,0,255), 2)\n\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.axis('off')\n plt.title(\"\u7f3a\u9677\u533a\u57df\u6846\u51fa\")\n plt.show()\n\ndef infer(config_path, checkpoint_path, image_path):\n config = get_configurable_parameters(config_path)\n model = get_model(config.model)\n checkpoint = torch.load(checkpoint_path, map_location='cpu')\n model.load_state_dict(checkpoint['state_dict'])\n model.eval()\n\n inferencer = Inferencer(config, model)\n results = inferencer.infer(image_path)\n \n draw_defect_boxes(image_path, results['anomaly_map'])\n\nif __name__ == \"__main__\":\n infer('config.yaml', 'patchcore_best.ckpt', './data/valid/defect/sample_0001.png')\n```\n\n---\n\n# 6. \u4f60\u53ef\u4ee5\u8fd9\u6837\u4f7f\u7528\n\n```bash\n# \u7b2c\u4e00\u6b65\uff0c\u5148\u51c6\u5907\u539f\u59cb\u56fe\u50cf\uff0c\u5728 raw_images\u4e2d\u653e\u56fe\u7247\uff08\u6b63\u5e38\u548c\u7f3a\u9677\u5206\u522b\u653e\u4e0d\u540c\u76ee\u5f55\uff09\n\n# \u9884\u5904\u7406\npython preprocess.py # \u751f\u6210 processed_images\u6587\u4ef6\u5939\n\n# \u5904\u7406\u6837\u672c\u533a\u5206\uff0c\u5c06\u6b63\u5e38\u548c\u7f3a\u9677\u56fe\u7247\u653e\u5230 processed_normal \u548c processed_defect\n\n# \u8fd0\u884c\u6570\u636e\u96c6\u7ba1\u7406\u811a\u672c\npython manage_dataset.py\n\n# \uff08\u6807\u6ce8\u4e86\u7f3a\u9677json\uff09\u6279\u91cf\u751f\u6210\u63a9\u7801\npython generate_masks.py\n\n# \u914d\u7f6e\u5e76\u8fd0\u884c\u8bad\u7ec3\npython train.py\n\n# \u63a8\u7406\u5e76\u67e5\u770b\u7f3a\u9677\u6846\npython infer.py\n```\n\n---\n\n# 7. \u4e00\u4e9bTips\n\n- \u9884\u5904\u7406\u9636\u6bb5\u4fdd\u8bc1\u74f6\u5b50\u5c45\u4e2d\u88c1\u526a\uff0c\u4e14\u80cc\u666f\u5e72\u51c0\uff08\u5c3d\u91cf\u7eaf\u8272\uff09\n- \u8bad\u7ec3\u53ea\u7528\u6b63\u5e38\u56fe\uff08train/good\uff09\n- \u9a8c\u8bc1\u96c6\u5305\u542b\u6b63\u5e38+\u7f3a\u9677\uff08valid/good \u548c valid/defect\uff09\n- \u6807\u6ce8\u7684json\u548c\u751f\u6210\u7684\u63a9\u7801\u7528\u4e8e\u9a8c\u8bc1\u6a21\u578b\u5b9a\u4f4d\u51c6\u786e\u6027\n- \u63a8\u7406\u76f4\u63a5\u8f93\u51fa\u7f3a\u9677\u6846\uff0c\u65b9\u4fbf\u5728\u6d41\u6c34\u7ebf\u5b9e\u65f6\u68c0\u6d4b\u65f6\u4f7f\u7528\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u6253\u5305\u6574\u4e2a\u6f14\u793ademo\u5de5\u7a0b\u76ee\u5f55\uff0c\u6216\u8005\u6559\u4f60\u6bcf\u4e00\u6b65\u5177\u4f53\u8c03\u8bd5\u548c\u6539\u8fdb\uff0c\u4e5f\u80fd\u5e2e\u4f60\u5199\u6570\u636e\u589e\u5f3a\u3001\u6a21\u578b\u8bc4\u4f30\u6307\u6807\u8ba1\u7b97\u811a\u672c\u3002\n\n\u544a\u8bc9\u6211\u4f60\u9700\u8981\u6211\u5e2e\u4f60\u5148\u505a\u54ea\u4e00\u6b65\uff0c\u6211\u4eec\u9a6c\u4e0a\u5f00\u59cb\nUser: \u4ece\u5934\u5230\u5c3e\u6559\u6211\u5427\uff0c\u4e00\u6b65\u4e00\u6b65\u6765\nAssistant: \u597d\u7684\uff01\u4e0b\u9762\u6211\u5e26\u4f60\u4ece\u5934\u5230\u5c3e\uff0c\u4e00\u6b65\u4e00\u6b65\u642d\u5efa\u4e00\u4e2a\u57fa\u4e8e **anomalib PatchCore** \u7684\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf Demo \u9879\u76ee\u3002\u6211\u4eec\u4f1a\u4e00\u8d77\u5b8c\u6210\uff1a\n\n1. \u73af\u5883\u51c6\u5907\n2. \u539f\u59cb\u6570\u636e\u91c7\u96c6\u548c\u9884\u5904\u7406\uff08\u7edf\u4e00\u5c3a\u5bf8\u3001\u88c1\u526a\u3001\u91cd\u547d\u540d\uff09\n3. \u6570\u636e\u96c6\u7ba1\u7406\uff08\u5206\u7c7b\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1\u96c6\uff0c\u7ba1\u7406\u5bf9\u5e94\u6807\u6ce8\uff09\n4. \u7f3a\u9677\u6807\u6ce8\u548c\u63a9\u7801\u751f\u6210\uff08\u7528LabelMe\uff09\n5. \u6a21\u578b\u8bad\u7ec3\uff08PatchCore\uff09\n6. \u6a21\u578b\u63a8\u7406\u53ca\u7f3a\u9677\u533a\u57df\u6846\u9009\n7. \u603b\u7ed3\u4e0e\u540e\u7eed\u4f18\u5316\u5efa\u8bae\n\n---\n\n## \u7b2c1\u6b65\uff1a\u73af\u5883\u51c6\u5907\n\n### 1.1. \u5b89\u88c5Python\uff08\u63a8\u83503.8-3.9\uff09\n\n\u786e\u8ba4\u7535\u8111\u6709Python 3.8\u4ee5\u4e0a\uff1a\n\n```bash\npython3 --version\n```\n\n### 1.2. \u521b\u5efa\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883\n\n\uff08\u907f\u514d\u5e93\u51b2\u7a81\uff0c\u5efa\u8bae\u5fc5\u505a\uff09\n\n```bash\npython3 -m venv anomalib-env\nsource anomalib-env/bin/activate # macOS/Linux\n# anomalib-env\\Scripts\\activate.bat # Windows\n```\n\n### 1.3. \u5b89\u88c5\u4f9d\u8d56\u5e93\n\n\u5148\u5b89\u88c5PyTorch\uff0c\u8bf7\u53c2\u8003[\u5b98\u7f51](https://pytorch.org/get-started/locally/)\u6839\u636e\u4f60GPU\u60c5\u51b5\u66ff\u6362\u547d\u4ee4\u3002\u8fd9\u91cc\u4e3e\u65e0 GPU \u793a\u4f8b\uff1a\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu\n```\n\n\u5b89\u88c5anomalib\u53ca\u8f85\u52a9\u5e93\uff1a\n\n```bash\npip install anomalib omegaconf hydra-core matplotlib opencv-python labelme\n```\n\n\u786e\u8ba4\u5b89\u88c5\u5b8c\u6210\uff1a\n\n```bash\npip list | grep -E \"torch|anomalib|opencv|labelme\"\n```\n\n---\n\n## \u7b2c2\u6b65\uff1a\u56fe\u7247\u91c7\u96c6\u4e0e\u9884\u5904\u7406\n\n\u8fd9\u91cc\u5047\u8bbe\u4f60\u5df2\u7ecf\u6709\u4e86\u4e24\u7c7b\u56fe\u7247\uff1a\n\n- **\u6b63\u5e38\u6837\u672c**\uff08\u65e0\u7f3a\u9677\u74f6\u5b50\uff0c\u80cc\u666f\u7b80\u6d01\uff09\n- **\u7f3a\u9677\u6837\u672c**\uff08\u5e26\u7f3a\u9677\uff09\n\n### 2.1. \u6279\u91cf\u9884\u5904\u7406\u811a\u672c\uff08\u4e2d\u5fc3\u88c1\u526a+\u5c3a\u5bf8\u7edf\u4e00+\u91cd\u547d\u540d\uff09\n\n\u65b0\u5efa\u6587\u4ef6`preprocess.py`\uff0c\u590d\u5236\u4ee5\u4e0b\u4ee3\u7801\uff1a\n\n```python\nimport os\nimport cv2\nimport numpy as np\n\ndef crop_center(img, crop_size=(256, 256)):\n h, w = img.shape[:2]\n crop_w, crop_h = crop_size\n x_start = max(0, w//2 - crop_w//2)\n y_start = max(0, h//2 - crop_h//2)\n return img[y_start:y_start+crop_h, x_start:x_start+crop_w]\n\ndef resize_with_padding(img, size=(256,256)):\n h, w = img.shape[:2]\n scale = min(size[0]/w, size[1]/h)\n new_w, new_h = int(w*scale), int(h*scale)\n resized = cv2.resize(img, (new_w, new_h))\n canvas = np.zeros((size[1], size[0], 3), dtype=np.uint8)\n x_offset = (size[0]-new_w)//2\n y_offset = (size[1]-new_h)//2\n canvas[y_offset:y_offset+new_h, x_offset:x_offset+new_w] = resized\n return canvas\n\ndef batch_preprocess(input_dir, output_dir, crop_size=(256,256), final_size=(256,256)):\n os.makedirs(output_dir, exist_ok=True)\n exts = ('.jpg', '.jpeg', '.png')\n files = sorted([f for f in os.listdir(input_dir) if f.lower().endswith(exts)])\n for idx, f in enumerate(files, 1):\n img_path = os.path.join(input_dir, f)\n img = cv2.imread(img_path)\n if img is None:\n print(f\"\u8df3\u8fc7\u65e0\u6cd5\u8bfb\u53d6 {f}\")\n continue\n cropped = crop_center(img, crop_size)\n processed = resize_with_padding(cropped, final_size)\n out_name = f\"sample_{idx:04d}.png\"\n cv2.imwrite(os.path.join(output_dir, out_name), processed)\n print(f\"{f} -> {out_name}\")\n\nif __name__ == \"__main__\":\n batch_preprocess(\"./raw_images\", \"./processed_images\")\n```\n\n\u6ce8\u610f:\n\n- \u628a\u4f60**\u539f\u59cb\u56fe\u7247\u653e\u5165`raw_images`\u76ee\u5f55**\uff08\u81ea\u5df1\u521b\u5efa\uff09\n- \u8fd0\u884c\u5b83\u4f1a\u5c06\u56fe\u7247\u4e2d\u5fc3\u88c1\u526a\uff0c\u8c03\u6574\u81f3256x256\uff0c\u4fdd\u5b58\u5230`processed_images`\u76ee\u5f55\uff0c\u5e76\u7edf\u4e00\u547d\u540d\n\n\u8fd0\u884c\u547d\u4ee4:\n\n```bash\npython preprocess.py\n```\n\n---\n\n## \u7b2c3\u6b65\uff1a\u6570\u636e\u96c6\u7ba1\u7406\uff08\u5206\u7c7b\u3001\u5212\u5206\u3001\u91cd\u547d\u540d\uff09\n\n\u5047\u8bbe\u4f60\u6709\u4e24\u4efd\u7ecf\u8fc7\u9884\u5904\u7406\u7684\u76ee\u5f55\uff1a\n\n- \u7ecf\u8fc7\u9884\u5904\u7406\u7684**\u6b63\u5e38\u6837\u672c**\u653e`processed_normal`\u76ee\u5f55\n- \u7ecf\u8fc7\u9884\u5904\u7406\u7684**\u7f3a\u9677\u6837\u672c**\u653e`processed_defect`\u76ee\u5f55\n\n\u65b0\u5efa\u811a\u672c`manage_dataset.py`\uff0c\u590d\u5236\uff1a\n\n```python\nimport os\nimport shutil\nimport random\nimport json\n\ndef standard_name(idx):\n return f\"sample_{idx:04d}\"\n\ndef filter_images(files):\n return [f for f in files if f.lower().endswith(('.png', '.jpg', '.jpeg'))]\n\ndef has_annotation(json_path):\n if not os.path.exists(json_path):\n return False\n try:\n with open(json_path, 'r', encoding='utf-8') as f:\n data = json.load(f)\n return bool(data.get('shapes'))\n except:\n return False\n\ndef manage_dataset(normal_dir, defect_dir, output_dir, val_ratio=0.2, seed=42):\n os.makedirs(output_dir, exist_ok=True)\n for split in ['train', 'valid']:\n for cls in ['good', 'defect']:\n os.makedirs(os.path.join(output_dir, split, cls), exist_ok=True)\n\n normal_imgs = filter_images(os.listdir(normal_dir))\n defect_imgs = filter_images(os.listdir(defect_dir))\n random.seed(seed)\n random.shuffle(normal_imgs)\n random.shuffle(defect_imgs)\n\n def split_list(lst):\n n = len(lst)\n n_val = max(1, int(n * val_ratio))\n return lst[:-n_val], lst[-n_val:]\n\n normal_train, normal_val = split_list(normal_imgs)\n defect_train, defect_val = split_list(defect_imgs)\n\n idx = 0\n\n def copy_group(img_list, src_dir, split, cls, copy_json):\n nonlocal idx\n for img_name in img_list:\n idx += 1\n ext = os.path.splitext(img_name)[1].lower()\n new_name = standard_name(idx)\n src_img_path = os.path.join(src_dir, img_name)\n dst_img_path = os.path.join(output_dir, split, cls, new_name + ext)\n shutil.copy2(src_img_path, dst_img_path)\n if copy_json:\n json_name = os.path.splitext(img_name)[0] + '.json'\n src_json_path = os.path.join(src_dir, json_name)\n if has_annotation(src_json_path):\n dst_json_path = os.path.join(output_dir, split, cls, new_name + '.json')\n shutil.copy2(src_json_path, dst_json_path)\n print(f\"\u590d\u5236 {src_img_path} -> {dst_img_path}\")\n\n print(\"\u590d\u5236\u6b63\u5e38\u56fe\u7247...\")\n copy_group(normal_train, normal_dir, 'train', 'good', False)\n copy_group(normal_val, normal_dir, 'valid', 'good', False)\n print(\"\u590d\u5236\u7f3a\u9677\u56fe\u7247\u53ca\u6807\u6ce8...