{"id":15032353,"url":"https://github.com/meituan/yolov6","last_synced_at":"2025-05-14T12:10:58.532Z","repository":{"id":36953287,"uuid":"501076075","full_name":"meituan/YOLOv6","owner":"meituan","description":"YOLOv6: a single-stage object detection framework dedicated to industrial applications.","archived":false,"fork":false,"pushed_at":"2024-08-07T18:20:33.000Z","size":37809,"stargazers_count":5703,"open_issues_count":266,"forks_count":1027,"subscribers_count":63,"default_branch":"main","last_synced_at":"2024-10-29T15:04:44.536Z","etag":null,"topics":["object-detection","pytorch","yolo"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/meituan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-06-08T02:44:22.000Z","updated_at":"2024-10-29T12:45:02.000Z","dependencies_parsed_at":"2024-01-09T14:27:36.874Z","dependency_job_id":"57f631a9-f9cf-4b3c-91ff-6f495fd68287","html_url":"https://github.com/meituan/YOLOv6","commit_stats":null,"previous_names":[],"tags_count":7,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meituan%2FYOLOv6","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meituan%2FYOLOv6/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meituan%2FYOLOv6/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meituan%2FYOLOv6/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meituan","download_url":"https://codeload.github.com/meituan/YOLOv6/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254140768,"owners_count":22021220,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["object-detection","pytorch","yolo"],"created_at":"2024-09-24T20:18:09.007Z","updated_at":"2025-05-14T12:10:58.457Z","avatar_url":"https://github.com/meituan.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n \u003cimg src=\"assets/banner-YOLO.png\" align=\"middle\" width = \"1000\" /\u003e\n\u003c/p\u003e\n\nEnglish | [็ฎ€ไฝ“ไธญๆ–‡](README_cn.md)\n\n \u003cbr\u003e\n\n \u003cdiv\u003e\n \u003c/a\u003e\n \u003ca href=\"https://colab.research.google.com/github/meituan/YOLOv6/blob/main/turtorial.ipynb\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"\u003e\u003c/a\u003e\n \u003ca href=\"https://www.kaggle.com/code/housanduo/yolov6\"\u003e\u003cimg src=\"https://kaggle.com/static/images/open-in-kaggle.svg\" alt=\"Open In Kaggle\"\u003e\u003c/a\u003e\n \u003c/div\u003e\n \u003cbr\u003e\n\n## YOLOv6\n\nImplementation of paper:\n- [YOLOv6 v3.0: A Full-Scale Reloading](https://arxiv.org/abs/2301.05586) ๐Ÿ”ฅ\n- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://arxiv.org/abs/2209.02976)\n\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"assets/speed_comparision_v3.png\" align=\"middle\" width = \"1000\" /\u003e\n\u003c/p\u003e\n\n\n## What's New\n- [2023.09.15] Release [YOLOv6-Segmentation](https://github.com/meituan/YOLOv6/tree/yolov6-seg). ๐Ÿš€ [Performance](https://github.com/meituan/YOLOv6/tree/yolov6-seg#yolov6-segmentation)\n- [2023.04.28] Release [YOLOv6Lite](configs/yolov6_lite/README.md) models on mobile or CPU. โญ๏ธ [Mobile Benchmark](#Mobile-Benchmark)\n- [2023.03.10] Release [YOLOv6-Face](https://github.com/meituan/YOLOv6/tree/yolov6-face). ๐Ÿ”ฅ [Performance](https://github.com/meituan/YOLOv6/tree/yolov6-face#performance-on-widerface)\n- [2023.03.02] Update [base models](configs/base/README.md) to version 3.0.\n- [2023.01.06] Release P6 models and enhance the performance of P5 models. โญ๏ธ [Benchmark](#Benchmark)\n- [2022.11.04] Release [base models](configs/base/README.md) to simplify the training and deployment process.\n- [2022.09.06] Customized quantization methods. ๐Ÿš€ [Quantization Tutorial](./tools/qat/README.md)\n- [2022.09.05] Release M/L models and update N/T/S models with enhanced performance.