meituan /YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
★ 5,893⑂ 1,057👁 58⑃ 280● 807▤ 7
+0
日增长
5,893
stars
1,057
forks
58
watchers
280
prs
807
issues
7
releases
README
English | 简体中文
YOLOv6
Implementation of paper:
- YOLOv6 v3.0: A Full-Scale Reloading 🔥
- YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
What's New
- [2023.09.15] Release YOLOv6-Segmentation. 🚀 Performance
- [2023.04.28] Release YOLOv6Lite models on mobile or CPU. ⭐️ Mobile Benchmark
- [2023.03.10] Release YOLOv6-Face. 🔥 Performance
- [2023.03.02] Update base models to version 3.0.
- [2023.01.06] Release P6 models and enhance the performance of P5 models. ⭐️ Benchmark
- [2022.11.04] Release base models to simplify the training and deployment process.
- [2022.09.06] Customized quantization methods. 🚀 Quantization Tutorial
- [2022.09.05] Release M/L models and update N/T/S models with enhanced performance.
- [2022.06.23] Release N/T/S models with excellent performance.
Benchmark
| Model | Size | mAPval0.5:0.95 | SpeedT4trt fp16 b1 (fps) | SpeedT4trt fp16 b32 (fps) | Params (M) | FLOPs (G) |
| :----------------------------------------------------------- | ---- | :----------------------- | --------------------------------------- | ---------------------------------------- | -------------------- | ------------------- |
| YOLOv6-N | 640 | 37.5 | 779 | 1187 | 4.7 | 11.4 |
| YOLOv6-S | 640 | 45.0 | 339 | 484 | 18.5 | 45.3 |
| YOLOv6-M | 640 | 50.0 | 175 | 226 | 34.9 | 85.8 |
| YOLOv6-L | 640 | 52.8 | 98 | 116 | 59.6 | 150.7 |
| | | | | |
| YOLOv6-N6 | 1280 | 44.9 | 228 | 281 | 10.4 | 49.8 |
| YOLOv6-S6 | 1280 | 50.3 | 98 | 108 | 41.4 | 198.0 |
| YOLOv6-M6 | 1280 | 55.2 | 47 | 55 | 79.6 | 379.5 |
| YOLOv6-L6 | 1280 | 57.2 | 26 | 29 | 140.4 | 673.4 |
Table Notes
- All checkpoints are trained with self-distillation except for YOLOv6-N6/S6 models trained to 300 epochs without distillation.
- Results of the mAP and speed are evTop issues
#366为什么最新的拉下来训练的很慢? 比半个月拉下来额慢了好几本 配置一样31 comments · 2022-07-26#535Training Failure21 comments · 2022-10-06#688请问要使用自蒸馏teacher model path要设置一个什么样的预训练权重,19 comments · 2023-01-16#799AttributeError: Can't get attribute 'SimConv' on <module 'yolov6.layers.common'15 comments · 2023-04-28#874iou_loss dfl_loss一直为011 comments · 2023-07-11#662How can I run the "infer" (inference pipeline) on a video and save the results? (video with bboxes and metrics if it possible)9 comments · 2022-12-17#768量化8 comments · 2023-04-06#590trained weight not shows the bounding boxes8 comments · 2022-11-04
Latest release
YOLOv6-Segmentation 0.4.1 2023-09-15Features - Release YOLOv6-Segmentation models at full scales - Achieve the state-of-the-art accuracy in Real-time Instance Segmentation. Performance of YOLOv6-seg models | Model | Size | mAPbox50-95 | mAPmask50-95 | SpeedT4trt fp16 b1 (fps) | Params (M) | FLOPs (G) | | :----------------------------------------------------------- | ---- | :-------------------- | ---------------------- | --------------------------------------- | -------------------- | ------------------- | | YOLOv6-N | 640 | 35.3 | 31.2