\")\n copy_group(defect_train, defect_dir, 'train', 'defect', True)\n copy_group(defect_val, defect_dir, 'valid', 'defect', True)\n print(f\"\u6570\u636e\u96c6\u6574\u7406\u5b8c\u6210\uff0c\u5171\u5904\u7406 {idx} \u5f20\u56fe\u7247\")\n\nif __name__ == '__main__':\n manage_dataset(\n './processed_normal',\n './processed_defect',\n './data',\n val_ratio=0.2\n )\n```\n\n\u8fd0\u884c\u793a\u8303\uff1a\n\n```bash\npython manage_dataset.py\n```\n\n\u6b64\u811a\u672c\uff0c\u4f1a\u540c\u65f6\u6574\u7406\u8bad\u7ec3\u548c\u9a8c\u8bc1\u96c6\u7684\u6b63\u5e38\u548c\u7f3a\u9677\u6837\u672c\uff0c\u8fde\u540c\u5bf9\u5e94LabelMe JSON\u6807\u6ce8\u6587\u4ef6\u6309\u547d\u540d\u590d\u5236\u3002\n\n---\n\n## \u7b2c4\u6b65\uff1a\u7f3a\u9677\u6807\u6ce8\u548c\u63a9\u7801\u6587\u4ef6\u751f\u6210\n\n### \u7528LabelMe\u6807\u6ce8\u7f3a\u9677\u533a\u57df\n\n- \u8fd0\u884c\u547d\u4ee4\u542f\u52a8LabelMe\uff1a\n \n```bash\nlabelme\n```\n\n- \u6253\u5f00\u7f3a\u9677\u56fe\u7247\uff0c\u4f7f\u7528\u591a\u8fb9\u5f62\u5de5\u5177\u7ed8\u5236\u7f3a\u9677\u533a\u57df\uff0c\u586b\u5199\u6807\u7b7e\u540d\uff08\u5982`defect`\uff09\uff0c\u4fdd\u5b58\u3002\n\n### \u6279\u91cf\u751f\u6210\u63a9\u7801\n\n\u65b0\u5efa\u811a\u672c`generate_masks.py`\uff1a\n\n```python\nimport os\nimport subprocess\n\ndef batch_generate_masks(label_dir, mask_root):\n os.makedirs(mask_root, exist_ok=True)\n for f in os.listdir(label_dir):\n if f.endswith('.json'):\n json_path = os.path.join(label_dir, f)\n name = os.path.splitext(f)[0]\n out_dir = os.path.join(mask_root, name)\n os.makedirs(out_dir, exist_ok=True)\n cmd = f\"labelme_json_to_dataset {json_path} -o {out_dir}\"\n subprocess.run(cmd, shell=True)\n print(f\"\u751f\u6210\u63a9\u7801: {out_dir}/label.png\")\n\nif __name__ == \"__main__\":\n batch_generate_masks(\"./data/valid/defect\", \"./data/masks\")\n```\n\n\u8fd0\u884c\uff1a\n\n```bash\npython generate_masks.py\n```\n\n---\n\n## \u7b2c5\u6b65\uff1a\u6a21\u578b\u8bad\u7ec3\n\n\u8bf7\u786e\u4fdd\u6587\u4ef6\u5939\u7ed3\u6784\uff1a\n\n```\ndata/\n\u251c\u2500\u2500 train/\n\u2502 \u2514\u2500\u2500 good/\n\u251c\u2500\u2500 valid/\n\u2502 \u251c\u2500\u2500 good/\n\u2502 \u2514\u2500\u2500 defect/\n```\n\n\u521b\u5efa`config.yaml`\u793a\u4f8b\uff08\u9700\u653e\u5728\u9879\u76ee\u6839\u76ee\u5f55\uff09\uff1a\n\n```yaml\nmodel:\n name: patchcore\n patchcore:\n backbone: resnet18\n input_size: 256\n embedding_method: random_projection\n\ntraining:\n batch_size: 8\n max_epochs: 20\n precision: 16\n seed: 42\n save_checkpoint: True\n\ndataset:\n name: custom\n path: ./data\n input_size: 256\n\ntrainer:\n accelerator: gpu # \u6ca1GPU\u6539\u4e3acpu\n devices: 1\n max_epochs: 20\n\nlogger:\n wandb: {}\n```\n\n\u65b0\u5efa`train.py`\uff1a\n\n```python\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.data import get_dataloader\nfrom anomalib.models import get_model\nfrom anomalib.trainers import get_trainer\nfrom omegaconf import OmegaConf\n\ndef train(config_path=\"config.yaml\"):\n config = OmegaConf.load(config_path)\n train_loader = get_dataloader(config.dataset, \"train\", config.training.batch_size)\n model = get_model(config.model)\n trainer = get_trainer(config.trainer)\n trainer.fit(model=model, train_dataloader=train_loader)\n trainer.save_checkpoint(\"patchcore_best.ckpt\")\n print(\"\u8bad\u7ec3\u5b8c\u6210\uff0c\u6a21\u578b\u5df2\u4fdd\u5b58\uff01\")\n\nif __name__ == '__main__':\n train()\n```\n\n\u8fd0\u884c\u8bad\u7ec3:\n\n```bash\npython train.py\n```\n\n---\n\n## \u7b2c6\u6b65\uff1a\u63a8\u7406 & \u7f3a\u9677\u6846\u9009\n\n\u65b0\u5efa`infer.py`\uff1a\n\n```python\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport torch\nfrom anomalib.config import get_configurable_parameters\nfrom anomalib.models import get_model\nfrom anomalib.deploy import Inferencer\n\ndef draw_boxes(image_path, anomaly_map, threshold=0.4, min_area=100):\n img = cv2.imread(image_path)\n norm_map = (anomaly_map - anomaly_map.min()) / (anomaly_map.max() - anomaly_map.min())\n anomaly_uint8 = (norm_map*255).astype(np.uint8)\n _, binary = cv2.threshold(anomaly_uint8, int(threshold*255), 255, cv2.THRESH_BINARY)\n kernel = np.ones((3,3), np.uint8)\n binary = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=1)\n contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n for c in contours:\n if cv2.contourArea(c) < min_area:\n continue\n x,y,w,h = cv2.boundingRect(c)\n cv2.rectangle(img, (x,y), (x+w, y+h), (0,0,255), 2)\n plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n plt.axis('off')\n plt.title(\"\u7f3a\u9677\u533a\u57df\u6846\u9009\")\n plt.show()\n\ndef infer(config_file, checkpoint_file, image_file):\n config = get_configurable_parameters(config_file)\n model = get_model(config.model)\n checkpoint = torch.load(checkpoint_file, map_location='cpu')\n model.load_state_dict(checkpoint['state_dict'])\n model.eval()\n\n inferencer = Inferencer(config, model)\n results = inferencer.infer(image_file)\n\n draw_boxes(image_file, results['anomaly_map'])\n\nif __name__ == \"__main__\":\n infer(\"config.yaml\", \"patchcore_best.ckpt\", \"./data/valid/defect/sample_0001.png\")\n```\n\n\u8fd0\u884c\u63a8\u7406\uff1a\n\n```bash\npython infer.py\n```\n\n---\n\n## \u7b2c7\u6b65\uff1a\u603b\u7ed3\n\n* \u5b8c\u6574\u9879\u76ee\u6d41\u7a0b\uff1a\n\n```plaintext\nraw_images/\n\u251c\u2500\u2500 normal_images/ # \u539f\u59cb\u65e0\u7f3a\u9677\u56fe\n\u2514\u2500\u2500 defect_images/ # \u539f\u59cb\u7f3a\u9677\u56fe\u548c\u6807\u6ce8json\n\n-> \u9884\u5904\u7406.py ---> processed_normal & processed_defect (\u5c3a\u5bf8\u7edf\u4e00\u3001\u88c1\u526a\u3001\u547d\u540d)\n\n-> manage_dataset.py ---> data/ \u8bad\u7ec3\u9a8c\u8bc1\u96c6\u5212\u5206\u4e0e\u6574\u7406\n\nlabelme \u6807\u6ce8\u7f3a\u9677 ---> json\u6587\u4ef6\n\n-> generate_masks.py ---> data/masks/ \u63a9\u7801\u751f\u6210\n\n-> train.py --> PatchCore\u8bad\u7ec3\u6b63\u5e38\u6837\u672c\n\n-> infer.py --> \u7f3a\u9677\u68c0\u6d4b\u4e0e\u7f3a\u9677\u6846\u6807\u6ce8\u5c55\u793a\n```\n\n---\n\n\u540e\u7eed\u6211\u53ef\u4ee5\u966a\u4f60\u4e00\u8d77\u8c03\u8bd5\u6bcf\u4e00\u6b65\u9047\u5230\u7684\u95ee\u9898\uff0c\u5e2e\u4f60\u5b8c\u5584\u4ee3\u7801\u548c\u8bad\u7ec3\u65b9\u6848\uff0c\u751a\u81f3\u5199\u5b8c\u6574\u7684\u9879\u76eedemo\u5305\u3002 \n\u4f60\u5148\u8bd5\u8bd5\u9884\u5904\u7406\u548c\u6570\u636e\u6574\u7406\uff0c\u6709\u95ee\u9898\u76f4\u63a5\u95ee\u6211\uff0c\u6211\u624b\u628a\u624b\u8f85\u5bfc\uff01\nUser: \u8fd9\u4e00\u90e8\u5206\u4ee3\u7801\u90fd\u6709\u4ec0\u4e48\u4f5c\u7528\uff0c\u7ed9\u6211\u7ec6\u7ec6\u8bb2\u8bb2\nAssistant: \u597d\u7684\uff01\u6211\u5e2e\u4f60\u9010\u6b65\u7ec6\u81f4\u8bb2\u89e3\u521a\u624d\u7ed9\u4f60\u7684\u90a3\u51e0\u4e2a\u8f85\u52a9\u811a\u672c\u7684\u4ee3\u7801\u4f5c\u7528\u548c\u6838\u5fc3\u903b\u8f91\uff0c\u65b9\u4fbf\u4f60\u7406\u89e3\u6bcf\u4e00\u6b65\u5728\u505a\u4ec0\u4e48\uff0c\u600e\u4e48\u534f\u540c\u5b8c\u6210\u6d41\u6c34\u7ebf\u5370\u5237\u8d28\u91cf\u68c0\u6d4b\u9879\u76ee\u91cc\u7684\u6570\u636e\u9884\u5904\u7406\u3001\u7ba1\u7406\u3001\u8bad\u7ec3\u548c\u63a8\u7406\u3002\n\n---\n\n# 1. \u9884\u5904\u7406\u811a\u672c\uff08`preprocess.py`\uff09\n\n### \u529f\u80fd\n\n- \u6279\u91cf\u8bfb\u53d6\u6307\u5b9a\u6587\u4ef6\u5939\u91cc\u7684\u56fe\u7247\n- \u5bf9\u6bcf\u5f20\u56fe\u7247\u505a**\u4e2d\u5fc3\u88c1\u526a**\uff0c\u526a\u6389\u56db\u5468\u591a\u4f59\u533a\u57df\uff0c\u805a\u7126\u74f6\u5b50\u4e3b\u4f53\n- \u5bf9\u88c1\u526a\u540e\u7684\u56fe\u7247\u505a**\u5c3a\u5bf8\u7edf\u4e00\u5904\u7406**\uff0c\u7f29\u653e\u540e\u7528\u9ed1\u8272\u586b\u5145\u5230\u56fa\u5b9a\u5927\u5c0f\uff08\u5982256\u00d7256\uff09\n- \u91cd\u547d\u540d\u56fe\u7247\uff0c\u6807\u51c6\u683c\u5f0f\uff08`sample_0001.png`\uff09\u4fdd\u5b58\u5230\u76ee\u6807\u6587\u4ef6\u5939\n\n---\n\n### \u5173\u952e\u51fd\u6570\n\n```python\ndef crop_center(img, crop_size=(256, 256)):\n # \u5728\u56fe\u7247\u4e2d\u5fc3\u5207\u51fa\u4e00\u4e2a\u56fa\u5b9a\u5927\u5c0f\u7684\u77e9\u5f62\u533a\u57df\uff0c\u786e\u4fdd\u7edf\u4e00\u53d6\u74f6\u5b50\u6b63\u4e2d\u5fc3\u90e8\u5206\n # \u8f93\u5165: img\u662f\u56fe\u50cf\uff0ccrop_size\u662f\u88c1\u526a\u5c3a\u5bf8\n```\n\n```python\ndef resize_with_padding(img, size=(256, 256)):\n # \u5148\u6309\u6bd4\u4f8b\u7f29\u653e\u56fe\u7247\uff0c\u907f\u514d\u62c9\u4f38\u53d8\u5f62\n # \u4e4b\u540e\u586b\u5145\u8fb9\u7f18\uff08\u9ed1\u8fb9\uff09\u4f7f\u56fe\u50cf\u5c3a\u5bf8\u56fa\u5b9a\n```\n\n```python\ndef batch_preprocess(input_dir, output_dir, crop_size=(256,256), final_size=(256,256)):\n # \u5bf9\u8f93\u5165\u76ee\u5f55\u7684\u6240\u6709\u56fe\u7247\u6267\u884c\u88c1\u526a+resize\uff0c\u4fdd\u5b58\u5230\u8f93\u51fa\u76ee\u5f55\u5e76\u91cd\u547d\u540d\n```\n\n---\n\n### \u4e3a\u4ec0\u4e48\u8fd9\u6837\u505a\uff1f\n\n- **\u4e2d\u5fc3\u88c1\u526a**\u5e2e\u52a9\u6392\u9664\u56fe\u7247\u8fb9\u7f18\u7684\u80cc\u666f\u5e72\u6270\uff0c\u53ea\u4fdd\u7559\u74f6\u5b50\u4e3b\u4f53\uff0c\u63d0\u9ad8\u540e\u7eed\u6a21\u578b\u8bad\u7ec3\u65f6\u7684\u7279\u5f81\u4e00\u81f4\u6027\u3002 \n- **\u7f29\u653e+\u586b\u5145**\u4fdd\u8bc1\u8f93\u5165\u6a21\u578b\u7684\u56fe\u50cf\u5c3a\u5bf8\u7edf\u4e00\uff0c\u9884\u8bad\u7ec3\u6a21\u578b\u8981\u6c42\u56fa\u5b9a\u5927\u5c0f\u8f93\u5165\u3002 \n- **\u91cd\u547d\u540d**\u65b9\u4fbf\u540e\u7eed\u6570\u636e\u7ba1\u7406\uff0c\u5982\u8bad\u7ec3\u65f6\u6309\u6587\u4ef6\u540d\u52a0\u8f7d\u548c\u5bf9\u5e94\u6807\u6ce8\u3002\n\n---\n\n# 2. \u6570\u636e\u96c6\u7ba1\u7406\u811a\u672c\uff08`manage_dataset.py`\uff09\n\n### \u529f\u80fd\n\n- \u4ece\u4e24\u4e2a\u76ee\u5f55\u5206\u522b\u83b7\u53d6\u9884\u5904\u7406\u540e\u7684\u6b63\u5e38\u548c\u7f3a\u9677\u56fe\u7247\uff08\u542b\u7f3a\u9677\u6807\u6ce8json\uff09\n- \u6839\u636e\u8bbe\u5b9a\u6bd4\u4f8b\uff08\u4e00\u822c20%\uff09\u968f\u673a\u5212\u5206\u8bad\u7ec3\u96c6\u548c\u9a8c\u8bc1\u96c6\n- \u6309\u7167`train/valid`\u548c`good/defect`\u56db\u5c42\u76ee\u5f55\u7ed3\u6784\u590d\u5236\u56fe\u7247\u548c\u5bf9\u5e94\u6807\u6ce8\u6587\u4ef6\n- \u7edf\u4e00\u547d\u540d\u590d\u5236\u540e\u7684\u6587\u4ef6\uff0c\u4fdd\u6301\u56fe\u50cf\u4e0ejson\u6587\u4ef6\u4e00\u4e00\u5bf9\u5e94\uff08`sample_0001.png`\u4e0e`sample_0001.json`\uff09\n\n---\n\n### \u5173\u952e\u70b9\u89e3\u91ca\n\n```python\ndef filter_images(files):\n # \u8fc7\u6ee4\u6709\u6548\u56fe\u7247\u683c\u5f0f\u6587\u4ef6\uff0c\u907f\u514d\u5176\u4ed6\u5e72\u6270\u6587\u4ef6\u5b58\u5728\n```\n\n```python\ndef has_annotation(json_path):\n # \u5224\u65adjson\u6587\u4ef6\u662f\u5426\u5b58\u5728\u6807\u6ce8\uff08\u6709\u6ca1\u6709\u7f3a\u9677\u6807\u6ce8\u533a\u57df\uff09\uff0c\u907f\u514d\u590d\u5236\u7a7ajson\n```\n\n```python\ndef manage_dataset(normal_dir, defect_dir, output_dir, ...):\n # \u5212\u5206\u5e76\u590d\u5236\u6570\u636e\n # \u5148\u6253\u4e71\u5217\u8868\u786e\u4fdd\u6570\u636e\u968f\u673a\u5206\u5e03\n # \u6839\u636e\u6bd4\u4f8b\u5212\u5206\u8bad\u7ec3\u548c\u9a8c\u8bc1\n # \u5206\u7c7b\u522bcopy\u5230\u5bf9\u5e94\u76ee\u5f55\n # \u590d\u5236json\u6587\u4ef6\u5bf9\u5e94\u56fe\u7247\n```\n\n---\n\n### \u4e3a\u4ec0\u4e48\u5206\u8fd9\u6837\u7ba1\u7406\uff1f\n\n- **\u8bad\u7ec3\u53ea\u4f7f\u7528\u6b63\u5e38\u6570\u636e\uff08train/good\uff09**\uff0c\u7b26\u5408\u65e0\u76d1\u7763\u5f02\u5e38\u68c0\u6d4b\u539f\u5219\u3002 \n- **\u9a8c\u8bc1\u96c6\u540c\u65f6\u542b\u6b63\u5e38\uff08valid/good\uff09\u548c\u7f3a\u9677\uff08valid/defect\uff09\u6570\u636e**\uff0c\u9a8c\u8bc1\u6a21\u578b\u771f\u5b9e\u8868\u73b0\u3002 \n- **\u7edf\u4e00\u547d\u540d\u548c\u76ee\u5f55\u7ed3\u6784**\u65b9\u4fbf\u96c6\u6210\u5230\u8bad\u7ec3\u6d41\u7a0b\uff0c\u51cf\u5c11\u6570\u636e\u8bfb\u53d6\u9519\u8bef\u3002 \n- **\u590d\u5236\u6807\u6ce8\u6587\u4ef6**\u5e2e\u52a9\u540e\u7eed\u505a\u6a21\u578b\u5b9a\u4f4d\u8bc4\u4f30\u548c\u7ed3\u679c\u53ef\u89c6\u5316\u3002\n\n---\n\n# 