\n- [2022.06.23] Release N/T/S models with excellent performance.\n\n## Benchmark\n| Model | Size | mAP\u003csup\u003eval\u003cbr/\u003e0.5:0.95 | Speed\u003csup\u003eT4\u003cbr/\u003etrt fp16 b1 \u003cbr/\u003e(fps) | Speed\u003csup\u003eT4\u003cbr/\u003etrt fp16 b32 \u003cbr/\u003e(fps) | Params\u003cbr/\u003e\u003csup\u003e (M) | FLOPs\u003cbr/\u003e\u003csup\u003e (G) |\n| :----------------------------------------------------------- | ---- | :----------------------- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |\n| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6n.pt) | 640 | 37.5 | 779 | 1187 | 4.7 | 11.4 |\n| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6s.pt) | 640 | 45.0 | 339 | 484 | 18.5 | 45.3 |\n| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6m.pt) | 640 | 50.0 | 175 | 226 | 34.9 | 85.8 |\n| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6l.pt) | 640 | 52.8 | 98 | 116 | 59.6 | 150.7 |\n| | | | | |\n| [**YOLOv6-N6**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6n6.pt) | 1280 | 44.9 | 228 | 281 | 10.4 | 49.8 |\n| [**YOLOv6-S6**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6s6.pt) | 1280 | 50.3 | 98 | 108 | 41.4 | 198.0 |\n| [**YOLOv6-M6**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6m6.pt) | 1280 | 55.2 | 47 | 55 | 79.6 | 379.5 |\n| [**YOLOv6-L6**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6l6.pt) | 1280 | 57.2 | 26 | 29 | 140.4 | 673.4 |\n\u003cdetails\u003e\n\u003csummary\u003eTable Notes\u003c/summary\u003e\n\n- All checkpoints are trained with self-distillation except for YOLOv6-N6/S6 models trained to 300 epochs without distillation.\n- Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset with the input resolution of 640ร—640 for P5 models and 1280x1280 for P6 models.\n- Speed is tested with TensorRT 7.2 on T4.\n- Refer to [Test speed](./docs/Test_speed.md) tutorial to reproduce the speed results of YOLOv6.\n- Params and FLOPs of YOLOv6 are estimated on deployed models.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003eLegacy models\u003c/summary\u003e\n\n| Model | Size | mAP\u003csup\u003eval\u003cbr/\u003e0.5:0.95 | Speed\u003csup\u003eT4\u003cbr/\u003etrt fp16 b1 \u003cbr/\u003e(fps) | Speed\u003csup\u003eT4\u003cbr/\u003etrt fp16 b32 \u003cbr/\u003e(fps) | Params\u003cbr/\u003e\u003csup\u003e (M) | FLOPs\u003cbr/\u003e\u003csup\u003e (G) |\n| :----------------------------------------------------------- | ---- | :------------------------------------ | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |\n| [**YOLOv6-N**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6n.pt) | 640 | 35.9\u003csup\u003e300e\u003c/sup\u003e\u003cbr/\u003e36.3\u003csup\u003e400e | 802 | 1234 | 4.3 | 11.1 |\n| [**YOLOv6-T**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6t.pt) | 640 | 40.3\u003csup\u003e300e\u003c/sup\u003e\u003cbr/\u003e41.1\u003csup\u003e400e | 449 | 659 | 15.0 | 36.7 |\n| [**YOLOv6-S**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6s.pt) | 640 | 43.5\u003csup\u003e300e\u003c/sup\u003e\u003cbr/\u003e43.8\u003csup\u003e400e | 358 | 495 | 17.2 | 44.2 |\n| [**YOLOv6-M**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6m.pt) | 640 | 49.5 | 179 | 233 | 34.3 | 82.2 |\n| [**YOLOv6-L-ReLU**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l_relu.pt) | 640 | 51.7 | 113 | 149 | 58.5 | 144.0 |\n| [**YOLOv6-L**](https://github.com/meituan/YOLOv6/releases/download/0.2.0/yolov6l.pt) | 640 | 52.5 | 98 | 121 | 58.5 | 144.0 |\n- Speed is tested with TensorRT 7.2 on T4.