diff --git a/README.md b/README.md index 96e0c08f..9d2722e2 100644 --- a/README.md +++ b/README.md @@ -283,6 +283,7 @@ Results and models are available in the [model zoo](docs/en/model_zoo.md). Supported Algorithms - [x] [YOLOv5](configs/yolov5) +- [ ] [YOLOv5u](configs/yolov5/yolov5u) (Inference only) - [x] [YOLOX](configs/yolox) - [x] [RTMDet](configs/rtmdet) - [x] [RTMDet-Rotated](configs/rtmdet) diff --git a/README_zh-CN.md b/README_zh-CN.md index 16c55a65..cc44f711 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -305,6 +305,7 @@ MMYOLO 用法和 MMDetection 几乎一致，所有教程都是通用的，你也 支持的算法 - [x] [YOLOv5](configs/yolov5) +- [ ] [YOLOv5u](configs/yolov5/yolov5u) (仅推理) - [x] [YOLOX](configs/yolox) - [x] [RTMDet](configs/rtmdet) - [x] [RTMDet-Rotated](configs/rtmdet) diff --git a/configs/ppyoloe/README.md b/configs/ppyoloe/README.md index 6ea827ec..70a5b205 100644 --- a/configs/ppyoloe/README.md +++ b/configs/ppyoloe/README.md @@ -19,12 +19,12 @@ PPYOLOE-PLUS-l model structure ### PPYOLOE+ COCO -| Backbone | Arch | Size | Epoch | SyncBN | Mem (GB) | Box AP | Config | Download | -| :---------: | :--: | :--: | :---: | :----: | :------: | :----: | :-------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| PPYOLOE+ -s | P5 | 640 | 80 | Yes | 4.7 | 43.5 | [config](../ppyoloe/ppyoloe_plus_s_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_s_fast_8xb8-80e_coco/ppyoloe_plus_s_fast_8xb8-80e_coco_20230101_154052-9fee7619.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_s_fast_8xb8-80e_coco/ppyoloe_plus_s_fast_8xb8-80e_coco_20230101_154052.log.json) | -| PPYOLOE+ -m | P5 | 640 | 80 | Yes | 8.4 | 49.5 | [config](../ppyoloe/ppyoloe_plus_m_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_m_fast_8xb8-80e_coco/ppyoloe_plus_m_fast_8xb8-80e_coco_20230104_193132-e4325ada.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_m_fast_8xb8-80e_coco/ppyoloe_plus_m_fast_8xb8-80e_coco_20230104_193132.log.json) | -| PPYOLOE+ -l | P5 | 640 | 80 | Yes | 13.2 | 52.6 | [config](../ppyoloe/ppyoloe_plus_l_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_l_fast_8xb8-80e_coco/ppyoloe_plus_l_fast_8xb8-80e_coco_20230102_203825-1864e7b3.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_l_fast_8xb8-80e_coco/ppyoloe_plus_l_fast_8xb8-80e_coco_20230102_203825.log.json) | -| PPYOLOE+ -x | P5 | 640 | 80 | Yes | 19.1 | 54.2 | [config](../ppyoloe/ppyoloe_plus_x_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_x_fast_8xb8-80e_coco/ppyoloe_plus_x_fast_8xb8-80e_coco_20230104_194921-8c953949.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_x_fast_8xb8-80e_coco/ppyoloe_plus_x_fast_8xb8-80e_coco_20230104_194921.log.json) | +| Backbone | Arch | Size | Epoch | SyncBN | Mem (GB) | Box AP | Config | Download | +| :---------: | :--: | :--: | :---: | :----: | :------: | :----: | :----------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| PPYOLOE+ -s | P5 | 640 | 80 | Yes | 4.7 | 43.5 | [config](./ppyoloe_plus_s_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_s_fast_8xb8-80e_coco/ppyoloe_plus_s_fast_8xb8-80e_coco_20230101_154052-9fee7619.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_s_fast_8xb8-80e_coco/ppyoloe_plus_s_fast_8xb8-80e_coco_20230101_154052.log.json) | +| PPYOLOE+ -m | P5 | 640 | 80 | Yes | 8.4 | 49.5 | [config](./ppyoloe_plus_m_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_m_fast_8xb8-80e_coco/ppyoloe_plus_m_fast_8xb8-80e_coco_20230104_193132-e4325ada.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_m_fast_8xb8-80e_coco/ppyoloe_plus_m_fast_8xb8-80e_coco_20230104_193132.log.json) | +| PPYOLOE+ -l | P5 | 640 | 80 | Yes | 13.2 | 52.6 | [config](./ppyoloe_plus_l_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_l_fast_8xb8-80e_coco/ppyoloe_plus_l_fast_8xb8-80e_coco_20230102_203825-1864e7b3.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_l_fast_8xb8-80e_coco/ppyoloe_plus_l_fast_8xb8-80e_coco_20230102_203825.log.json) | +| PPYOLOE+ -x | P5 | 640 | 80 | Yes | 19.1 | 54.2 | [config](./ppyoloe_plus_x_fast_8xb8-80e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_x_fast_8xb8-80e_coco/ppyoloe_plus_x_fast_8xb8-80e_coco_20230104_194921-8c953949.