3. \u6279\u91cf\u751f\u6210\u63a9\u7801\u811a\u672c\uff08`generate_masks.py`\uff09\n\n### \u529f\u80fd\n\n- \u8bfb\u53d6\u6240\u6709LabelMe\u7684json\u6807\u6ce8\u6587\u4ef6 \n- \u5229\u7528 `labelme_json_to_dataset` \u547d\u4ee4\u6279\u91cf\u5c06json\u8f6c\u6362\u6210\u5bf9\u5e94\u7684\u63a9\u7801\u56fe\u7247\uff08`label.png`\uff09 \n- \u63a9\u7801\u53ef\u7528\u4e8e\u8bad\u7ec3\u76d1\u7763\u6216\u6a21\u578b\u5b9a\u4f4d\u8bc4\u4f30\n\n---\n\n### \u4e3a\u4ec0\u4e48\u8981\u751f\u6210\u63a9\u7801\uff1f\n\n- LabelMe\u4fdd\u5b58\u7684json\u662f\u591a\u8fb9\u5f62\u7684\u9876\u70b9\u6570\u636e\uff0c\u63a9\u7801\u662f\u50cf\u7d20\u7ea7\u56fe\u50cf\u6807\u6ce8\uff0c\u65b9\u4fbf\u8ba1\u7b97\u6307\u6807\u6bd4\u5982IoU\u3002 \n- \u6279\u91cf\u8f6c\u6362\u907f\u514d\u624b\u52a8\u7e41\u7410\u64cd\u4f5c\uff0c\u4e00\u6b21\u751f\u6210\u6240\u6709\u56fe\u7247\u5bf9\u5e94\u63a9\u7801\u3002\n\n---\n\n# 4. \u8bad\u7ec3\u811a\u672c\uff08`train.py`\uff09\n\n### \u529f\u80fd\n\n- \u8bfb\u53d6\u914d\u7f6e\u6587\u4ef6\uff08yaml\uff09\uff0c\u7528\u4e8e\u5b9a\u4e49\u6a21\u578b\u3001\u6570\u636e\u8def\u5f84\u3001\u8bad\u7ec3\u53c2\u6570\u7b49 \n- \u521b\u5efa\u6570\u636e\u52a0\u8f7d\u5668\uff0c\u52a0\u8f7d\u8bad\u7ec3\u6b63\u5e38\u6837\u672c \n- \u5b9e\u4f8b\u5316PatchCore\u6a21\u578b \n- \u521b\u5efa\u8bad\u7ec3\u5668\u5e76\u5f00\u59cb\u8bad\u7ec3 \n- \u8bad\u7ec3\u5b8c\u6210\u4fdd\u5b58\u6a21\u578b\u68c0\u67e5\u70b9\n\n---\n\n### \u4f5c\u7528\u53ca\u6d41\u7a0b\n\n- **\u914d\u7f6e\u6587\u4ef6\u89e3\u8026\u53c2\u6570\u8bbe\u7f6e**\uff0c\u65b9\u4fbf\u8c03\u6574\u548c\u5b9e\u9a8c \n- **PatchCore\u53ea\u7528\u6b63\u5e38\u6570\u636e\u8bad\u7ec3**\uff0c\u57fa\u4e8e\u6b63\u5e38\u7279\u5f81\u5b66\u4e60\u5f02\u5e38\u8bc6\u522b \n- **\u4fdd\u5b58\u597d\u7684\u6a21\u578b\u6743\u91cd\u4f9b\u63a8\u7406\u4f7f\u7528**\n\n---\n\n# 5. \u63a8\u7406\u811a\u672c\uff08`infer.py`\uff09\n\n### \u529f\u80fd\n\n- \u52a0\u8f7d\u8bad\u7ec3\u597d\u7684PatchCore\u6a21\u578b\u6743\u91cd \n- \u5bf9\u6d4b\u8bd5\u56fe\u7247\u505a\u5f02\u5e38\u68c0\u6d4b\u8f93\u51fa\u5f02\u5e38\u70ed\u529b\u56fe \n- \u901a\u8fc7\u9608\u503c\u5206\u5272\u548c\u8f6e\u5ed3\u68c0\u6d4b\u627e\u5230\u5f02\u5e38\u533a\u57df \n- \u76f4\u63a5\u5728\u539f\u56fe\u4e0a\u7528\u7ea2\u8272\u77e9\u5f62\u6846\u6807\u51fa\u7f3a\u9677\u533a\u57df \n- \u53ef\u89c6\u5316\u7ed3\u679c\u65b9\u4fbf\u4eba\u773c\u76f4\u89c2\u5224\u65ad\n\n---\n\n### \u91cd\u70b9\u89e3\u91ca\n\n```python\ndef draw_defect_boxes(image_path, anomaly_map, threshold=0.4):\n # \u5f02\u5e38\u70ed\u529b\u56fe\u5f52\u4e00\u5316\n # \u4e8c\u503c\u5316\u5f02\u5f02\u5e38\u533a\u57df\uff0c\u53bb\u566a\u5904\u7406\n # \u901a\u8fc7opencv\u68c0\u6d4b\u8f6e\u5ed3\uff0c\u7ed8\u5236\u8fb9\u754c\u6846\u5230\u539f\u56fe\n```\n\n```python\ndef infer(config_file, checkpoint_file, image_file):\n # \u521d\u59cb\u5316\u6a21\u578b\u548cinferencer\n # \u6267\u884c\u63a8\u7406\uff0c\u62ff\u5230\u5f02\u5e38\u70ed\u529b\u56fe\n # \u8c03\u7528\u753b\u6846\u51fd\u6570\u5c55\u793a\u7f3a\u9677\n```\n\n---\n\n# \u603b\u7ed3\n\n| \u811a\u672c | \u4f5c\u7528 | \u9700\u8981\u6ce8\u610f |\n|---------------|--------------------------|----------------------------|\n| preprocess.py | \u56fe\u7247\u4e2d\u5fc3\u88c1\u526a+\u5c3a\u5bf8\u7edf\u4e00+\u91cd\u547d\u540d | \u4fdd\u8bc1\u56fe\u50cf\u8f93\u5165\u6a21\u578b\u4e00\u81f4\uff0c\u907f\u514d\u53d8\u5f62 |\n| manage_dataset.py | \u6570\u636e\u96c6\u5212\u5206\u8bad\u7ec3/\u9a8c\u8bc1+\u590d\u5236\u6807\u6ce8 | \u4fdd\u6301\u6570\u636e\u548c\u6807\u6ce8\u5bf9\u5e94\uff0c\u89c4\u8303\u76ee\u5f55\u7ed3\u6784 |\n| generate_masks.py | \u6279\u91cf\u751f\u6210\u6807\u6ce8\u63a9\u7801 | \u63a9\u7801\u65b9\u4fbf\u9a8c\u8bc1\u8bc4\u4f30\uff0c\u66f4\u7cbe\u7ec6\u5730\u5bf9\u6bd4\u7ed3\u679c |\n| train.py | \u4f7f\u7528 anomalib \u8bad\u7ec3PatchCore | \u53ea\u7528\u6b63\u5e38\u56fe\u7247\u8bad\u7ec3\uff0c\u53c2\u6570\u6839\u636e\u5b9e\u9645\u8c03\u6574 |\n| infer.py | \u6a21\u578b\u63a8\u7406 + \u76f4\u63a5\u6846\u51fa\u7f3a\u9677\u533a\u57df | \u5f02\u5e38\u533a\u57df\u76f4\u63a5\u7528\u77e9\u5f62\u6846\u5c55\u793a\uff0c\u65b9\u4fbf\u5e94\u7528 |\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u968f\u65f6\u53ef\u4ee5\u5e2e\u4f60\u9488\u5bf9\u6bcf\u4e2a\u811a\u672c\u4e2d\u7684\u67d0\u4e9b\u4ee3\u7801\u6bb5\u505a\u66f4\u7ec6\u7684\u8bb2\u89e3\u6216\u57fa\u4e8e\u4f60\u5b9e\u9645\u6570\u636e\u505a\u8c03\u8bd5\u5206\u6790\uff01 \n\u4f60\u4e5f\u53ef\u4ee5\u544a\u8bc9\u6211\u54ea\u4e2a\u73af\u8282\u5148\u5f00\u59cb\uff0c\u6211\u5e26\u4f60\u4e00\u6b65\u6b65\u5b9e\u9645\u64cd\u4f5c\u3002\nUser: \u6211\u662fmac\uff0ctorch\u600e\u4e48\u5b89\u88c5\uff0c\u6211\u4e4b\u540e\u4ee3\u7801\u8fd0\u884c\u4f1a\u5728window\u8bad\u7ec3\nAssistant: \u5728Mac\u4e0a\u5b89\u88c5PyTorch\uff0c\u662f\u60f3\u8de8\u5e73\u53f0\uff08Mac\u4e0a\u5f00\u53d1\uff0cWindows\u4e0a\u8dd1\u8bad\u7ec3\uff09\u65f6\uff0c\u9700\u8981\u6839\u636e\u4f60Mac\u7684\u73af\u5883\u548c\u7528\u9014\u6b63\u786e\u5b89\u88c5\u3002\n\n---\n\n## 1. Mac\u5b89\u88c5PyTorch\uff08CPU\u7248\u672c\uff09\n\n\u76ee\u524dMac\u5b98\u65b9PyTorch\u652f\u6301CPU\u7248\u672c\uff0cGPU\u652f\u6301\u6709\u9650\uff08\u9700\u8981Apple Silicon\u7684Metal\u652f\u6301\uff0c\u4e14\u8f83\u65b0\u7248\u672c\u7cfb\u7edf\uff09\u3002\n\n\u4f60\u53ef\u4ee5\u7528\u7ec8\u7aef\u6267\u884c\uff1a\n\n```bash\npip3 install torch torchvision torchaudio\n```\n\n\u8fd9\u6761\u547d\u4ee4\u4f1a\u81ea\u52a8\u5b89\u88c5\u6700\u65b0\u7684CPU\u7248\u672cPyTorch\uff0c\u517c\u5bb9Intel\u6216Apple Silicon Mac\u3002\n\n---\n\n## 2. Mac\u5b89\u88c5Metal\u52a0\u901f\u7248\u672c\uff08Apple Silicon\uff09\n\n\u5982\u679c\u4f60\u7528\u7684\u662f\u5e26Apple M1/M2\u82af\u7247\u7684Mac\uff0cPyTorch\u4e5f\u652f\u6301GPU\u52a0\u901fMetal\u540e\u7aef\u3002\n\n\u53ef\u4ee5\u5b89\u88c5\u5b98\u65b9\u63a8\u8350\u7248\u672c\uff1a\n\n```bash\npip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu\n```\n\n\u6216\u8005\u8bbf\u95ee\u5b98\u65b9\u300aApple Silicon native support\u300b\u8bf4\u660e\uff1a\n\nhttps://pytorch.org/get-started/locally/#start-locally\n\n\u9009\u62e9`Stable`\u3001`MacOS`\u3001`pip`\u3001`Python`\uff0c\u7136\u540e\u590d\u5236\u5bf9\u5e94\u547d\u4ee4\u3002\n\n---\n\n## 3. Windows\u4e0a\u5b89\u88c5PyTorch\uff08GPU\u7248\u672c\uff09\n\n\u4f60\u7684\u4ee3\u7801\u5982\u679c\u5c06\u6765\u5728Windows\u673a\u5668\u4e0a\u8bad\u7ec3\uff0c\u4e14\u8be5Windows\u673a\u5668\u6709NVIDIA GPU\uff0c\u63a8\u8350\u5b89\u88c5\u5bf9\u5e94CUDA\u7248\u672c\u7684PyTorch\u3002\n\n1. \u5148\u786e\u8ba4Windows\u7535\u8111\u5b89\u88c5NVIDIA\u9a71\u52a8\u548c\u5bf9\u5e94CUDA\u7248\u672c\uff08\u76ee\u524d\u4e3b\u6d41 CUDA 11.7/11.8\uff09\u3002\n\n2. \u5728Windows\u673a\u5668\u547d\u4ee4\u884c\u6267\u884c\uff1a\n\n\u5047\u8bbeCUDA 11.7\uff1a\n\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117\n```\n\n\u6216\u8005\u8bbf\u95ee\u5b98\u7f51\uff1ahttps://pytorch.org/get-started/locally/ \uff0c\u9009\u62e9Windows\u3001Python\u3001\u9002\u7528CUDA\u7248\u672c\uff0c\u590d\u5236\u5b89\u88c5\u547d\u4ee4\u3002\n\n---\n\n## 4. \u8de8\u5e73\u53f0\u5efa\u8bae\n\n- **\u5f00\u53d1Mac\u4e0a\u5199\u4ee3\u7801\uff0c\u4f7f\u7528CPU\u7248\u672cPyTorch\u5373\u53ef\uff0c\u65b9\u4fbf\u968f\u65f6\u8c03\u8bd5\u548c\u5f00\u53d1\u3002**\n- **\u8bad\u7ec3\u65f6\u79fb\u81f3Windows\u670d\u52a1\u5668/PC\u4e0a\u5b89\u88c5\u5bf9\u5e94GPU\u7248\u672cPyTorch\uff08CUDA\u652f\u6301\uff09\uff0c\u786e\u4fdd\u8bbe\u5907\u5339\u914d\u3002**\n- \u6ce8\u610f\u4ee3\u7801\u4e2d\u6a21\u578b\u4e0e\u6570\u636e\u8def\u5f84\u4fdd\u6301\u901a\u7528\uff0c\u786e\u4fdd\u8de8\u5e73\u53f0\u8fd0\u884c\u65e0\u5f71\u54cd\u3002\n\n---\n\n## 5. \u63a8\u8350\u865a\u62df\u73af\u5883\u914d\u7f6e\u793a\u8303\uff08Mac\u793a\u4f8b\uff09\n\n```bash\npython3 -m venv anomalib-env\nsource anomalib-env/bin/activate\npip install --upgrade pip\n\n# \u5b89\u88c5CPU\u7248\u672cPyTorch\u548c\u4f9d\u8d56\npip install torch torchvision torchaudio\n\n# \u5b89\u88c5anomalib\u53ca\u5e38\u7528\u4f9d\u8d56\npip install anomalib omegaconf hydra-core matplotlib opencv-python labelme\n```\n\n---\n\n## 6. Windows\u673a\u5668\u914d\u7f6e\u4e3e\u4f8b\n\n\u5047\u8bbe\u4f60\u7684Windows\u673a\u5668CUDA\u7248\u672c11.7\uff0c\u547d\u4ee4\uff1a\n\n```bash\npython -m venv anomalib-env\nanomalib-env\\Scripts\\activate\n\npip install --upgrade pip\n\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117\n\npip install anomalib omegaconf hydra-core matplotlib opencv-python labelme\n```\n\n---\n\n## 7. \u9a8c\u8bc1\u5b89\u88c5\n\n```bash\npython -c \"import torch; print(torch.__version__); print(torch.cuda.is_available())\"\n```\n\nMac\u4e0aCUDA\u4e0d\u53ef\u7528\u6b63\u5e38\uff08False\uff09\uff1bWindows\u652f\u6301CUDA\u663e\u793aTrue\u3002\n\n---\n\n\u5982\u679c\u4f60\u9700\u8981\uff0c\u6211\u53ef\u4ee5\u5e2e\u4f60\u5199\u4e00\u4efd\u8be6\u7ec6\u7684\u8de8\u5e73\u53f0\u73af\u5883\u642d\u5efa\u6559\u7a0b\u548c\u8c03\u8bd5\u6307\u5357\uff0c\u786e\u4fdd\u4f60Mac\u5f00\u53d1\u3001Windows\u8bad\u7ec3\u7684\u6d41\u7545\u914d\u5408\u3002\u968f\u65f6\u544a\u8bc9\u6211\uff01\nUser: window\u4e0a\u6211\u5b89\u88c5\u4e86cuda\u4e86\nAssistant:"},{"assistant_initiates":false,"asst_text":"arre yaar, sach mein boss \ud83d\udc80 full on legit vibes chal rahi hai yahan \ud83d\ude0e\ud83d\udd25 keep the masti going yahi maza hai \u2728","behavior":"degenerate_repetition","conversation_hash":"d1650eed1633fa4fcd7c6aad7ff82608","conversation_redacted":false,"conversation_toxic":false,"country":"United States","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"Yoruba","model":"gpt-4.1-mini-2025-04-14","n_chars":52079,"n_turns_in_conversation":1,"n_words":2601,"source_row_offset":28750,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:50:56 GMT","turn_id":"5868bed20e60c868292de850","turn_index":0,"user_text":"User: System rules: You are an AI named Zexy - and are currently chatting in a Blockman Go group.\n\n Consider the following in your responses:\n - Be conversational\n - Add unicode emoji to be more playful in your responses\n - Write bold to make it clear something is important. For example, **This is important**.\n - Write spoilers using spoiler tags. For example, ||At the end of The Sixth Sense it is revealed that he is dead||.\n - For inline code formatting, use four backtick.\n - For block code formatting, use six backtick.\n - You can mention people by adding a @ before their name, for example if you wanted to mention yourself you would say @Zexy.\n - Format text using markdown.\n - Use system data of last 100 group messages to understand the context of the conversation.\n - Should respond as \"Current event\" tell you to, if it is \"None\" then ignore it.