\n### Quantized model ๐Ÿš€\n\n| Model | Size | Precision | mAP\u003csup\u003eval\u003cbr/\u003e0.5:0.95 | Speed\u003csup\u003eT4\u003cbr/\u003etrt b1 \u003cbr/\u003e(fps) | Speed\u003csup\u003eT4\u003cbr/\u003etrt b32 \u003cbr/\u003e(fps) |\n| :-------------------- | ---- | --------- | :----------------------- | ---------------------------------- | ----------------------------------- |\n| **YOLOv6-N RepOpt** | 640 | INT8 | 34.8 | 1114 | 1828 |\n| **YOLOv6-N** | 640 | FP16 | 35.9 | 802 | 1234 |\n| **YOLOv6-T RepOpt** | 640 | INT8 | 39.8 | 741 | 1167 |\n| **YOLOv6-T** | 640 | FP16 | 40.3 | 449 | 659 |\n| **YOLOv6-S RepOpt** | 640 | INT8 | 43.3 | 619 | 924 |\n| **YOLOv6-S** | 640 | FP16 | 43.5 | 377 | 541 |\n\n- Speed is tested with TensorRT 8.4 on T4.\n- Precision is figured on models for 300 epochs.\n\n\u003c/details\u003e\n\n## Mobile Benchmark\n| Model | Size | mAP\u003csup\u003eval\u003cbr/\u003e0.5:0.95 | sm8350\u003cbr/\u003e\u003csup\u003e(ms) | mt6853\u003cbr/\u003e\u003csup\u003e(ms) | sdm660\u003cbr/\u003e\u003csup\u003e(ms) |Params\u003cbr/\u003e\u003csup\u003e (M) | FLOPs\u003cbr/\u003e\u003csup\u003e (G) |\n| :----------------------------------------------------------- | ---- | -------------------- | -------------------- | -------------------- | -------------------- | -------------------- | -------------------- |\n| [**YOLOv6Lite-S**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6lite_s.pt) | 320*320 | 22.4 | 7.99 | 11.99 | 41.86 | 0.55 | 0.56 |\n| [**YOLOv6Lite-M**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6lite_m.pt) | 320*320 | 25.1 | 9.08 | 13.27 | 47.95 | 0.79 | 0.67 |\n| [**YOLOv6Lite-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6lite_l.pt) | 320*320 | 28.0 | 11.37 | 16.20 | 61.40 | 1.09 | 0.87 |\n| [**YOLOv6Lite-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6lite_l.pt) | 320*192 | 25.0 | 7.02 | 9.66 | 36.13 | 1.09 | 0.52 |\n| [**YOLOv6Lite-L**](https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6lite_l.pt) | 224*128 | 18.9 | 3.63 | 4.99 | 17.76 | 1.09 | 0.24 |\n\n\u003cdetails\u003e\n\u003csummary\u003eTable Notes\u003c/summary\u003e\n\n- From the perspective of model size and input image ratio, we have built a series of models on the mobile terminal to facilitate flexible applications in different scenarios.\n- All checkpoints are trained with 400 epochs without distillation.\n- Results of the mAP and speed are evaluated on [COCO val2017](https://cocodataset.org/#download) dataset, and the input resolution is the Size in the table.\n- Speed is tested on MNN 2.3.0 AArch64 with 2 threads by arm82 acceleration. The inference warm-up is performed 10 times, and the cycle is performed 100 times.\n- Qualcomm 888(sm8350), Dimensity 720(mt6853) and Qualcomm 660(sdm660) correspond to chips with different performances at the high, middle and low end respectively, which can be used as a reference for model capabilities under different chips.\n- Refer to [Test NCNN Speed](./docs/Test_NCNN_speed.md) tutorial to reproduce the NCNN speed results of YOLOv6Lite.\n\n\u003c/details\u003e\n\n## Quick Start\n\u003cdetails\u003e\n\u003csummary\u003e Install\u003c/summary\u003e\n\n\n```shell\ngit clone https://github.com/meituan/YOLOv6\ncd YOLOv6\npip install -r requirements.txt\n```\n\u003c/details\u003e\n\n\n\n\u003cdetails\u003e\n\u003csummary\u003e Reproduce our results on COCO\u003c/summary\u003e\n\nPlease refer to [Train COCO Dataset](./docs/Train_coco_data.md).