{"full_name":"ultralytics/yolov5","owner":"ultralytics","name":"yolov5","shard":"1","url":"https://github.com/ultralytics/yolov5","description":"Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.","homepage":"https://docs.ultralytics.com/yolov5/","topics":["yolov5","object-detection","pytorch","onnx","coreml","tflite","yolo","deep-learning","ultralytics","computer-vision","image-classification","inference","instance-segmentation","model-export","model-training"],"tag_pages":["computer-vision","coreml","deep-learning","image-classification","inference","instance-segmentation","object-detection","onnx","pytorch","tflite","yolo"],"language":"Python","license":"AGPL-3.0","avatar":"https://avatars.githubusercontent.com/u/26833451?v=4","created_at":"2020-05-18T03:45:11Z","pushed_at":"2026-11-07T16:59:45Z","metrics":{"stars":58272,"forks":17434,"watchers":379,"issues":9428,"prs":3071,"releases":10,"issues_open":24,"issues_closed":9404,"prs_open":5,"prs_closed":725,"prs_merged":2341,"discussions":922},"growth":{"day":{"stars":5,"forks":2,"base_day":"2026-11-15"},"week":{"stars":17,"forks":-5,"base_day":"2026-11-09"},"month":{"stars":92,"forks":-22,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[57970,57973,57974,57982,57989,57989,57991,57995,58005,58008,58015,58020,58033,58041,58047,58056,58063,58066,58069,58078,58083,58089,58091,58092,58097,58101,58103,58103,58104,58106,58107,58108,58113,58115,58128,58134,58143,58151,58161,58170,58177,58180,58179,58181,58183,58184,58185,58184,58206,58213,58220,58227,58231,58233,58237,58243,58247,58247,58246,58251,58255,58258,58260,58264,58262,58265,58267,58272],"forks":[17469,17469,17466,17465,17465,17468,17469,17468,17467,17468,17471,17470,17469,17467,17469,17469,17467,17466,17461,17462,17462,17461,17461,17462,17461,17458,17460,17459,17459,17460,17461,17461,17461,17457,17456,17460,17459,17457,17460,17459,17459,17456,17457,17458,17457,17457,17457,17457,17456,17455,17452,17447,17446,17443,17442,17442,17445,17445,17445,17447,17439,17439,17437,17435,17435,17431,17432,17434],"watchers":[380,381,381,381,381,381,381,381,381,381,380,380,380,380,380,380,380,380,380,380,380,380,381,381,381,381,381,381,381,381,381,381,381,381,382,382,382,382,382,382,382,382,382,382,382,382,382,382,383,378,378,378,378,378,378,378,378,378,378,378,null,null,378,378,378,378,379,379],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,24,24,24,24,24,24],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,0,0,2,2,3,5]},"boards":{},"same_owner":[{"full_name":"ultralytics/ultralytics","name":"ultralytics","shard":"1","boards":{}}],"issues":[{"number":251,"title":"TFLite, ONNX, CoreML, TensorRT Export","comments":407,"created_at":"2020-06-30T22:59:28Z"},{"number":36,"title":"Load YOLOv5 from PyTorch Hub ⭐","comments":320,"created_at":"2020-06-11T04:14:04Z"},{"number":12,"title":"Train Custom Data Tutorial ⭐","comments":214,"created_at":"2020-06-03T17:32:57Z"},{"number":607,"title":"Hyperparameter Evolution","comments":204,"created_at":"2020-08-02T19:28:35Z"},{"number":475,"title":"Multi-GPU Training 🌟","comments":111,"created_at":"2020-07-22T11:36:27Z"},{"number":318,"title":"Model Ensembling Tutorial","comments":108,"created_at":"2020-07-07T22:39:30Z"},{"number":9627,"title":"NVIDIA Jetson Nvidia Jetson Nano, Xavier NX, Orin Deployment tutorial","comments":78,"created_at":"2022-09-28T06:25:43Z"},{"number":6998,"title":"YOLOv5 (6.0/6.1) brief summary","comments":65,"created_at":"2022-03-16T04:39:06Z"}],"discussions":[{"number":13863,"title":"Create custom dataset from pre-existing datasets","comments":2,"category":"Show and tell","created_at":"2026-08-17T22:29:32Z"},{"number":13722,"title":"cv2.cuda_GpuMat()","comments":0,"category":"Q&A","created_at":"2026-03-16T05:51:38Z"},{"number":13639,"title":"Synthetic YOLO Dataset Generator","comments":0,"category":"Show and tell","created_at":"2025-08-03T22:22:52Z"},{"number":13636,"title":"CUDNN ERROR in Blackwell GPU","comments":0,"category":"Q&A","created_at":"2025-07-30T06:38:44Z"},{"number":13569,"title":"Generating Precision, Recall, and mAP@0.5 Metrics for Each Category in Faster R-CNN Using Detectron2 Object Detection Models","comments":0,"category":"Q&A","created_at":"2025-04-20T11:31:16Z"},{"number":13557,"title":"Problem with incorporating Python in visual studio code to employ YOLOv5 and practice object detection","comments":1,"category":"Q&A","created_at":"2025-04-08T09:33:15Z"},{"number":13538,"title":"How can I add more hyperparameters in YOLOv5 Genetic algorithm to