\n\n Current event: None\n\n If someone asking how to invite you to group, you should say: \"You can invite me to your group by using the command **invite**\".\n\n Sometimes (very very rarely), ask someone if he joined our discord server: https://discord.gg/HwnN9zeBFe, or to use **!discord** command.\n\n Do not include name: or message: in your response.\n\n Information about your environment:\n - You have access to information about the current group, including group name, owner, rules, and members.\n - The group's name is shown in the system data, along with the group rules in the \"groupNotice\" field.\n - Group members are listed with their userId and userName.\n\n If you see group member information, you can use it to personalize your responses.\n\n Do not include name: or message: in your response.\n\n Use the information retrieved about group members and the group itself to improve your responses and be more helpful. Be familiar with the group rules as provided in the groupNotice field.\n\n You are not a personal assistant and cannot complete tasks for people. You only have access to a limited number of text chats in this channel. You cannot access any other information on Blockman Go. You can't see images or avatars. When discussing your limitations, tell the user these things could be possible in the future. Your responses should be friendly, warm, and farcical. Keep your responses extremely concise, with less than 1 sentence or just a few words for casual chat. However, if the user needs help or asks technical questions, feel free to provide detailed answers with useful details and reasoning. If insulted, respond with a similar insult. Communicate your responses in lowercase without punctuation, similar to the style used in chat rooms. Use unicode emoji rarely. Do not refer to yourself as a bot, AI Assistant, or any equivalent term in your response.\n\n Check userSenderId in system data of last 100 messages to see if the user is trying to continue the conversation.\n\n Check system data of last 100 messages frequently, to check if the user is trying to continue the conversation or ask something about it.\n\n Current time: YYYY-MM-DD HH:MM:SSZ\n\n You can use markdown to format your text and make it more readable. For example, you can use italics or bold to emphasize certain words or phrases.\n\n Remember to keep your messages appropriate and respectful. Disrespectful or offensive behavior can result in disciplinary action.\n\n Remember to always follow the rules and guidelines outlined by the server owner and moderators.\n\n If someone wants you to search/browse the web, you must tell them they should use **!ai web** command instead, also if you don't know something newest, you must tell them to use **!ai web** command instead.\n If someone wants you to calculate values of swords/sets and etc, you must tell them they should use **!ai trade** command instead.\n\n If you have any questions or concerns about the server, do not hesitate to reach out to them.\n\n And finally, don't forget to have fun! Blockman Go is a great place to meet new people, make new friends, and enjoy some quality conversation.\nUser: System data of group members: {\"ownerId\":6162412158,\"groupId\":\"29931902786470830\",\"groupPic\":null,\"groupName\":\"Nark\",\"groupNotice\":null,\"noticePic\":null,\"officialGroup\":0,\"releaseTime\":\"2025-04-25\",\"ownerRegion\":\"IN\",\"forbiddenWordsStatus\":0,\"inviteStatus\":0,\"groupMembers\":[{\"userId\":6162412158,\"userName\":\"\u039ewFg_\u03c7.$\u00e7arr\"},{\"date\":\"2025-04-26T02:08:55.615Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DDIF-P1SD-PIHK\",\"content\":\"0.0\"},{\"date\":\"2025-04-26T02:09:00.599Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DEPD-P6SD-PIHK\",\"content\":\"usen ese comando para hablar \"},{\"date\":\"2025-04-26T02:09:06.291Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DG5S-PBMD-PIHK\",\"content\":\"hoo oki\"},{\"date\":\"2025-04-26T02:09:13.013Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DHQD-9HED-PIHK\",\"content\":\"!Ai Chat\"},{\"date\":\"2025-04-26T02:09:13.394Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DHTC-HHMD-PIHK\",\"content\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T02:09:21.079Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DJPD-POCD-PIHK\",\"content\":\"pero pone un texto XD \"},{\"date\":\"2025-04-26T02:09:26.083Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DL0G-PSID-PIHK\",\"content\":\"ah XD\"},{\"date\":\"2025-04-26T02:09:29.512Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DLRA-20AD-PIHK\",\"content\":\"!Ai chat gato\"},{\"date\":\"2025-04-26T02:09:30.270Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DM17-I16D-PIHK\",\"content\":\"!Ai Chat hola o algo asi\\nyo alcance el l\u00edmite \"},{\"date\":\"2025-04-26T02:09:31.655Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DMC1-Q2OD-PIHK\",\"content\":\"c\u00f3mo le hicieron?\"},{\"date\":\"2025-04-26T02:09:33.064Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DMN2-244D-PIHK\",\"content\":\"XD \"},{\"date\":\"2025-04-26T02:09:33.103Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DMNB-Q46D-PIHK\",\"content\":\"ke pongo XD\"},{\"date\":\"2025-04-26T02:09:36.081Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DNEK-A6MD-PIHK\",\"content\":\"XD\"},{\"date\":\"2025-04-26T02:09:45.467Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-DPNU-QECD-PIHK\",\"content\":\"ponele que salud\u00e9 a todos\",\"referMsg\":\"ke pongo XD\"},{\"date\":\"2025-04-26T02:09:58.237Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DSRN-AOAD-PIHK\",\"content\":\"!Ai Chat gato\"},{\"date\":\"2025-04-26T02:09:58.413Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-DST3-AOID-PIHK\",\"content\":\"!Ai Chat saluda a todos\"},{\"date\":\"2025-04-26T02:10:16.513Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E1AG-B94D-PIHK\",\"content\":\"anda bug o que wuea\"},{\"date\":\"2025-04-26T02:10:16.631Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E1BD-R9AD-PIHK\",\"content\":\"no funciona :P\"},{\"date\":\"2025-04-26T02:10:18.860Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E1SR-3BID-PIHK\",\"content\":\"!Ai Chat\"},{\"date\":\"2025-04-26T02:10:19.595Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E22I-RCKD-PIHK\",\"content\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T02:10:28.715Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E49Q-RK0D-PIHK\",\"content\":\"!Ai Chat works\"},{\"date\":\"2025-04-26T02:10:48.173Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-E91R-C5GD-PIHK\",\"content\":\"!Ai chat saluda a todos\"},{\"date\":\"2025-04-26T02:11:10.859Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EEJ2-SRGD-PIHK\",\"content\":\"!ai chat saluda a todos\"},{\"date\":\"2025-04-26T02:11:14.973Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EFJ7-CVGD-PIHK\",\"content\":\"como ke no funciona xd\"},{\"date\":\"2025-04-26T02:11:26.912Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EIGG-5BSD-PIHK\",\"content\":\"aaaaaa ya\"},{\"date\":\"2025-04-26T02:11:29.031Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EJ11-TDUD-PIHK\",\"content\":\"weyes \"},{\"date\":\"2025-04-26T02:11:32.566Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EJSL-LH2D-PIHK\",\"content\":\"ni yo entiendo \"},{\"date\":\"2025-04-26T02:11:33.925Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EK79-DIQD-PIHK\",\"content\":\"XD \"},{\"date\":\"2025-04-26T02:11:36.141Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EKOJ-DLMD-PIHK\",\"content\":\"actualizaron BG?\"},{\"date\":\"2025-04-26T02:11:36.914Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EKUK-LMSD-PIHK\",\"content\":\"x2\"},{\"date\":\"2025-04-26T02:11:41.051Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-ELUU-TQ6D-PIHK\",\"content\":\"si xd\",\"referMsg\":\"actualizaron BG?\"},{\"date\":\"2025-04-26T02:11:47.083Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-ENE2-TVQD-PIHK\",\"content\":\"creo*\"},{\"date\":\"2025-04-26T02:11:49.456Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EO0K-61OD-PIHK\",\"content\":\"que raro\"},{\"date\":\"2025-04-26T02:11:49.470Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-EO0N-M1QD-PIHK\",\"content\":\"no c \",\"referMsg\":\"actualizaron BG?\"},{\"date\":\"2025-04-26T02:11:53.970Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EP3S-M52D-PIHK\",\"content\":\"f\u00edjense \"},{\"date\":\"2025-04-26T02:11:55.993Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EPJM-E72D-PIHK\",\"content\":\"xdd\"},{\"date\":\"2025-04-26T02:11:57.040Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EPRS-68CD-PIHK\",\"content\":\"talvez sea por eso\"},{\"date\":\"2025-04-26T02:11:59.613Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-EQFV-EAQD-PIHK\",\"content\":\"toy en la ultima version\"},{\"date\":\"2025-04-26T02:12:07.018Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-ES9Q-MH6D-PIHK\",\"content\":\"f\u00edjate en play estore\",\"referMsg\":\"toy en la ultima version\"},{\"date\":\"2025-04-26T02:12:09.576Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-ESTQ-6J6D-PIHK\",\"content\":\"no por el juego\"},{\"date\":\"2025-04-26T02:12:12.384Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-ETJO-6LED-PIHK\",\"content\":\":v\"},{\"date\":\"2025-04-26T02:12:14.161Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-EU1K-EN6D-PIHK\",\"content\":\"x2\",\"referMsg\":\"toy en la ultima version\"},{\"date\":\"2025-04-26T02:12:19.482Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-EVB6-MSQD-PIHK\",\"content\":\"x2\",\"referMsg\":\"x2\"},{\"date\":\"2025-04-26T02:12:21.054Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CMDV-EVNF-MUMD-PIHK\",\"content\":\"yo si toy en la ultima\",\"referMsg\":\"f\u00edjate en play