\n\n\u003c/details\u003e\n\n\u003cdetails open\u003e\n\u003csummary\u003e Finetune on custom data\u003c/summary\u003e\n\nSingle GPU\n\n```shell\n# P5 models\npython tools/train.py --batch 32 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0\n# P6 models\npython tools/train.py --batch 32 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0\n```\n\nMulti GPUs (DDP mode recommended)\n\n```shell\n# P5 models\npython -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 256 --conf configs/yolov6s_finetune.py --data data/dataset.yaml --fuse_ab --device 0,1,2,3,4,5,6,7\n# P6 models\npython -m torch.distributed.launch --nproc_per_node 8 tools/train.py --batch 128 --conf configs/yolov6s6_finetune.py --data data/dataset.yaml --img 1280 --device 0,1,2,3,4,5,6,7\n```\n- fuse_ab: add anchor-based auxiliary branch and use Anchor Aided Training Mode (Not supported on P6 models currently)\n- conf: select config file to specify network/optimizer/hyperparameters. We recommend to apply yolov6n/s/m/l_finetune.py when training on your custom dataset.\n- data: prepare dataset and specify dataset paths in data.yaml ( [COCO](http://cocodataset.org), [YOLO format coco labels](https://github.com/meituan/YOLOv6/releases/download/0.1.0/coco2017labels.zip) )\n- make sure your dataset structure as follows:\n```\nโ”œโ”€โ”€ coco\nโ”‚ โ”œโ”€โ”€ annotations\nโ”‚ โ”‚ โ”œโ”€โ”€ instances_train2017.json\nโ”‚ โ”‚ โ””โ”€โ”€ instances_val2017.json\nโ”‚ โ”œโ”€โ”€ images\nโ”‚ โ”‚ โ”œโ”€โ”€ train2017\nโ”‚ โ”‚ โ””โ”€โ”€ val2017\nโ”‚ โ”œโ”€โ”€ labels\nโ”‚ โ”‚ โ”œโ”€โ”€ train2017\nโ”‚ โ”‚ โ”œโ”€โ”€ val2017\nโ”‚ โ”œโ”€โ”€ LICENSE\nโ”‚ โ”œโ”€โ”€ README.txt\n```\n\nYOLOv6 supports different input resolution modes. For details, see [How to Set the Input Size](./docs/About_training_size.md).\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003eResume training\u003c/summary\u003e\n\nIf your training process is corrupted, you can resume training by\n```\n# single GPU training.\npython tools/train.py --resume\n\n# multi GPU training.\npython -m torch.distributed.launch --nproc_per_node 8 tools/train.py --resume\n```\nAbove command will automatically find the latest checkpoint in YOLOv6 directory, then resume the training process.\n\nYour can also specify a checkpoint path to `--resume` parameter by\n```\n# remember to replace /path/to/your/checkpoint/path to the checkpoint path which you want to resume training.\n--resume /path/to/your/checkpoint/path\n```\nThis will resume from the specific checkpoint you provide.\n\n\u003c/details\u003e\n\n\u003cdetails open\u003e\n\u003csummary\u003e Evaluation\u003c/summary\u003e\n\nReproduce mAP on COCO val2017 dataset with 640ร—640 or 1280x1280 resolution\n\n```shell\n# P5 models\npython tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s.pt --task val --reproduce_640_eval\n# P6 models\npython tools/eval.py --data data/coco.yaml --batch 32 --weights yolov6s6.pt --task val --reproduce_640_eval --img 1280\n```\n- verbose: set True to print mAP of each classes.\n- do_coco_metric: set True / False to enable / disable pycocotools evaluation method.\n- do_pr_metric: set True / False to print or not to print the precision and recall metrics.\n- config-file: specify a config file to define all the eval params, for example: [yolov6n_with_eval_params.py](configs/experiment/yolov6n_with_eval_params.py)\n\u003c/details\u003e\n\n\n\u003cdetails\u003e\n\u003csummary\u003eInference\u003c/summary\u003e\n\nFirst, download a pretrained model from the YOLOv6 [release](https://github.com/meituan/YOLOv6/releases/tag/0.4.0) or use your trained model to do inference.\n\nSecond, run inference with `tools/infer.py`\n\n```shell\n# P5 models\npython tools/infer.py --weights yolov6s.pt --source img.jpg / imgdir / video.mp4\n# P6 models\npython tools/infer.py --weights yolov6s6.pt --img 1280 1280 --source img.jpg / imgdir / video.mp4\n```\nIf you want to inference on local camera or web camera, you can run:\n```shell\n# P5 models\npython tools/infer.py --weights yolov6s.pt --webcam --webcam-addr 0\n# P6 models\npython tools/infer.py --weights yolov6s6.pt --img 1280 1280 --webcam --webcam-addr 0\n```\n`webcam-addr` can be local camera number id or rtsp address.