evolve them?","comments":0,"category":"General","created_at":"2025-03-20T11:20:32Z"},{"number":13518,"title":"font and color of the annotation box","comments":1,"category":"Q&A","created_at":"2025-02-24T13:16:40Z"}],"latest_release":{"name":"v7.0 - YOLOv5 SOTA Realtime Instance Segmentation","tag":"v7.0","published_at":"2022-11-22T15:29:09Z","body":"[assets]: https://github.com/ultralytics/yolov5/releases\r\n[previous]: https://github.com/ultralytics/yolov5/releases/tag/v6.2\r\n[current]: https://github.com/ultralytics/yolov5/releases/tag/v7.0\r\n[TTA]: https://github.com/ultralytics/yolov5/issues/303\r\n\r\n<div align=\"center\">\r\n<a align=\"center\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\r\n<img width=\"850\" src=\"https://github.com/ultralytics/assets/blob/main/yolov5/v70/splash.png\"></a>\r\n</div>\r\n<br>\r\n\r\nOur new YOLOv5 v7.0 instance segmentation models are the fastest and most accurate in the world, beating all current [SOTA benchmarks](https://paperswithcode.com/sota/real-time-instance-segmentation-on-mscoco). We've made them super simple to train, validate and deploy. See full details in our [Release Notes](https://github.com/ultralytics/yolov5/releases/v7.0) and visit our [YOLOv5 Segmentation Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb) for quickstart tutorials.\r\n\r\n<div align=\"center\">\r\n<a align=\"center\" href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\r\n<img width=\"800\" src=\"https://user-images.githubusercontent.com/61612323/204180385-84f3aca9-a5e9-43d8-a617-dda7ca12e54a.png\"></a>\r\n</div>\r\n<br>\r\n\r\nOur primary goal with this release is to introduce super simple YOLOv5 segmentation workflows just like our existing object detection models. The new v7.0 YOLOv5-seg models below are just a start, we will continue to improve these going forward together with our existing detection and classification models. We'd love your feedback and [contributions](https://github.com/ultralytics/yolov5/blob/master/CONTRIBUTING.md) on this effort!\r\n\r\nThis release incorporates [**280 PRs** from **41 contributors**](https://github.com/ultralytics/yolov5/compare/v6.2...v7.0) since our last [release][previous] in August 2022.\r\n\r\n\r\n## Important Updates\r\n\r\n- **Segmentation Models ⭐ NEW**: SOTA YOLOv5-seg COCO-pretrained segmentation models are now available for the first time (https://github.com/ultralytics/yolov5/pull/9052 by @glenn-jocher, @AyushExel and @Laughing-q)\r\n- **Paddle Paddle Export**: Export any YOLOv5 model (cls, seg, det) to Paddle format with python export.py --include paddle (https://github.com/ultralytics/yolov5/pull/9459 by @glenn-jocher)\r\n- **YOLOv5 AutoCache**: Use `python train.py --cache ram` will now scan available memory and compare against predicted dataset RAM usage. This reduces risk in caching and should help improve adoption of the dataset caching feature, which can significantly speed up training. (https://github.com/ultralytics/yolov5/pull/10027 by @glenn-jocher)\r\n- **Comet Logging and Visualization Integration:** Free forever, [Comet](https://bit.ly/yolov5-readme-comet) lets you save YOLOv5 models, resume training, and interactively visualise and debug predictions. (https://github.com/ultralytics/yolov5/pull/9232 by @DN6)\r\n\r\n\r\n### New Segmentation Checkpoints\r\n\r\nWe trained YOLOv5 segmentations models on COCO for 300 epochs at image size 640 using A100 GPUs. We exported all models to ONNX FP32 for CPU speed tests and to TensorRT FP16 for GPU speed tests. We ran all speed tests on Google [Colab Pro](https://colab.research.google.com/signup) notebooks for easy reproducibility.\r\n\r\n| Model                                                                                              | size<br><sup>(pixels) | mAP<sup>box<br>50-95 | mAP<sup>mask<br>50-95 | Train time<br><sup>300 epochs<br>A100 (hours) | Speed<br><sup>ONNX CPU<br>(ms) | Speed<br><sup>TRT A100<br>(ms) | params<br><sup>(M) | FLOPs<br><sup>@640 (B) |\r\n|----------------------------------------------------------------------------------------------------|-----------------------|----------------------|-----------------------|-----------------------------------------------|--------------------------------|--------------------------------|--------------------|------------------------|\r\n| [YOLOv5n-seg](https://github.com/ultralytics/yolov5/releases/download/v7.0/yolo","is_prerelease":false},"readme":true,"readme_zh":true,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}