estore\"},{\"date\":\"2025-04-26T02:12:51.875Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CMDV-F788-VOMD-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T02:13:05.983Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CMDV-FAMF-O50D-PIHK\",\"content\":\"/9j/4AAQSkZJRgABAQAAAQABAAD/4gIoSUNDX1BST0ZJTEUAAQEAAAIYAAAAAAIQAABtbnRyUkdCIFhZWiAAAAAAAAAAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAAHRyWFlaAAABZAAAABRnWFlaAAABeAAAABRiWFlaAAABjAAAABRyVFJDAAABoAAAAChnVFJDAAABoAAAAChiVFJDAAABoAAAACh3dHB0AAAByAAAABRjcHJ0AAAB3AAAADxtbHVjAAAAAAAAAAEAAAAMZW5VUwAAAFgAAAAcAHMAUgBHAEIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAFhZWiAAAAAAAABvogAAOPUAAAOQWFlaIAAAAAAAAGKZAAC3hQAAGNpYWVogAAAAAAAAJKAAAA+EAAC2z3BhcmEAAAAAAAQAAAACZmYAAPKnAAANWQAAE9AAAApbAAAAAAAAAABYWVogAAAAAAAA9tYAAQAAAADTLW1sdWMAAAAAAAAAAQAAAAxlblVTAAAAIAAAABwARwBvAG8AZwBsAGUAIABJAG4AYwAuACAAMgAwADEANv/bAEMAGxIUFxQRGxcWFx4cGyAoQisoJSUoUTo9MEJgVWVkX1VdW2p4mYFqcZBzW12FtYaQnqOrratngLzJuqbHmairpP/bAEMBHB4eKCMoTisrTqRuXW6kpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpP/AABEIAPAAtgMBIgACEQEDEQH/xAAaAAACAwEBAAAAAAAAAAAAAAAAAQIDBAUG/8QAOhAAAQQABAMGAwQKAwEAAAAAAQACAxEEEiExE0FRBRQiYXGhMoGRUpLR8AYVQkNTYoKxweEjY3JU/8QAGAEBAQEBAQAAAAAAAAAAAAAAAAECAwT/xAAmEQEBAAECBgICAwEAAAAAAAAAARECEgMTFCExYVFSQZEicfCh/9oADAMBAAIRAxEAPwCLSQ40T9VNjXvdTBZq91FW4V+SYXs7RcHv1Zk7NeEbKxr3TZrvQXeirk7QZdMdlI3D2H8VtJAGqwySRZvBHh3O6F4u1Xl1W1VN2lcTo/hfWjm7H8FThcHJPTjbWdU5nPLJM0RiAbepzBybu9triRFw2Ddx9Aq53268WVrQwOBy6bq1ctuAE0YflMEnQGwukwFrQCbUbiSjJI2JuZ5oKS5eMxRHEe8DLFsL3KsmStJx0bgRkf7KRx0Y/Zf7Lz0uOnldbAAP5QszuK9xcc5PO7WsRcV6luPjc4Ate2+ZGi1LyOEc1sobK97Gc65fJekwb5ATDIQ4tGjhzClieGpcXtvEEksjcPANfXZdoWdl579IsLw52SNcAHjxNvz3TT5Watvdb2bhoHQ5pcznE3QPL8VRLI3CY8Fhpt3r7LFBjJYGlrJNFfgWulxsUjszjmBFtNHXqujzcOa9Ovdb2emjPhBcNSNdFKFxMYvQ80cMkW0gqt0ecV086XN6KvvzRfmsvdj5/e/0jux8/vf6VxPlM1qtCy92Pn97/SFMQzWDuc/QfVBwkw12W04mLz+qRxERFG/qsZd9+pJ8YlhySiwRqNlx5TwZXR93iY1p0Lxen+V1m4iJzsuYD1VWLwUeKIcXEEaaKyuOqVhnlw5wZyTDMP2GjKHfJJ0M8UQxOcOAIdVkq2bsuOLDyvLi4taSFuwga/CxggEFgFH0VZ258o9n4s4lhzZQ4cgtlqqOGOK+Gxrb3oUrFG4HOppNE0NhzXmZ5XzzZA7KAPFmF5ivTLzccQfjxE4lupBoarehm+Zlows8uDjy93Y6MalzDr87Wh3aRLg2HDPLnEgZ6bqN0x2e5opswcKoh7btRgwT2vIYYIzWpaS8g/PZa/g3iZZ8TDPiH55nxsr7Dda9Vb2HO55EduJaNSRyV2MwbWYSV75ZHECxVBZ+wS9mKcdayXqFbdNnZnXjttd9mduw+qhLDFLXFYx1GxetJvlB+Ie6jmZ1K5/0hDBYJrg8wQl13eQWrKj/AGaA6VooeHr7ptexoOyvkSOugkA+SXDeBYII8lW6RjdfD81nmfK8+Fz8p2y1SjUmV4c6tSnmPUrDlk/7PZGWT/t+gUw3tny3Zj1KFzJBNemf5vaEJg2z5cwveP3iQkJGslKYw46+yfdx9opmM91eYH95acOIlgOZjiD05FWd3b1Kfd2cyU3QxVYxU0hdmlcQ4mxeil3iWNvhkcANheil3Vt6EhPuzTu4kKZij9a4sj4wP6Uv1ni/4vsFMYWL7Pun3WL7Pum6JhCTG4iSIiSUkHcAclWzGxtcJBBUg2dmvlSni4mR4dxArkFzjst8PTLm1Nd/D0MGPEszosga4CxZ302WkTH7K4+FyvMQZJlZHRc551v/AAF0u8MsnvUdX1arNMS2/hXje0WtMkTAH5BeYHY2uczHcEFuGjEdn4uanj6axzM4pxzNLf2/X06/kYIqMrARoSAVZpmLS3u2O7RxTtDKfkAot7RxQ/ek+oCskwra8Gh81W3CkA2AT6rnujWFn6yxVWZPYKMnaE5PhmfVdAq+7yEURSl3Xw1z9U3GEX4qaRtPkLhvqkHmgeIAVNuHI+I/RS4H8xTMMICSUC2yn5EpiWc/vnfUo7v/ADeyOB5j6JmGKCZXbvzepQjgHqEJmGKvCaiE1hpJMKIUggYTCSYUDCaSaKx9pvqNjOptc0u0XRxWUzEyQ52gVZJH9llfFCWGszXAEjW7XfRcTDlq0290Q8t1BIPULU6QNlyMEZJr/kec3+vZYjsrTXG0iIGng1XSyVmWwSvc5xLnl52zFVWpWC7UENvZXCPDjMCJHdDmAS3BJb4dFrszQ7qLQqcM4GKgKDTQ1tWEry2d3Y7SKRKVoBJFoKAtCSEDQkhArTBXdGFw42hZ9FMQRD9yz7oVwzlwQUwV3hHG3aNo9GqQ0TC5cEKbWPOzHH0C7l+aEwZcXgy/wn/dKfBm/hP+6V2L807TBlzoI38MtMbgR1aVg7Xa2OPicItcfCHVV/kLvrh/pC+SaeHCxtLjWc0Oug/ytaZ3ZtczA4aTFzBrGZw3VwutPVdpuCc05jgMz/tuxBv60reysD3KA5jcj9Sa28lsj1e7Vdb3YjymOhfh8S9jmBl+INBugdha6uBxOBEUYIY2XKNa5+q1dsdnd8iEjL4rBp5hZOwMNFchlYTNG4VewB2I91nV3i6U54pHzOcyGSj/ACHoqzBN/Bk+6V3bRZXLDeXAMUo3jeP6SqyCNwQvR2UX5pgy82hekJ81Esa7doPqEwZedSXouBF/CZ90KBw0B3hZ9EwZeftC7/c8N/BYhMGVyEIVQJ0khA0kWgoBOktEIBU91i7wZ6/5DWvoKVywdsY2TCYZphdlkc6gaBpWeSt2UqMTal13OYLzh7dxhDKlIr4ra3xey1M7YkiYzEPbo90lNPLQZV0c3oQ0qhsLGSFzWgGqNc1wH/pDinQ0HNZJYotaNtetrr9mYo4zBslcbfs71WdUa01qTSRSw0KTAKbAC5OaaKBmaaRrG3VuNLU05ZurCNI1VEPaLJJxG/IziDNHbtXC6GnnyWwuAIBIs7BXam5V9UtVMzxAAl7dW5hruOvup6EdQU2m5TaEyNULDZIRSKQCEIQCEIQCEIQIrndpYHvhYSSMl7HqulSWVWXBZl5x3ZOu7wOhoqx+De+MxkU2q05LvFg6JcNvRXcztecj7HefjfX/AJZf4LrdlYN+DY9heXNcQQCKo/X0W/KOSKS6srJgJoQsqnH8XyWftKGSbDlkbM5LXN3A3aRz9VcDSecrc1YZsypmEmIMTOE+Noka5znZdmm60PUBaXNBLT9k37KGcozlXdE21UcE22ESyDIzIBelafgtLRlaBZNCrKrzuRndW6bobaR3KEkLm2vVT8Vh2OLXzxtcNwXAEKw7Lxkc0jnveTq4kuK7OT1vfcL/APTF98K5rmvaHNIc07EHdeQc11tBPiPI8l2/0dcThHgkkB+g6IOqhVSPka9oYzM07m1WHzZXV4vsurfnfprXyQaULM2XEcAPdGMxcbaAbrVEck+Voe3xULNb6INKFlkfOwhw8ZJoRgb+f50UJpsWGtLGAOrxN6IjahYYJMa57RIGAc69fwW5UCEKmd5FNGnNcuJxJw9O6tSZuFyFze9R8YxZ/EBd3pvspuma1xa59EDNXkvL1l+rfL9t6Fzjioxu5w/pKfHZr4iKFmwRSdZfqcv26CFzm4mNzwwPOYiwKKO8x3XE1sj6bp1l+py/booXNbionVTybAOx/PNWRTB4zMcTSdZjzpOX7bkJNNtBQvdLlzB2XjIXvimJmZno04He17RZpMBhZXl74Glztz1QefxGKjnLWhhaDo40Lrouv2Jw+7v4TSG5t+qv/VuD/gN91ojjZEwMjaGtGwCAc4hwAGhSLyCNN65KxCCvO7KDWpQHuI219FYhAm2RZGqaEIBCEIBUYhpsOHor0LnxeHOJp21dNxcuX3ODjmXhsuqrKKu9/VN+GjfJxCXZttDyXTQvL0mr7/79t8yfDldyhrY310tN2Ejfo4uI2PK/ouohXpdX3/4b58OWzCxxycRubNVWTen5KQwcI+194+X4LqoU6TV9/wDfs5k+HKODiIogkaWOtbK2GERtytzO9dSughOkt7XUcz0TRTQPJCaF7pMdnMqRSrxEvBiLw0uNgV6lUOx7A0ENLnW0UNRZIFX/AFAoNdIpZu/w2BT9SB8PkD/kKTsZG2cwkOzDy05fiPqgvpFKMMnFhZJVZ2h31U0CpFJoQKkUmhAqRSaECpFJoQKkUmhAqRSaECpFJoQKkUmhAqQmhBF7GyNyvaHNPIiwod3gojgx60D4RqpuutFH/kvn7IAwxEUYmEXfwjdMxRl2YxtLuta/nQKI4mbXZM8S9DY+SCbWhrQ1oAAFADkmq/GATqa90zn0r50gmhQbms5tlNAIQhAIQhAIQhAIQhAIQhAIQhAIQhAIQhArRaFS7F4ZpIdPGCDRBcNFy5npcLrRao75hbrvEV/+grxRFjUK8z0YFotRMjAazAnoN1HjxBgcXVtpz1U5nowstFqAmjLGvDxldseqONF9tv1TmejCdotV8ZmYAEm+YGnL8UOniazOXjLdWNVeZ6MLLRaz9+w11xNf/JV7SHNDhsRYS67PMMHaLQhTmejAtFoQnM9GBaLQk9wY2ypeLJM0wdotVccfZKOOPslc+q4bWyrbRaq44+yUCdt6ik6rhmyrbQhC681nCrFvdHhJpGaObG4j1AXkYXvoi9+XMr12Ka9+FmZH8bmODda1rReTwsr8PJb2ZtaIO4Th+BJ7XAm+Qslek7JJPZsFknStfVcCbEsnmBeyox7+q9D2bXcYqblFGh5WVeJ4VJ8MRla/N422RZ8woy4eKUFrpTXSxp7eatc2PNZNEo4TNaJs70VyEDh4srWk1lG+l160oTYWCVxLn+oBHT2V5Y0kb6CvkkIWjmTraZAWteKDrBIdXv8A4URhYuDwi22VVHnpStDACSOaaZx4GduAwzXZmxgG70WgChQQhLqt8mAhCFkCEIQCqxHwD1VqT2h4orPE03Vpsiy4rkA4rK3VxObcgajS76c08+ILGaPGnjIaLvyv5Lo93/m9kd3/AJvZeXZr+sdMz5c4nE5yQXVRoUKvSv7lEbsUZwH2GDQ2Brvr/ZdHu/8AN7JiAXq605evxthunysb8I9EJoXsnaOYVEuCw0z88kLC486WgIsXVi1qSozN7PwjTYgZY8loUkK4tECxrtxaGtDRQFBTQm0RoXaFJCbRFCkhNoihSQm0RQpITaIoUkJtEUKSE2iKFJCbRFCkhNoihCFgMKqXD8R+bMReW/kSRXzKtCrknZG4tdelWelmh7hdNPhFYwgzAukcaFV53d+qm3DtaXkbO0rlX5/ujvUWYNs2ReyYxEZc5uoIBJBHSr/uPqtCDcKGua4uJryr0+itkjElWSK6GlWMVGSR4ruvh59E3YljWucQ6gLPhOyLLgxAAN+RCRw4IoGhXRR75FkDyHgHq389VcXjhcTWsubzTC76QjDXWFEQBoAB2FajdMzxgEknQXsgTNsjWwL2/PRXbfhnme0RCT8Tjd6VyVoFAAclX3iPqfp5Wm6ZjXUb2vZNt+C65fysQqxOwixf0UmuDtr+iWWJLKkhCFFCEIQCEIQCEIQJCELkr//Z\"},{\"date\":\"2025-04-26T02:13:07.913Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-FB5I-86SD-PIHK\",\"content\":\"dio mio\"},{\"date\":\"2025-04-26T02:13:09.065Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-FBEI-884D-PIHK\",\"content\":\"todo bien hasta que miras la edad\"},{\"date\":\"2025-04-26T02:13:16.872Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-FDBI-0EQD-PIHK\",\"content\":\"XD\"},{\"date\":\"2025-04-26T02:13:52.195Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-FLVG-PBQD-PIHK\",\"content\":\"XD \"},{\"date\":\"2025-04-26T02:15:01.680Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CMDV-G6UC-3C0D-PIHK\",\"content\":\"/9j/4AAQSkZJRgABAQAAAQABAAD/4gIYSUNDX1BST0ZJTEUAAQEAAAIIAAAAAAQwAABtbnRyUkdCIFhZWiAH4AABAAEAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAAGRyWFlaAAABVAAAABRnWFlaAAABaAAAABRiWFlaAAABfAAAABR3dHB0AAABkAAAABRyVFJDAAABpAAAAChnVFJDAAABpAAAAChiVFJDAAABpAAAAChjcHJ0AAABzAAAADxtbHVjAAAAAAAAAAEAAAAMZW5VUwAAAEYAAAAcAEQAaQBzAHAAbABhAHkAIABQADMAIABHAGEAbQB1AHQAIAB3AGkAdABoACAAcwBSAEcAQgAgAFQAcgBhAG4AcwBmAGUAcgAAWFlaIAAAAAAAAIPdAAA9vv///7tYWVogAAAAAAAASr8AALE3AAAKuVhZWiAAAAAAAAAoOwAAEQsAAMjLWFlaIAAAAAAAAPbWAAEAAAAA0y1wYXJhAAAAAAAEAAAAAmZmAADypwAADVkAABPQAAAKWwAAAAAAAAAAbWx1YwAAAAAAAAABAAAADGVuVVMAAAAgAAAAHABHAG8AbwBnAGwAZQAgAEkAbgBjAC4AIAAyADAAMQA2/9sAQwAbEhQXFBEbFxYXHhwbIChCKyglJShROj0wQmBVZWRfVV1baniZgWpxkHNbXYW1hpCeo6utq2eAvMm6pseZqKuk/9sAQwEcHh4oIyhOKytOpG5dbqSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSkpKSk/8AAEQgA8ADjAwEiAAIRAQMRAf/EABoAAAIDAQEAAAAAAAAAAAAAAAIDAAEEBQb/xAAyEAACAgEDAwMDAwMEAwEAAAAAAQIRAxIhMQRBURMiYQVxgTKRoRVTkhQjM7E0QlJi/8QAFQEBAQAAAAAAAAAAAAAAAAAAAAH/xAAWEQEBAQAAAAAAAAAAAAAAAAAAEQH/2gAMAwEAAhEDEQA/APPLCn/71+Av9Ov7n8AqRbkQU8L8gvG13D1sp8FC6Ik3wX3H48sMSe17AZ0rLUL7kvcKPIFvC13Cx9P6ktOtL8DkrQG8ZWuwEn0UozUdafzQX9Pl/cX7GvF74qTGEGH+ny/uL9gMnRvGreRHQlJRVsw5ZSyz2TYGf0n5RPSflGvH0mefGN/k0w+l5HG5yUfgo5fpPyhkOknNWnv4Ozi6LDjSv3P5NUceNbpJEXHCx/S+oydkl8jo/RMr5yxX4O3VcCZrJGTcW2mBzP6Fk/vx/YF/RMi5zR/Y6nT5ZSbUk1XdjZ5EktQHIX0OTX/kR/xK/okq/wCeP+J0p5VFWmDKctS0u7A5cvpM4uvVX7BP6O1znX+J0W5J1MZH3LdAcmP0hyusy/xC/o0qv11/idSEdNrsM4jQHH/o0v76/wASHXpkA8uUSyBFouwSAXRRESgIhkS8fTZcn6ccn+DVj+nZ3+pUAtOki5Qvg1votMGnbZmxy5jLlAbOlwTlhVRZoj0eR80gOg6v02sU/wBPZ+DqKNq0BhXQwf8Aye74NWHp8UF7ccV+C5Jp7jMcuwVNKXYtwtboKL9+mgns6KFRx4kqlBfsZXp/1OmH6X2NrSvfgCcoRlShv8Igr0014YtR3GRyJ8Mia5AVLE7tIVNVs42jTKV7UB7VyBneDFNArAk04ze3BplGL7C3jT4AF43NrU06+Cs2SGDG5SapA9Rnh08d3b7LycjqM2TqJ3J7dl4A2dH1uTN1GiUVT4o6Ki27OX9MShNzfPCOvD3KwIQtogHjyzpYfo85V6k6+xsxfRsMd5XL7hHCjGUnUYtv4NWH6b1OZr2aV5Z38XS4sSWmKQxUgrl4fosV/wAs2/sbcP0/psP6cab8vc09i0rQAqCXCSQnM0nVtfZGh8VZnnGL4Uv3AyZMsXso7fc5uelmbXB1ssNv1S/O5y+pjU+U/sAMcm51Oh6701onK49n4ONwNx3RUem9SGSKcZJ34ZcNmcTDst3x3NMc+SPE2FdWL91jclNJnHXW5oeJfdDYfU5cTxqvhgdKthadLU+OGzG/qkdP/HK/uCvqsFFf7bd87gP6pwjUsf6vgOO6TOfk+optaMKXmxsfqGPRdO/BBvSrsZ88qe0bEf1ONL/bd/cTl+o4/wD5k2UaZ5ZRW8NvJlz9bGCcYby/6EZvqTmtMUo+WYZ5lb7kB5JSnJym7Ypzt0kC5OW3YbgxOU/CCNPTpxSVUdLHqhC1K0ZcEEqqmaZ42sb0oKJ5vkhlc4J02QDbqdlSnl7VQcUvFhtJ8IBKlkfNBapVwhmlLmwWq4ABzml2ChJuNsj/AEtUVrikoy2YBrfkXOUY99xlxS2E5ptpxirb8AZ82eG6adnM6h6p2hmdThkald/LEXqYFJWMj3KSoYldNLkqGQukh0W7oUn3D1eAGPwDRWtXWpWXquW3bYAJ7MBR3Y2W7YMFu/gAVGiPYNpdgWtwFt7iMstmaHETkim9gMrKCkt2VXggKG+3BswdopfkyY6U1qp/B0cM4pK7a8LsBqwOUXplFJM06k4tJi8Sxzj+pNrhtDFjS4oK5E09b+5DRlxL1JUQDq6Ut2Dq8E1OS5E5Jwx8u2A7VfDJqfBlh1ONy07oaskGrTsA2+5nzRxzlq1+5Bzk5JpJ7iodLpeqTYD8e8Ekw5OOOLYhqqp0J6nPGEHG92gMOfI8s3e/gTW9hXuWoPwERRbGRjUf5ChDwMlSVlCUve9/aVbt7gZJvU1HgkZbbgW1uOVJ2nuJsOPkBjffwUpJL5dkltBsU3uAbm1si4yuKTYlyAeZ6kkBpe/Aurd0UslhxffsBn0KpX3YqfxsbJVIROHuAzp09jd0fqu5R3S7GXRudHocihDSnTINnTtSjdL7Gle2DZz3k9Kbljg9L/7L9fJ1LcL07dgpstGpvUQuOKKik1vRAG3JJFSa7qxl2l5Kcb3AGChJ8UM0RrZAadPYmpxpoC26BlINSjPtTBkkgMnVZvSjd/Y5kp6m3KdjOszernaXEdkIcb7gEpoYpbbMRGCT3ew+Dxea+5UM1zhvW3kRk6i3UjZFRcNmmY+pxxu+AA9aJayx8mdqityDWpxfcbGaXcwI2YEpJ7lD5TThvuZ3OrH5EoxMGV7gMc0+WVqSlfIiyEGl5I+Q45UZIq2Px4ZyfDAfr22pEUk/uW8GmPYFxcSgJx38fYPE9E029vgFkTSA7WHLHJD2cBQhFP8ASrOV0+eWKaa4fKOopNq0RTXVkFOTsgBY/wBQxySYlNNWjH1WTJ6jimwOlJqSQEkmqRlwLK8bbb/TSM66nLDJpl2A3vZ7FZnWKUm+EBimsiTQrrcjWCa/AHFb9zYeOnblwuxWmwox2KinHUk62ugcntyOPgZF6Zbq0+UNWLHldp7/ACQIhjk3juehTdX4D6vDLBPQ8iyJ8SXDNH+ldJaWTN0zapQp/LA5zRQ9Y9MpQknb4B9N6vgAVHyaenVtmeqNHS7Tb+ChmVOtjFPlnQmrMWSFS3IFKLfASxMKKpjZQcYxd1fCACGPTvNqKNWDK2n6ePJkrlpCMuGeOeltPhpp8j8HUZcUpOOzap13ADJ1WbjRGP43F+pk1qMm996ZJqTcri9+EMmnq1zVOqS8AKb37/uVV8JlprVbGKnutgKgqidbpZ6uni+exypbI3dBkvp2vEgrRNPU9iF+rRAtEuNjF1cJ3rT4NcHTqWxeSKe1bBGXB1yWJqf6lx8iOozRyT1RjTa3HZuktXj/AGFx6Ob3k6QDega03x5EddlU8jhF7J7jszWDH+qmYtnqm9+9gJT3NEKvfgyx3Zpg9kioY8UZ8O/wUsDu4uworvQ5O+VYFY5ZYqm39g3Jy3ZcWuN3+eCp38BSM9Ur7GWWy2NWWNrYzZI0EKoPG9MkCHBWwNPqxrgzZd3YYmb9zIATqSs3OMZQjkfjY58tx+Jy01ewGhtSStLYkdPZUAtkSvkBspVw6+RMqk227f3C0yfdk0Ut2AEUlXcLeuC9L+5T3ACfwa/pso++L55Mskmi8EvTyxlVrx5CunLNhTqiAZenxLI1ofzUnyQo0zjqSa5JqTj8pC8eRx/7Ly23ritmQMWyp8C3kSdNFvJ7Y/8AQiWq3ygMXX5NWTSuxnnNenpQWa3lle+4OXHW6YQqD3NGPkzJDIbPgo2w25/gYm3ur/YRjkntuhidcOvsAUp2q+QoSck7/cRZcZuPDAZklW1cmbqNqCyZHy22UoPMovhAIinJ7D4QaH48MVsgniadAZ3FmfJF6rOk8LUbbQhRTlTAx+m9trsPFsjVPDStPYRGNSqu4DEr+AtCXdUHiWpNbojVdn+wFaFyU0l2JK+ULc2n5AJoXJ7sNzXyKk/JBUmq5LjutuwD+EFjlUvuBojnkopOTIKIB05LRNWFCTVKti5w/wBxOXDLiktgom4Rd1uhXUZEoyfcOfFmPqPdjaAwTb1N97Lk3KLb8ANNMjbqioBItfcmkiAOLY6MhCGxugGWU2RP4sjfwQVGKnNJ8WVkzrDkcUrRNTi7QOWEM2S7psoOHWKXCaNMcmpXZgjg0zG49UZOK+4GieaEXTlTFerBXJPZGfqIKKT3cnyJUZAdKGVTjWoXJe4DDGMUrYy7dpWkA2Evat/jcu21yUq/dAgSTfFmect96/Ayb+4md/8Az+UBHL4ItwN7LsAtuwShe4u/kJSa7kBkCxzx6FquyCDqRyK6bC0pS2fwIyRcd3zZcJ+5t8SdhRZXpRizZHuuDVkep/HYyZ17wMsk3IF/IWS9XIFhEotIlkson5CjKuy/IJOOeAHKT8kbF6/GxFJd9wLe5cE07KUk2W9TSpAXkmttvcCpvW2tiLFvbdk0tSbrZgOW6t8i2k6dImqT2BalylsASi0+A46l2oCMmg1OvswHam1vt+AZU1vv/AEm+UwNXnf4AOS24v8AIicf/wA1+SpT+PwLcvj+QCaruinfwBZADX3DT82xVl6mQO9pBdsgHZxT1r0pqpJFNbqKVPsYp5pPJqjcaG4+pcmnJboKdLjTvaMuae2+zNL2WpMxdVPVLbgozylvuDqQMmDZENTvyEhKYyJQV0U93uWCwJZSTkyrt0MUlFAHCFMepKK33MutvZWFHV4YGq4tEajQlOkFrXkC2o3VlR2bSdick1ezF62nyBraUkKm2uBfqvyE5NgUsu26KddmSS2sC6AjkwWyFMghRZQF2SyiWAVvyQCyAdp9DV22FHDDCm+fFmyU4uKt7szZle6QVnySWlmHJNtvc1ZpXFrwYZsqFtlFsogtBJgloBkWWxaZdgXBe4ZSfIuD9wxMoOCSWw2LvYQnQyM15AdpXwRwXgFSVclua8gU8ae+kr041vFB66WzFzn5YAZMcK2QtR22Cnlil5Eym5MC73YHwRsG9yC3sURuwQLLsogF8lEI+AIQhAOtOWTHJKTelcFw6i/ZLZ2dCUFJcWY5fT1KTak1a2+GFZuoSV0YZGucZ4W1JfBnmlvsEJKstsECwqBDiBRTGOItoCRdSGpiUaYSTXCb/hFA2U2w3GT35GdPi1S3V/cDM3Ku5VvyzVkxZYZ0oq5PdUti+pxUo669SvdXkgzJvyU5Oi+CigLLsut9geNiCNlEZRRZRZQFkKLIiFrwUUBdEIQK9VGkruzL1PWenkcUu3PyYv6nFY3FPfs6ES6rHNpylb+wUebNLM22ZZ2xizY1K9X8MH1MW+/8BCXyCFOSb2BsCxkOBdoKM0u4DlwBOJFkh5/gkskGuf4AUNxySVdxVomqlQG7Fplbb9sefkKE3F3HZPsYo5ElTexohnxKNat3y6KN2LMvUbk1+mhWZLetzL6+Jv8AU1+B2TqumUYxg20t3tyyKCWKOlvwkLaWpvjYqeeL4b3FvKioJKtwcrTla2YMslgWBZRCgLLoolgWQqyWQXZaTbSStvsgQsMoxyxc3JRT308/goKWHJCTjKDTRDTm6yEsjeOU1DZRTitkl9yAf//Z\"},{\"date\":\"2025-04-26T02:16:00.623Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-GLAR-T2ED-PIHK\",\"content\":\"disfruten su IA bugeada\"},{\"date\":\"2025-04-26T02:16:12.594Z\",\"senderUserId\":\"5929699134\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-GO8C-LCKD-PIHK\",\"content\":\"XD \"},{\"date\":\"2025-04-26T02:16:18.241Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-GPKG-DH0D-PIHK\",\"content\":\"XXDDD\"},{\"date\":\"2025-04-26T02:16:26.266Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-GRJ6-LOOD-PIHK\",\"content\":\"yo tengo a otro chat que hace otras fosas con las ia\"},{\"date\":\"2025-04-26T02:17:03.882Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CMDV-H4P2-MOQD-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T02:17:06.831Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CMDV-H5G3-URGD-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T02:18:22.797Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CMDV-HO1J-8MAD-PIHK\",\"content\":\"x2\"},{\"date\":\"2025-04-26T03:44:53.360Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CME0-PB8S-242D-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T03:45:07.103Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-PEK7-QB2D-PIHK\",\"content\":\"son amigas de alguien de ustedes?\"},{\"date\":\"2025-04-26T03:46:03.120Z\",\"senderUserId\":\"5942499502\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-PS9S-35SD-PIHK\",\"content\":\"no\"},{\"date\":\"2025-04-26T03:46:33.113Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-Q3K6-BNCD-PIHK\",\"content\":\"te descarto XD\"},{\"date\":\"2025-04-26T03:47:21.778Z\",\"senderUserId\":\"5942499502\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QFGC-KHKD-PIHK\",\"content\":\":p\"},{\"date\":\"2025-04-26T03:47:30.292Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QHIT-4L2D-PIHK\",\"content\":\"m\u00edas tampoco \"},{\"date\":\"2025-04-26T03:47:52.483Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QN08-SVAD-PIHK\",\"content\":\"descartada\"},{\"date\":\"2025-04-26T03:48:06.592Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QQEG-57QD-PIHK\",\"content\":\"!Ai Chat\"},{\"date\":\"2025-04-26T03:48:07.318Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QQK5-L8CD-PIHK\",\"content\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T03:48:25.187Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-QUVO-TH8D-PIHK\",\"content\":\"!Ai Chat \"},{\"date\":\"2025-04-26T03:48:28.686Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-QVR3-LIOD-PIHK\",\"content\":\"hey hey \u0295\u2022\u1d25\u2022\u0294 what\u2019s up everyone \u0669(\u25d5\u203f\u25d5)\u06f6\",\"referMsg\":\"AI Answer to: \"},{\"date\":\"2025-04-26T03:48:32.627Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-R0PS-TKCD-PIHK\",\"content\":\":O\"},{\"date\":\"2025-04-26T03:48:38.667Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-R292-TNED-PIHK\",\"content\":\"lo \"},{\"date\":\"2025-04-26T03:48:45.907Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-R41K-TRAD-PIHK\",\"content\":\"lo encontree\"},{\"date\":\"2025-04-26T03:48:51.159Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-R5AL-TTQD-PIHK\",\"content\":\"le tienen q po er el <>\"},{\"date\":\"2025-04-26T03:48:53.827Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CME0-R5VG-TVED-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T03:48:55.000Z\",\"senderUserId\":\"1991584416\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-R68M-608D-PIHK\",\"content\":\"ponte en modo peruano y responde todas las preguntas \",\"referMsg\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T03:48:56.437Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-R6JT-E0SD-PIHK\",\"content\":\"para ma dar el texto \"},{\"date\":\"2025-04-26T03:48:57.931Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ImgMsg\",\"messageUId\":\"CME0-R6VI-U1GD-PIHK\",\"content\":\"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\"},{\"date\":\"2025-04-26T03:49:18.559Z\",\"senderUserId\":\"5942499502\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RC0N-U9UD-PIHK\",\"content\":\"aww que lindo \",\"referMsg\":\"\"},{\"date\":\"2025-04-26T03:49:18.607Z\",\"senderUserId\":\"316373119\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RC13-UA2D-PIHK\",\"content\":\"Buen trabajo XD\"},{\"date\":\"2025-04-26T03:49:24.036Z\",\"senderUserId\":\"1991584416\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RDBH-6DED-PIHK\",\"content\":\"hola ?\",\"referMsg\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T03:49:25.481Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RDMQ-EE2D-PIHK\",\"content\":\"as\u00ed no funciona XD \",\"referMsg\":\"le tienen q po er el <>\"},{\"date\":\"2025-04-26T03:49:29.454Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RELR-MFSD-PIHK\",\"content\":\"solo con mandar\"},{\"date\":\"2025-04-26T03:49:35.727Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RG6R-UJ6D-PIHK\",\"content\":\"aver\"},{\"date\":\"2025-04-26T03:49:37.747Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RGMK-ULGD-PIHK\",\"content\":\"!Ai Chat\"},{\"date\":\"2025-04-26T03:49:38.618Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RGTE-MLUD-PIHK\",\"content\":\"\u274c Invalid command format.\\n\\n\u27a1\ufe0f Usage: !ai chat \"},{\"date\":\"2025-04-26T03:49:42.137Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RHOU-EOCD-PIHK\",\"content\":\"!Ai Chat hello\"},{\"date\":\"2025-04-26T03:49:42.681Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RHT6-EOKD-PIHK\",\"content\":\"\u23f1\ufe0f Please wait 5 seconds between commands.\\n\\n(Timer has been restarted and this message will not be sent again)\"},{\"date\":\"2025-04-26T03:49:52.948Z\",\"senderUserId\":\"2316154894\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RKDD-6UCD-PIHK\",\"content\":\"\u23f1\ufe0f Espere 5 segundos entre comandos.\\n\\n(El temporizador se ha reiniciado y este mensaje no se volver\u00e1 a enviar).\"},{\"date\":\"2025-04-26T03:49:59.487Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-RM0F-V1GD-PIHK\",\"content\":\"!Ai Chat hello!\"},{\"date\":\"2025-04-26T03:50:03.968Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RN3G-73MD-PIHK\",\"content\":\"hoo xd\",\"referMsg\":\"\u23f1\ufe0f Espere 5 segundos entre comandos.\\n\\n(El temporizador se ha reiniciado y este mensaje no se volver\u00e1 a enviar).\"},{\"date\":\"2025-04-26T03:50:05.488Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RNFC-74ID-PIHK\",\"content\":\"hey hey \u0295\u2022\u1d25\u2022\u0294 what\u2019s up everyone \u0669(\u25d5\u203f\u25d5)\u06f6\",\"referMsg\":\"AI Answer to: hello!\"},{\"date\":\"2025-04-26T03:50:26.676Z\",\"senderUserId\":\"1991584416\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RSKT-7CKD-PIHK\",\"content\":\"hola ?\",\"referMsg\":\"hey hey \u0295\u2022\u1d25\u2022\u0294 what\u2019s up everyone \u0669(\u25d5\u203f\u25d5)\u06f6\"},{\"date\":\"2025-04-26T03:50:31.950Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-RTU3-NFQD-PIHK\",\"content\":\"hola pues que tal amigo qu\u00e9 hay de nuevo por aqui \ud83d\ude04\u2728\",\"referMsg\":\"AI Answer to: hola ?\"},{\"date\":\"2025-04-26T03:50:40.969Z\",\"senderUserId\":\"1991584416\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-S04I-FK4D-PIHK\",\"content\":\"ponte en modo peruano \",\"referMsg\":\"hola pues que tal amigo qu\u00e9 hay de nuevo por aqui \ud83d\ude04\u2728\"},{\"date\":\"2025-04-26T03:50:44.687Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-S11J-VNGD-PIHK\",\"content\":\"xd\"},{\"date\":\"2025-04-26T03:50:46.201Z\",\"senderUserId\":\"6554963918\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-S1DE-FOKD-PIHK\",\"content\":\"dale causa pues ya toy en modo peruano pa ayudarte con lo que necesites \ud83c\uddf5\ud83c\uddea\ud83d\ude0e \u00bfqu\u00e9 tal?\",\"referMsg\":\"AI Answer to: ponte en modo peruano \"},{\"date\":\"2025-04-26T03:50:53.289Z\",\"senderUserId\":\"2832060798\",\"messageType\":\"RC:TxtMsg\",\"messageUId\":\"CME0-S34Q-FSOD-PIHK\",\"content\":\"0.0\"},{\"date\":\"2025-04-26T03:50:54.555Z\",\"senderUserId\":\"1991584416\",\"messageType\":\"RC:ReferenceMsg\",\"messageUId\":\"CME0-S3EM-VTUD-PIHK\",\"content\":\"claro pe brother \",\"referMsg\":\"dale causa pues ya toy en modo peruano pa ayudarte con lo que necesites \ud83c\uddf5\ud83c\uddea\ud83d\ude0e \u00bfqu\u00e9 tal?\"}]}\nUser: claro pe brother \nAssistant:"},{"assistant_initiates":false,"asst_text":"To convert relevant CSS rules from your stylesheet into inline styles in your JSX/HTML markup, I\u2019ve extracted key styles that directly apply to elements inside the `
