\u6846\u67b6\u4f9d\u8cf4<\/strong><\/td>PyTorch\uff08\u81ea\u52d5\u5b89\u88dd\uff09<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n\u5efa\u7acb YOLO \u865b\u64ec\u74b0\u5883<\/h2>\n\n\n\n \u70ba\u4e86\u4fdd\u6301\u958b\u767c\u74b0\u5883\u4e7e\u6de8\u3001\u907f\u514d\u8207\u5176\u4ed6 Python \u5c08\u6848\u7684\u5957\u4ef6\u885d\u7a81\uff0c\u5efa\u8b70\u5148\u5efa\u7acb\u4e00\u500b\u5c08\u5c6c\u7684\u865b\u64ec\u74b0\u5883\uff1a<\/p>\n\n\n\n
python -m venv yoloenv<\/code><\/code><\/pre>\n\n\n\n\u63a5\u8457\u555f\u7528\u74b0\u5883\uff1a<\/p>\n\n\n\n
# macOS \/ Linux\nsource yoloenv\/bin\/activate\n\n# Windows\nyoloenv\\Scripts\\activate<\/code><\/pre>\n\n\n\n(yoloenv)<\/code> \u6642\uff0c\u5c31\u8868\u793a\u865b\u64ec\u74b0\u5883\u5df2\u7d93\u555f\u7528\u6210\u529f\u3002<\/p>\n\n\n\n\u5b89\u88dd YOLO \u5957\u4ef6<\/h2>\n\n\n\n Ultralytics \u63d0\u4f9b\u5b98\u65b9\u7684 YOLO \u5de5\u5177\u5305\uff0c\u5176\u4e2d\u5df2\u5305\u542b\u8a72\u6a21\u578b\u6a21\u578b\u8207\u547d\u4ee4\u5217\u4ecb\u9762\u3002\u53ea\u9700\u4e00\u884c\u6307\u4ee4\u5373\u53ef\u5b89\u88dd\uff1a<\/p>\n\n\n\n
pip install ultralytics<\/code><\/pre>\n\n\n\n\u5b89\u88dd\u5b8c\u6210\u5f8c\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u6307\u4ee4\u6aa2\u67e5\u662f\u5426\u6210\u529f\uff1a<\/p>\n\n\n\n
yolo version<\/code><\/pre>\n\n\n\n\u82e5\u986f\u793a\u7248\u672c\u865f\u70ba\u5982 8.3.x\uff0c\u5c31\u4ee3\u8868\u5b89\u88dd\u5b8c\u6210 \u3002<\/p>\n\n\n\n
Code<\/h2>\n\n\n\n \u5728 Python \u4e2d\u57f7\u884c\u4ee5\u4e0b\u7a0b\u5f0f\u78bc\uff0c\u5982\u679c\u6210\u529f\u8f09\u5165\u6a21\u578b\u4e14\u6c92\u6709\u5831\u932f\uff0c\u5247\u8aaa\u660e\u74b0\u5883\u57fa\u672c\u914d\u7f6e\u6b63\u78ba\u3002<\/p>\n\n\n\n
# ===============================\n# YOLO Complete Python Example\n# ===============================\n\nimport os\nfrom ultralytics import YOLO\n\n# Set up project folder\nproject_dir = \"\/Users\/kdm4\/Desktop\/yoloenv\/main\/outputs\" # Customize the save folder\nos.makedirs(project_dir, exist_ok=True) # Automatically create if it doesn't exist\n\n# Load YOLO pre-trained model\n# This is the nano version \u2013 lightweight and fast\nmodel = YOLO(\"yolo11n.pt\")\n\n# Run inference on an image and save results\nimage_source = \"https:\/\/ultralytics.com\/images\/bus.jpg\"\n\nresults = model(\n image_source,\n save=True, # Automatically save the output\n project=project_dir, # Specify the save location\n name=\"demo\", # Subfolder name\n)\n\n# Display inference results\nresults[0].show() # Opens a window showing detection boxes\n\n# Print bounding box details\nfor i, box in enumerate(results[0].boxes):\n cls_id = int(box.cls) # Class index\n conf = float(box.conf) # Confidence score\n xyxy = box.xyxy[0].tolist() # Bounding box coordinates [x1, y1, x2, y2]\n print(f\"Object {i+1}: Class {cls_id}, Confidence {conf:.2f}, BBox {xyxy}\")\n\n# Show save directory\nprint(f\"Results saved to: {results[0].save_dir}\")<\/code><\/pre>\n\n\n\n\u7a0b\u5f0f\u8aaa\u660e<\/h2>\n\n\n\n \u5c0e\u5165\u5957\u4ef6 :<\/strong><\/p>\n\n\n\nimport os\nfrom ultralytics import YOLO<\/code><\/pre>\n\n\n\n\nos<\/code> \u7528\u4f86\u5efa\u7acb\u8cc7\u6599\u593e\u6216\u64cd\u4f5c\u6a94\u6848\u8def\u5f91\u3002<\/li>\n\n\n\nultralytics.YOLO<\/code> \u662f\u8a72\u6a21\u578b\u7684 Python \u6a21\u7d44\uff0c\u7528\u4f86\u8f09\u5165\u6a21\u578b\u3001\u9032\u884c\u63a8\u8ad6\u3001\u7ba1\u7406\u7d50\u679c\u3002<\/li>\n<\/ul>\n\n\n\n\u8a2d\u5b9a\u5c08\u6848\u8cc7\u6599\u593e :<\/strong><\/p>\n\n\n\nproject_dir = \"\/Users\/kdm4\/Desktop\/yoloenv\/main\/outputs\"\nos.makedirs(project_dir, exist_ok=True)<\/code><\/pre>\n\n\n\n\nproject_dir<\/code>\uff1a\u6307\u5b9a\u8a72\u6a21\u578b\u5132\u5b58\u63a8\u8ad6\u7d50\u679c\u7684\u4e3b\u8cc7\u6599\u593e\u3002<\/li>\n\n\n\nos.makedirs(..., exist_ok=True)<\/code>\uff1a\u5982\u679c\u8cc7\u6599\u593e\u4e0d\u5b58\u5728\u6703\u81ea\u52d5\u5efa\u7acb\uff0c\u907f\u514d\u7a0b\u5f0f\u5831\u932f\u3002<\/li>\n<\/ul>\n\n\n\n\u8f09\u5165\u6a21\u578b :<\/strong><\/p>\n\n\n\nmodel = YOLO(\"yolo11n.pt\")<\/code><\/pre>\n\n\n\n\nyolo11n.pt<\/code> \u662f YOLO11 nano \u7248<\/strong>\uff0c\u8f15\u91cf\u4e14\u5feb\u901f\u3002<\/li>\n\n\n\n\u9019\u884c\u7a0b\u5f0f\u6703\u8f09\u5165\u6a21\u578b\u5230 Python\uff0c\u6e96\u5099\u9032\u884c\u63a8\u8ad6\u3002<\/li>\n<\/ul>\n\n\n\n\u63a8\u8ad6\u5716\u7247\u4e26\u81ea\u52d5\u5132\u5b58 :<\/strong><\/p>\n\n\n\nresults = model(\n \"https:\/\/ultralytics.com\/images\/bus.jpg\",\n save=True,\n project=project_dir,\n name=\"demo\",\n)<\/code><\/pre>\n\n\n\n\n\"https:\/\/ultralytics.com\/images\/bus.jpg\"<\/code>\uff1a\u63a8\u8ad6\u7684\u5716\u7247\uff0c\u53ef\u4ee5\u662f\u672c\u5730\u6a94\u6848\u6216\u7db2\u8def\u5716\u7247\u3002<\/li>\n\n\n\nsave=True<\/code>\uff1a\u81ea\u52d5\u628a\u7d50\u679c\u5b58\u6210\u5e36\u6a19\u8a3b\u7684\u5716\u7247\u3002<\/li>\n\n\n\nproject<\/code>\uff1a\u5132\u5b58\u4e3b\u8cc7\u6599\u593e\u3002<\/li>\n\n\n\nname<\/code>\uff1a\u5efa\u7acb\u5b50\u8cc7\u6599\u593e\u540d\u7a31\uff0c\u907f\u514d\u591a\u6b21\u57f7\u884c\u8986\u84cb\u820a\u7d50\u679c\u3002<\/li>\n<\/ul>\n\n\n\n\u986f\u793a\u5716\u7247\u7d50\u679c :<\/strong><\/p>\n\n\n\nresults[0].show()<\/code><\/pre>\n\n\n\n\n\u6253\u958b\u4e00\u500b\u8996\u7a97\uff0c\u986f\u793a\u63a8\u8ad6\u5f8c\u7684\u5716\u7247\uff0c\u6846\u51fa\u5075\u6e2c\u5230\u7684\u7269\u4ef6\u4e26\u6a19\u793a\u985e\u5225\u8207\u4fe1\u5fc3\u5206\u6578\u3002<\/li>\n<\/ul>\n\n\n\n\u5217\u5370\u5075\u6e2c\u6846\u8cc7\u6599 :<\/strong><\/p>\n\n\n\nfor i, box in enumerate(results[0].boxes):\n