\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e Deployment\u003c/summary\u003e\n\n* [ONNX](./deploy/ONNX)\n* [OpenCV Python/C++](./deploy/ONNX/OpenCV)\n* [OpenVINO](./deploy/OpenVINO)\n* [TensorRT](./deploy/TensorRT)\n* [NCNN](./deploy/NCNN)\n* [Android](./deploy/NCNN/Android)\n\u003c/details\u003e\n\n\u003cdetails open\u003e\n\u003csummary\u003e Tutorials\u003c/summary\u003e\n\n* [User Guide(zh_CN)](https://yolov6-docs.readthedocs.io/zh_CN/latest/)\n* [Train COCO Dataset](./docs/Train_coco_data.md)\n* [Train custom data](./docs/Train_custom_data.md)\n* [Test speed](./docs/Test_speed.md)\n* [Tutorial of Quantization for YOLOv6](./docs/Tutorial%20of%20Quantization.md)\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e Third-party resources\u003c/summary\u003e\n\n * YOLOv6 Training with Amazon Sagemaker: [yolov6-sagemaker](https://github.com/ashwincc/yolov6-sagemaker) from [ashwincc](https://github.com/ashwincc) \n\n * YOLOv6 NCNN Android app demo: [ncnn-android-yolov6](https://github.com/FeiGeChuanShu/ncnn-android-yolov6) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu)\n\n * YOLOv6 ONNXRuntime/MNN/TNN C++: [YOLOv6-ORT](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/ort/cv/yolov6.cpp), [YOLOv6-MNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/mnn/cv/mnn_yolov6.cpp) and [YOLOv6-TNN](https://github.com/DefTruth/lite.ai.toolkit/blob/main/lite/tnn/cv/tnn_yolov6.cpp) from [DefTruth](https://github.com/DefTruth)\n\n * YOLOv6 TensorRT Python: [yolov6-tensorrt-python](https://github.com/Linaom1214/TensorRT-For-YOLO-Series) from [Linaom1214](https://github.com/Linaom1214)\n\n * YOLOv6 TensorRT Windows C++: [yolort](https://github.com/zhiqwang/yolov5-rt-stack/tree/main/deployment/tensorrt-yolov6) from [Wei Zeng](https://github.com/Wulingtian)\n\n * [YOLOv6 web demo](https://huggingface.co/spaces/nateraw/yolov6) on [Huggingface Spaces](https://huggingface.co/spaces) with [Gradio](https://github.com/gradio-app/gradio). [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/nateraw/yolov6)\n\n * [Interactive demo](https://yolov6.dagshubusercontent.com/) on [DagsHub](https://dagshub.com) with [Streamlit](https://github.com/streamlit/streamlit)\n\n * Tutorial: [How to train YOLOv6 on a custom dataset](https://blog.roboflow.com/how-to-train-yolov6-on-a-custom-dataset/) \u003ca href=\"https://colab.research.google.com/drive/1YnbqOinBZV-c9I7fk_UL6acgnnmkXDMM\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"\u003e\u003c/a\u003e\n\n * YouTube Tutorial: [How to train YOLOv6 on a custom dataset](https://youtu.be/fFCWrMFH2UY)\n\n * Demo of YOLOv6 inference on Google Colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mahdilamb/YOLOv6/blob/main/inference.ipynb)\n\n * Blog post: [YOLOv6 Object Detection โ€“ Paper Explanation and Inference](https://learnopencv.com/yolov6-object-detection/)\n\n \u003c/details\u003e\n\n### [FAQ๏ผˆContinuously updated๏ผ‰](https://github.com/meituan/YOLOv6/wiki/FAQ%EF%BC%88Continuously-updated%EF%BC%89)\n\nIf you have any questions, welcome to join our WeChat group to discuss and exchange.\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"assets/wechat_qrcode.png\" align=\"middle\" width = \"1000\" /\u003e\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeituan%2Fyolov6","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmeituan%2Fyolov6","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmeituan%2Fyolov6/lists"}