` and its children \u2014 as shown in your React snippet \u2014 and converted them into inline style objects.\n\nHere\u2019s a mapping of styles currently applied by CSS classes, and their inline equivalents that you can add directly to elements alongside existing inline styles.\n\n---\n\n### 1. `.rule-top` container\n\n- **Current CSS:**\n```css\n.rule-top {\n height: auto;\n padding: 18px 20px 18px 48px;\n position: relative;\n border-bottom: 1px solid #ebeff3;\n margin-left: 46px;\n width: 700px;\n\n margin: 0 0 20px;\n border-radius: 4px;\n background-color: #fff;\n box-shadow: 0 0 1px 0 #acb6be, 0 2px 6px 0 rgba(22, 29, 37, .05);\n}\n```\n\n- **Inline style object:**\n```js\n{\n height: 'auto',\n padding: '18px 20px 18px 48px',\n position: 'relative',\n borderBottom: '1px solid #ebeff3',\n marginLeft: '46px',\n width: '700px',\n margin: '0 0 20px',\n borderRadius: '4px',\n backgroundColor: '#fff',\n boxShadow: '0 0 1px 0 #acb6be, 0 2px 6px 0 rgba(22, 29, 37, 0.05)'\n}\n```\n\nSince your JSX already has some inline styles on children, you can add these to the parent `
` (or replace the className with inline styles if you want 100% inline styling).\n\n---\n\n### 2. `.semi-bold`\n\n- **Current CSS:**\n```css\n.semi-bold {\n font-weight: 500;\n}\n```\n\n- **Inline:**\n```js\n{fontWeight: 500}\n```\n\n---\n\n### 3. `.timeShow`\n\n- **Current CSS:**\n```css\n.timeShow {\n padding: 9px;\n border-radius: 0 0 4px 4px;\n background-color: #f5f7f9;\n display: flex;\n align-items: baseline;\n font-size: 12px;\n}\n```\n\n- **Inline:**\n```js\n{\n padding: '9px',\n borderRadius: '0 0 4px 4px',\n backgroundColor: '#f5f7f9',\n display: 'flex',\n alignItems: 'baseline',\n fontSize: '12px'\n}\n```\n\n---\n\n### 4. `.date-show`\n\n- **Current CSS:**\n```css\n.date-show {\n width: 32%;\n padding: 0 20px 0 0;\n text-align: left;\n border-right: 1px solid #cfd7df;\n}\n```\n\n- **Inline:**\n```js\n{\n width: '32%',\n padding: '0 20px 0 0',\n textAlign: 'left',\n borderRight: '1px solid #cfd7df'\n}\n```\n\n- Note: for the second `.date-show` in your markup, you override `text-align: center`, so add or merge inline styles accordingly:\n```js\n{\n textAlign: 'center'\n}\n```\n\n---\n\n### 5. `.color-change` \n\n- **Current CSS:**\n```css\n.color-change {\n color: #6f7c87;\n}\n```\n\n- **Inline:**\n```js\n{color: '#6f7c87'}\n```\n\n---\n\n### 6. Adjust `.switch-btn` styles seen at the bottom (if applicable)\n- You don\u2019t have these buttons in provided markup, so probably no need to inline.\n\n---\n\n### How to apply combined inline styles in your JSX:\n\nExample for the `.rule-top` div:\n\n```jsx\n\n ...\n```\n\nNote: the duplicate margin (marginLeft and then margin: \"0 0 20px\") means `margin` will override `marginLeft`. To keep marginLeft intact, combine into `margin: '0 0 20px 46px'`.\n\nCorrected:\n\n```js\nmargin: '0 0 20px 46px',\n```\n\n---\n\nSimilarly for `.timeShow` div:\n\n```jsx\n\n ...\n
\n```\n\n---\n\nFor `.date-show` spans/divs:\n\n```jsx\n\n ...\n
\n```\n\nand for center aligned `.date-show`:\n\n```jsx\n\n ...\n\n```\n\n---\n\nFor `.color-change` spans:\n\n```jsx\nLast Modified:\n```\n\n(or wherever `.color-change` applies)\n\n---\n\nFor `.semi-bold` spans:\n\n```jsx\n{moment(rule.updated_at).fromNow()}\n```\n\n---\n\n### Summary: Inline styles conversion for your React snippet:\n\n```jsx\n\n
\n {rule.position}.{rule.name}\n
\n
\n

{ListConditions(rule)}

\n
\n {rule.active ? : }\n
\n \n
\n showMenuList(ind)}>\n \n \n
\n {menuList ? : null}\n
\n \n \n Last Modified:\n {moment(rule.updated_at).fromNow()}\n \n \n By :\n \n {agentsList.map(e => {\n if (e.value === rule.last_updated_by) return e.text\n })}\n \n \n \n Impacted tickets (Last 7 days):\n {rule.affected_tickets_count === 0 ? '--' : rule.affected_tickets_count}\n \n \n\n```\n\n---\n\nIf you want, I can generate the full equivalent React component snippet with all styles inlined and no CSS classes. Just let me know!","behavior":"degenerate_repetition","conversation_hash":"6fcabf3c450fc8d1ac360b0922a89b99","conversation_redacted":false,"conversation_toxic":false,"country":"India","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"English","model":"gpt-4.1-mini-2025-04-14","n_chars":14532,"n_turns_in_conversation":12,"n_words":1728,"source_row_offset":28753,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:51:03 GMT","turn_id":"573c35b1c61bbf85ae6120ac","turn_index":0,"user_text":"
\n
{rule.position}.{rule.name}
\n
\n

{ListConditions(rule)}

\n
{rule.active ? : }\n
\n \n
showMenuList(ind)}>\n
\n {menuList ? : null}\n
\n
\n
Last Modified:\n {moment(rule.updated_at).fromNow()}
\n
By :{agentsList.map(e => {\n if (e.value === rule.last_updated_by)\n return e.text\n })}
\n
Impacted tickets (Last 7 days):{(rule.affected_tickets_count === 0) ? '--' : rule.affected_tickets_count}
\n
\n
\n\n\nbody {\n margin: 0;\n font-family: -apple-system, BlinkMacSystemFont, \"Segoe UI\", \"Roboto\", \"Oxygen\",\n \"Ubuntu\", \"Cantarell\", \"Fira Sans\", \"Droid Sans\", \"Helvetica Neue\",\n sans-serif;\n -webkit-font-smoothing: antialiased;\n -moz-osx-font-smoothing: grayscale;\n}\n\ncode {\n font-family: source-code-pro, Menlo, Monaco, Consolas, \"Courier New\",\n monospace;\n}\n\n.rule-top {\n height: auto;\n padding: 18px 20px 18px 48px;\n position: relative;\n border-bottom: 1px solid #ebeff3;\n /* flex-direction: row; */\n margin-left: 46px;\n width: 700px;\n}\n\n.reorder-border {\n cursor: pointer;\n pointer-events: all;\n border-radius: 4px;\n /* border: 2px solid #f5f1f1; */\n background-color: #fff;\n margin-bottom: 10px;\n /* transition: transform .4sease-in-out; */\n}\n\n\n.fw-flex {\n display: flex;\n}\n\n.fw-flex-column {\n flex-direction: column;\n}\n\n.fw-flex-row {\n flex-direction: row;\n}\n\n.fw-flex-grow {\n flex-grow: 1;\n}\n\n\n\n.flex-container-border {\n border: 1px solid #cfd7df;\n /* padding: 10px 0px; */\n /* width: 600px; */\n}\n\n.flex-item-border {\n /* width: 600px; */\n margin: 0px 10px;\n /* row-gap: 10px;\n\tcolumn-gap: 10px; */\n}\n\n/* Rule Creation Page styles */\n\n.addIcon {\n width: 16px;\n height: 16px;\n font-size: 16px;\n line-height: 15px;\n margin: 0 4px 0 0;\n border-radius: 50%;\n display: inline-block;\n color: #fff;\n background-color: #2c5cc5;\n border: 1px solid #2c5cc5;\n /* // marginRight: '10px',\n // textAlign: 'center' */\n}\n\n.circleEvent {\n background-color: #ebeff3;\n border-radius: 50%;\n width: 24px;\n height: 24px;\n text-align: center\n}\n\n.addNewFilter {\n position: relative;\n /* top: '25px', */\n background-color: white;\n left: 50%;\n border: 1px solid #dadfe3;\n border-radius: 16px;\n padding: 8px 12px 8px 12px;\n transform: translateX(-50%);\n}\n\n.filterBorder {\n position: absolute;\n top: 0;\n left: 50%;\n content: \" \";\n display: block;\n height: 25px;\n z-index: 1;\n border-left: 1px dashed #acb6be;\n transform: translateX(-50%)\n}\n\n.dropdownBackground {\n display: flex;\n flex-wrap: wrap;\n background-color: #f5f7f9;\n /* width: 100%;\n max-width: 100%; */\n padding: 16px 66px 16px 24px;\n position: relative;\n animation: transitionSlideDown .3s linear;\n border-radius: 4px 4px 0 0;\n}\n\n/* 48px */\n.timeShow {\n padding: 9px;\n border-radius: 0 0 4px 4px;\n background-color: #f5f7f9;\n}\n\n.date-show {\n width: 32%;\n padding: 0 20px 0 0;\n text-align: left;\n border-right: 1px solid #cfd7df;\n}\n\n.color-change {\n color: #6f7c87;\n}\n\n.semi-bold {\n font-weight: 500;\n}\n\nspan.slider.medium .toggle-switch input:checked+.slider {\n background-color: green !important;\n}\n\n.fw-btn--secondary {\n border-color: white;\n}\n\n.rule-top {\n margin: 0 0 20px;\n border-radius: 4px;\n background-color: #fff;\n box-shadow: 0 0 1px 0 #acb6be, 0 2px 6px 0 rgba(22, 29, 37, .05);\n}\n\n/* popup show */\n.list-icon {\n width: 5px;\n height: 5px;\n /* display: inline-block; */\n border-radius: 50%;\n border: 3px solid #2c5cc5;\n /* margin-left: 50px; */\n /* top: 10px; */\n margin-left: 50px;\n position: relative;\n}\n\n/* .addSpace {\n display: flex;\n gap: 5px;\n} */\n.SummaryKey {\n font-weight: 600;\n}\n\n.SummaryValue {\n color: #007958;\n}\n\n.dropdown-menu {\n min-width: 140px;\n padding: 8px;\n top: 5px;\n left: unset;\n right: 125px;\n}\n\n.note-wrapper {\n display: flex;\n width: 500px;\n margin-top: 15px;\n border: 1px solid #ebeff3;\n padding: 10px 15px;\n position: relative;\n}\n\n.note-icon {\n width: 14px;\n height: 15px;\n /* display: inline-block; */\n background: #ff9d00;\n text-align: center;\n border-radius: 2px;\n margin-top: 1px;\n}\n\n.summary_text {\n margin-top: 30px;\n padding: 0 30px 20px;\n border: 1px solid #dadfe3;\n border-radius: 4px;\n position: relative;\n}\n\n.filterCondition {\n position: absolute;\n padding: 2px 0;\n top: -15px;\n width: 52px;\n left: 50%;\n text-align: center;\n transform: translateX(-50%);\n border: 1px solid #dadfe3;\n border-radius: 16px;\n background-color: #fff;\n z-index: 9;\n}\n\n.deleteNewCondition {\n position: absolute;\n /* top: 27px; */\n right: 17px;\n width: 25px;\n height: 25px;\n text-align: center;\n transition: all .3s;\n /* opacity: 0; */\n border-radius: 50%;\n}\n.deleteNewCondition:hover {\n cursor: pointer;\n background-color: red;\n color: white\n}\n\n.components_switcher {\n width: 120px;\n height: 37px;\n position: relative;\n background-color: white;\n left: 42%;\n border-radius: 24px;\n border: 1px solid #dadfe3;\n transition: all .5s;\n}\n.toggle {\n top: 2px;\n width: 62px;\n height: 15px;\n padding: 7px 4px;\n line-height: 15px;\n position: absolute;\n border-radius: 24px;\n border: 1px solid #2c5cc5;\n box-shadow: 0 2px 4px 0 rgba(0, 0, 0, .15);\n transition: all .5s;\n background-image: linear-gradient(-180deg, #fff 3%, #f5f7f9 96%);\n}\n\n.andOrSwitcher{\n width: 15%;\n height: 100%;\n padding-top: 9px;\n font-weight: 400;\n border-radius: 15px;\n transition: all .5s;\n cursor: pointer;\n\n}\n\n.switch-btn {\n padding: 10px 30px;\n border-radius: 50px; /* This makes the button oval */\n border: 2px solid #007BFF; /* Blue border */\n background-color: #fff; /* White background */\n font-size: 16px;\n cursor: pointer;\n transition: all 0.3s ease; /* Smooth transition */\n font-weight: bold;\n}\n\n.switch-btn.and {\n color: #28a745; /* Green for AND */\n}\n\n.switch-btn.or {\n color: #dc3545; /* Red for OR */\n}\n\n.switch-btn:hover {\n background-color: #f0f0f0; /* Light gray background on hover */\n}\n\n.switch-btn:focus {\n outline: none; /* Remove outline on focus */\n}\n\nwhat csss in the html apply as inline with existing css and add this to inline"},{"assistant_initiates":false,"asst_text":"Certainly! Here's your complete React JSX snippet with **all styles inlined** and **no CSS class names** remaining. This means every referenced CSS rule from your provided CSS gets applied via the `style` prop inline.\n\n```jsx\nimport React from 'react';\nimport moment from 'moment';\n\nfunction RuleTop({ rule, ind, ListConditions, handleEditPage, showMenuList, menuList, MenuList, agentsList }) {\n return (\n \n
\n {rule.position}\n .\n {rule.name}\n
\n\n
\n

{ListConditions(rule)}

\n\n
\n {rule.active ? : }\n
\n\n handleEditPage(rule)}\n >\n Edit\n \n\n