cls_id = int(box.cls)\n conf = float(box.conf)\n xyxy = box.xyxy[0].tolist()\n print(f\"Object {i+1}: Class {cls_id}, Confidence {conf:.2f}, BBox {xyxy}\")<\/code><\/pre>\n\n\n\n\nresults[0].boxes<\/code>\uff1a\u6240\u6709\u5075\u6e2c\u6846\u7684\u96c6\u5408\uff0c\u6bcf\u500b\u7269\u4ef6\u7684\u8a73\u7d30\u8cc7\u8a0a\u90fd\u5728\u9019\u88e1\u3002<\/li>\n\n\n\ncls_id<\/code>\uff1a\u7269\u4ef6\u985e\u5225\u7de8\u865f\u3002<\/li>\n\n\n\nconf<\/code>\uff1a\u6a21\u578b\u5c0d\u8a72\u7269\u4ef6\u7684\u4fe1\u5fc3\u5206\u6578\uff080~1\uff09\u3002<\/li>\n\n\n\nxyxy<\/code>\uff1a\u908a\u754c\u6846\u5ea7\u6a19 [x1, y1, x2, y2]<\/code>\u3002<\/li>\n\n\n\n\u9019\u6bb5\u7a0b\u5f0f\u6703\u9010\u4e00\u5217\u5370\u6bcf\u500b\u7269\u4ef6\u7684\u8cc7\u8a0a\u5230\u7d42\u7aef\u6a5f\u3002<\/li>\n<\/ul>\n\n\n\n\u986f\u793a\u5132\u5b58\u8def\u5f91 :<\/strong><\/p>\n\n\n\nprint(f\"Results saved to: {results[0].save_dir}\")<\/code><\/pre>\n\n\n\n\nresults[0].save_dir<\/code>\uff1a\u63a8\u8ad6\u7d50\u679c\u5132\u5b58\u7684\u8cc7\u6599\u593e\u8def\u5f91\uff0c\u65b9\u4fbf\u4f60\u6253\u958b\u6aa2\u8996\u3002<\/li>\n<\/ul>\n\n\n\n\u57f7\u884c\u5f8c\u4f60\u6703\u770b\u5230 :<\/strong><\/p>\n\n\n\n\n\u5f48\u51fa\u8996\u7a97<\/strong>\uff1a\u5716\u7247\u4e2d\u6240\u6709\u5075\u6e2c\u5230\u7684\u7269\u4ef6\u90fd\u6709\u6a19\u8a3b\u6846\u8207\u985e\u5225\u540d\u7a31\u3002<\/li>\n\n\n\n\u7d42\u7aef\u6a5f\u8f38\u51fa<\/strong>\uff1a\u6bcf\u500b\u5075\u6e2c\u7269\u4ef6\u7684\u985e\u5225\u3001\u4fe1\u5fc3\u5206\u6578\u8207\u5ea7\u6a19\u3002<\/li>\n\n\n\n\u8cc7\u6599\u593e\u7d50\u679c<\/strong>\uff1aoutputs\/demo\/<\/code> \u5167\u6703\u6709\u6a19\u8a3b\u5f8c\u7684\u5716\u7247\uff0c\u65b9\u4fbf\u4fdd\u5b58\u6216\u5206\u6790\u3002<\/li>\n<\/ul>\n\n\n\n\u6e2c\u8a66\u5716\u7247\u4f86\u6e90\uff1aUltralytics<\/code> \u5b98\u65b9\u793a\u7bc4\u5f71\u50cf\u6a94 bus.jpg <\/figcaption><\/figure>\n\n\n\n\u7d50\u8ad6<\/h2>\n\n\n\n YOLO11<\/a>\uff0c\u4e0d\u53ea\u662f YOLO \u7cfb\u5217\u7684\u9032\u5316\uff0c\u66f4\u662f\u4e00\u5834\u5373\u6642\u7269\u4ef6\u5075\u6e2c\u7684\u9769\u547d\u3002<\/strong><\/p>\n\n\n\n\u5b83\u50cf\u662f\u4e00\u9053\u9583\u96fb\uff0c\u4ee5\u9a5a\u4eba\u7684\u901f\u5ea6\u5283\u7834\u8996\u89ba\u8655\u7406\u7684\u5929\u7a7a\uff0c\u540c\u6642\u53c8\u4ee5\u9df9\u773c\u822c\u7684\u7cbe\u6e96\u9396\u5b9a\u6bcf\u4e00\u500b\u7d30\u7bc0\u3002\u7121\u8ad6\u662f\u8857\u982d\u76e3\u63a7\u3001\u667a\u6167\u96f6\u552e\uff0c\u9084\u662f\u81ea\u99d5\u8eca\u7684\u5373\u6642\u5224\u8b80\uff0cYOLO \u90fd\u80fd\u5728\u6beb\u79d2\u4e4b\u9593\u5b8c\u6210\u8fa8\u8b58\uff0c\u70ba AI \u61c9\u7528\u6ce8\u5165\u524d\u6240\u672a\u6709\u7684\u6548\u7387\u8207\u53ef\u9760\u6027\u3002<\/p>\n\n\n\n