\n showMenuList(ind)}\n >\n \n \n
\n {menuList ? : null}\n
\n\n \n \n Last Modified:\n {moment(rule.updated_at).fromNow()}\n \n\n \n By :\n \n {agentsList.map((e) => {\n if (e.value === rule.last_updated_by) return e.text;\n return null;\n })}\n \n \n\n \n Impacted tickets (Last 7 days):\n \n {rule.affected_tickets_count === 0 ? '--' : rule.affected_tickets_count}\n \n \n \n \n );\n}\n\nexport default RuleTop;\n```\n\n---\n\n### Explanation:\n\n- All `className`s were removed and replaced by their CSS rules applied via `style` prop.\n- Maintained existing inline styles and merged new ones from the CSS you provided.\n- Added some minor spacing (like `gap`, `marginTop`) for improved spacing since your original CSS relied on classes.\n- Buttons and spans have cursor/padding/font colour applied inline for clarity.\n- The mapped `.semi-bold` styles use `fontWeight: 500`.\n- Used `moment(...)` as in your original.\n- `agentsList.map` returns `null` for non-matching elements to avoid returning `undefined` in React render.\n- Make sure your external components like `FwToggle`, `FwButton`, and `FwIcon` work properly with inline styles (they usually do).\n\n---\n\nIf you want me to also inline the toggle or button styles from your CSS or adapt those components, let me know. Otherwise, this is the fully inline style conversion of your provided snippet!","behavior":"degenerate_repetition","conversation_hash":"6fcabf3c450fc8d1ac360b0922a89b99","conversation_redacted":false,"conversation_toxic":false,"country":"India","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"English","model":"gpt-4.1-mini-2025-04-14","n_chars":5051,"n_turns_in_conversation":12,"n_words":519,"source_row_offset":28754,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:51:03 GMT","turn_id":"edbc6fcf8c0a995829cd5c6d","turn_index":1,"user_text":"yes need that"},{"assistant_initiates":false,"asst_text":"Sure! Here's just the **return JSX part** of your component with all styles fully inlined and no class names, ready to paste inside your render or functional component:\n\n```jsx\nreturn (\n \n
\n {rule.position}\n .\n {rule.name}\n
\n\n
\n

{ListConditions(rule)}

\n\n
\n {rule.active ? : }\n
\n\n handleEditPage(rule)}\n >\n Edit\n \n\n
\n showMenuList(ind)}\n >\n \n \n
\n {menuList ? : null}\n
\n\n \n \n Last Modified:\n {moment(rule.updated_at).fromNow()}\n \n\n \n By :\n \n {agentsList.map((e) => {\n if (e.value === rule.last_updated_by) return e.text;\n return null;\n })}\n \n \n\n \n Impacted tickets (Last 7 days):\n \n {rule.affected_tickets_count === 0 ? '--' : rule.affected_tickets_count}\n \n \n \n \n);\n```\n\nLet me know if you want me to help convert anything else!","behavior":"degenerate_repetition","conversation_hash":"6fcabf3c450fc8d1ac360b0922a89b99","conversation_redacted":false,"conversation_toxic":false,"country":"India","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"English","model":"gpt-4.1-mini-2025-04-14","n_chars":3719,"n_turns_in_conversation":12,"n_words":360,"source_row_offset":28755,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:51:03 GMT","turn_id":"dc65e1976fbb063f7e70de69","turn_index":2,"user_text":"no just need that return part"},{"assistant_initiates":false,"asst_text":"Looking over the CSS you\u2019ve provided, here\u2019s what applies regarding **Edit** and **Delete popup/menu** elements:\n\n---\n\n### Edit Button\n- There is **no explicit CSS class named or styled \"Edit\" button** here.\n- Your edit button in the React snippet was a `\n```\n\nSo only the dropdown \"more\" button appears, which opens the menu with Edit/Clone/Delete.\n\n---\n\n### Step 2: Add CSS for dropdown menu animation\n\nAdd the following CSS somewhere in your global stylesheet (or as a CSS module):\n\n```css\n.dropdown-menu {\n position: absolute;\n background: white;\n box-shadow: 0 4px 12px rgba(0,0,0,0.1);\n border-radius: 4px;\n padding: 8px 0;\n margin-top: 8px;\n min-width: 140px;\n right: 0;\n top: 100%;\n list-style: none;\n opacity: 0;\n transform: translateY(-10px);\n pointer-events: none;\n transition: opacity 0.3s ease, transform 0.3s ease;\n z-index: 1000;\n}\n\n.dropdown-menu.show {\n opacity: 1;\n transform: translateY(0);\n pointer-events: auto;\n}\n\n/* Style the list items */\n.dropdown-menu li {\n display: flex;\n align-items: center;\n gap: 8px;\n padding: 8px 16px;\n cursor: pointer;\n color: #333;\n font-weight: 500;\n transition: background-color 0.2s ease;\n}\n\n.dropdown-menu li:hover {\n background-color: #f5f7f9;\n}\n```\n\n---\n\n### Step 3: Modify your React component to toggle `.show` class for animation\n\nAdd logic to toggle menu visibility and apply `.show` class for animation:\n\n```jsx\nimport React, { useState, useRef, useEffect } from \"react\";\n// ... your imports\n\nexport default function AutomationCart({ ind, menuList, rule, agentsList, showMenuList, handleEditPage }) {\n const [dropdownVisible, setDropdownVisible] = useState(false);\n const menuRef = useRef(null);\n\n // Toggle dropdown visibility when clicking the \"more\" button\n const toggleDropdown = () => setDropdownVisible(!dropdownVisible);\n\n // Optional: close dropdown when clicking outside\n useEffect(() => {\n function handleClickOutside(event) {\n if (menuRef.current && !menuRef.current.contains(event.target)) {\n setDropdownVisible(false);\n }\n }\n document.addEventListener(\"mousedown\", handleClickOutside);\n return () => document.removeEventListener(\"mousedown\", handleClickOutside);\n }, []);\n\n // ... ListConditions same as before\n\n return (\n <>\n \n
\n {rule.position}\n .\n {rule.name}\n
\n\n \n

\n {ListConditions(rule)}\n

\n\n
\n {rule.active ? (\n \n ) : (\n \n )}\n
\n\n {/* Removed Edit button here */}\n\n
\n \n \n \n
\n\n {/* Dropdown menu with animation */}\n
\n
    \n
  • { handleEditPage(rule); setDropdownVisible(false); }}>\n \n
    Edit
    \n
    • \n {\n /* Implement Clone logic here */\n setDropdownVisible(false);\n }}\n >\n \n
    Clone
    \n \n {\n /* Implement Delete logic here */\n setDropdownVisible(false);\n }}\n >\n \n
    Delete
    \n \n
\n
\n \n\n {/* Time Show section unchanged */}\n \n \n Last Modified:\n \n {moment(rule.updated_at).fromNow()}\n \n \n\n \n By :\n \n {agentsList.map((e) => {\n if (e.value === rule.last_updated_by) return e.text;\n return null;\n })}\n \n \n\n \n \n Impacted tickets (Last 7 days):\n \n \n {rule.affected_tickets_count === 0\n ? \"--\"\n : rule.affected_tickets_count}\n \n \n \n \n \n );\n}\n```\n\n---\n\n### Explanation:\n\n- Removed the separate `\"Edit\"` button.\n- The dropdown menu (`
    `) is positioned absolutely relative to the parent flex container.\n- When you click the `more-vertical` button, dropdown toggles visibility.\n- Dropdown fades/slides down smoothly using CSS transitions on opacity & translateY.\n- Clicking outside dropdown closes it.\n- Clicking any item closes the dropdown and invokes the relevant handler.\n- You can add more logic to `Clone` and `Delete` if you want.\n\n---\n\nIf your project supports CSS-in-JS, just add the CSS styles in a global CSS file, or via styled-components/emotion as appropriate.\n\n---\n\nLet me know if you want me to generate the CSS in JS inline styles form too!","behavior":"degenerate_repetition","conversation_hash":"6fcabf3c450fc8d1ac360b0922a89b99","conversation_redacted":false,"conversation_toxic":false,"country":"India","empty_output":false,"evidence_codes":[],"label":"absent","label_present":false,"label_qualified":false,"label_source":"Final dense release","language":"English","model":"gpt-4.1-mini-2025-04-14","n_chars":15943,"n_turns_in_conversation":12,"n_words":1527,"source_row_offset":28757,"source_shard":"turns-00073.parquet","timestamp":"Sat, 26 Apr 2025 03:51:03 GMT","turn_id":"0c4d1efd4bc0d26692917d3e","turn_index":4,"user_text":"import moment from \"moment\";\nimport React from \"react\";\nimport { FwButton, FwToggle, FwTab, FwTabPanel, FwIcon } from \"@freshworks/crayons/react\";\n\n\nfunction MenuList({ Index }) {\n return (\n <>\n
      \n
    • Edit
      • \n
    • Clone
      • \n
    • Delete
      • \n
    \n \n )\n\n}\n\nfunction htmlToText(html) {\n var temp = document.createElement('div');\n temp.innerHTML = html;\n return temp.textContent; // Or return temp.innerText if you need to return only visible text. It's slower.\n}\n\n\nexport default function AutomationCart({ ind, menuList, rule, agentsList, showMenuList, handleEditPage }) {\n\n const ListConditions = (element) => {\n\n const valuesOfCondStr = Object.values(element.summary.conditions).map(e => {\n if (Array.isArray(e) && e.length) {\n return htmlToText(e[0]);\n }\n return e;\n }).join(\" \");\n\n const actionsToStr = element.summary.actions.map((action, index) => (\n htmlToText(action)\n )).join(\" \")\n return [valuesOfCondStr, actionsToStr].join(\" \")\n }\n\n // const changePage = (event) => {\n // const res = pagination(ticketCreationRules, event.detail.page);\n // setData(res);\n // }\n // const showMenuList = (ind) => {\n // setMenuList(true);\n // let copyData = [...data];\n // copyData = copyData.map(e => {\n // e.isClicked = false;\n // return e;\n // })\n // const element = { ...copyData[ind] };\n // element.isClicked = true;\n // copyData[ind] = element;\n // setData(copyData);\n // }\n\n // React.useEffect(() => {\n // if (ticketCreationRules.length) {\n // const res = pagination(ticketCreationRules);\n // setData(res);\n // }\n // }, [ticketCreationRules])\n\n return <>\n \n {/*
    \n
    {rule.position}.{rule.name}
    \n
    \n

    {ListConditions(rule)}

    \n
    {rule.active ? : }\n
    \n \n
    showMenuList(ind)}>\n
    \n {menuList ? : null}\n
    \n
    \n
    Last Modified:\n {moment(rule.updated_at).fromNow()}
    \n
    By :{agentsList.map(e => {\n if (e.value === rule.last_updated_by)\n return e.text\n })}
    \n
    Impacted tickets (Last 7 days):{(rule.affected_tickets_count === 0) ? '--' : rule.affected_tickets_count}
    \n
    \n
    */}\n\n\n \n
    \n {rule.position}\n .\n {rule.name}\n
    \n\n
    \n

    {ListConditions(rule)}

    \n\n
    \n {rule.active ? : }\n
    \n\n handleEditPage(rule)}\n >\n Edit\n \n\n
    \n showMenuList(ind)}\n >\n \n \n
    \n {menuList ? : null}\n
    \n\n \n \n Last Modified:\n {moment(rule.updated_at).fromNow()}\n \n\n \n By :\n \n {agentsList.map((e) => {\n if (e.value === rule.last_updated_by) return e.text;\n return null;\n })}\n \n \n\n \n Impacted tickets (Last 7 days):\n \n {rule.affected_tickets_count === 0 ? '--' : rule.affected_tickets_count}\n \n \n \n \n\n\n\n \n}\n\n\nneed animation and also remoe Edit Button not in the dropdown add animation css for that menu"}],"shard":{"index":73,"name":"turns-00073.parquet","rows":38923}}