\u66f4\u4ee4\u4eba\u9a5a\u8277\u7684\u662f\uff0c\u8a72\u6a21\u578b\u4e0d\u50c5\u300c\u770b\u5f97\u5feb\u3001\u770b\u5f97\u6e96\u300d\uff0c\u9084\u80fd\u300c\u770b\u5f97\u591a\u300d\u2014\u2014\u5f9e\u7269\u4ef6\u5075\u6e2c\u3001\u8a9e\u7fa9\u5206\u5272\u3001\u59ff\u614b\u4f30\u8a08\uff0c\u5230\u5716\u50cf\u5206\u985e\uff0c\u4e00\u500b\u6a21\u578b\u5c31\u80fd\u641e\u5b9a\u591a\u7a2e\u4efb\u52d9\uff0c\u5fb9\u5e95\u985b\u8986\u50b3\u7d71\u96fb\u8166\u8996\u89ba\u7684\u5de5\u4f5c\u6d41\u7a0b\u3002<\/p>\n\n\n\n
\u5c0d\u65bc\u7814\u7a76\u4eba\u54e1\uff0c\u5b83\u662f\u63a2\u7d22\u672a\u4f86\u7684\u5229\u5668\uff1b\u5c0d\u65bc\u958b\u767c\u8005\uff0c\u5b83\u662f\u5feb\u901f\u843d\u5730\u7684\u6a4b\u6a11\uff1b\u5c0d\u65bc\u4f01\u696d\uff0c\u5b83\u662f\u667a\u6167\u8f49\u578b\u7684\u52a0\u901f\u5668\u3002\u5728\u9019\u500b AI \u9ad8\u901f\u6f14\u9032\u7684\u6642\u4ee3\uff0c\u8a72\u6a21\u578b\u4e0d\u53ea\u662f\u6280\u8853\u7684\u7a81\u7834\uff0c\u66f4\u662f\u667a\u6167\u8996\u89ba\u666e\u53ca\u5316\u7684\u95dc\u9375\u4e00\u6b65\u2014\u2014\u8b93\u6bcf\u4e00\u500b\u8a2d\u5099\u90fd\u80fd\u300c\u770b\u898b\u300d\u4e16\u754c\uff0c\u8b93\u6bcf\u4e00\u500b\u61c9\u7528\u90fd\u80fd\u300c\u7406\u89e3\u300d\u73fe\u5be6\u3002<\/p>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
YOLO11\uff0c\u4f5c\u70ba Ultralytics \u63a8\u51fa\u7684\u6700\u65b0\u4e00\u4ee3\u5373\u6642\u7269\u4ef6\u5075\u6e2c\u6a21\u578b\uff0c\u6b63\u6380\u8d77\u96fb\u8166\u8996\u89ba\u9818\u57df\u7684\u65b0\u4e00\u6ce2\u9769\u547d\u3002\u5b83 […]<\/p>\n","protected":false},"author":1,"featured_media":4086,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[93],"tags":[92,27,21,91,44,9,86,11],"class_list":["post-4081","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","tag-ai","tag-c","tag-ide","tag-ollama","tag-programming-language","tag-python","tag-rtos","tag-tutorial"],"blocksy_meta":[],"_links":{"self":[{"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/posts\/4081","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/comments?post=4081"}],"version-history":[{"count":15,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/posts\/4081\/revisions"}],"predecessor-version":[{"id":4098,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/posts\/4081\/revisions\/4098"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/media\/4086"}],"wp:attachment":[{"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/media?parent=4081"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/categories?post=4081"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saludpcb.com\/zh\/wp-json\/wp\/v2\/tags?post=4081"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"YOLO11\"](\"https:\/\/saludpcb.com\/zh\/wp-content\/uploads\/2025\/11\/YOLO11-Is-Insane-The-Fastest-and-Most-Accurate-AI-Detection-Model-Yet.jpg\" "\\"\\"")
<\/figure>\n\n\n\n