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/ppyoloe/ppyoloe_plus_x_fast_8xb8-80e_coco/ppyoloe_plus_x_fast_8xb8-80e_coco_20230104_194921.log.json) | **Note**: diff --git a/configs/razor/subnets/README.md b/configs/razor/subnets/README.md index 093dedd7..456021bd 100644 --- a/configs/razor/subnets/README.md +++ b/configs/razor/subnets/README.md @@ -62,14 +62,14 @@ CUDA_VISIBLE_DEVICES=0 PORT=29500 ./tools/dist_test.sh configs/razor/subnets/yol Here we provide the baseline version of YOLO Series with NAS backbone. -| Model | size | box AP | Params(M) | FLOPs(G) | Config | Download | -| :------------------------: | :--: | :----: | :----------: | :------: | :---------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| yolov5-s | 640 | 37.7 | 7.235 | 8.265 | [config](https://github.com/open-mmlab/mmyolo/blob/main/configs/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700.log.json) | -| yolov5_s_spos_shufflenetv2 | 640 | 38.0 | 7.04(-2.7%) | 7.03 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/razor/subnets/yolov5_s_spos_shufflenetv2_syncbn_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/yolov5_s_spos_shufflenetv2_syncbn_8xb16-300e_coco_20230211_220635-578be9a9.pth) \| log | -| yolov6-s | 640 | 44.0 | 18.869 | 24.253 | [config](https://github.com/open-mmlab/mmyolo/blob/main/configs/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035-932e1d91.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035.log.json) | -| yolov6_l_attentivenas_a6 | 640 | 45.3 | 18.38(-2.6%) | 8.49 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/razor/subnets/yolov6_l_attentivenas_a6_d12_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/yolov6_l_attentivenas_a6_d12_syncbn_fast_8xb32-300e_coco_20230211_222409-dcc72668.pth) \| log | -| RTMDet-tiny | 640 | 41.0 | 4.8 | 8.1 | [config](./rtmdet_l_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/rtmdet/rtmdet_tiny_syncbn_fast_8xb32-300e_coco/rtmdet_tiny_syncbn_fast_8xb32-300e_coco_20230102_140117-dbb1dc83.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/rtmdet/rtmdet_tiny_syncbn_fast_8xb32-300e_coco/rtmdet_tiny_syncbn_fast_8xb32-300e_coco_20230102_140117.log.json) | -| rtmdet_tiny_ofa_lat31 | 960 | 41.3 | 3.91(-18.5%) | 6.09 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/razor/subnets/rtmdet_tiny_ofa_lat31_syncbn_16xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/rtmdet_tiny_ofa_lat31_syncbn_16xb16-300e_coco_20230214_210623-449bb2a0.pth) \| log | +| Model | size | box AP | Params(M) | FLOPs(G) | Config | Download | +| :------------------------: | :--: | :----: | :----------: | :------: | :---------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| yolov5-s | 640 | 37.7 | 7.235 | 8.265 | [config](../../yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700.log.json) | +| yolov5_s_spos_shufflenetv2 | 640 | 38.0 | 7.04(-2.7%) | 7.03 | [config](./yolov5_s_spos_shufflenetv2_syncbn_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/yolov5_s_spos_shufflenetv2_syncbn_8xb16-300e_coco_20230211_220635-578be9a9.pth) \| log | +| yolov6-s | 640 | 44.0 | 18.869 | 24.253 | [config](../../yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035-932e1d91.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035.log.json) | +| yolov6_l_attentivenas_a6 | 640 | 45.3 | 18.38(-2.6%) | 8.49 | [config](./yolov6_l_attentivenas_a6_d12_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/yolov6_l_attentivenas_a6_d12_syncbn_fast_8xb32-300e_coco_20230211_222409-dcc72668.pth) \| log | +| RTMDet-tiny | 640 | 41.0 | 4.8 | 8.1 | [config](../../rtmdet/rtmdet_l_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/rtmdet/rtmdet_tiny_syncbn_fast_8xb32-300e_coco/rtmdet_tiny_syncbn_fast_8xb32-300e_coco_20230102_140117-dbb1dc83.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/rtmdet/rtmdet_tiny_syncbn_fast_8xb32-300e_coco/rtmdet_tiny_syncbn_fast_8xb32-300e_coco_20230102_140117.log.json) | +| rtmdet_tiny_ofa_lat31 | 960 | 41.3 | 3.91(-18.5%) | 6.09 | [config](./rtmdet_tiny_ofa_lat31_syncbn_16xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmrazor/v1/yolo_nas_backbone/rtmdet_tiny_ofa_lat31_syncbn_16xb16-300e_coco_20230214_210623-449bb2a0.pth) \| log | **Note**: diff --git a/configs/yolov5/README.md b/configs/yolov5/README.md index 4f7d236a..cc6eff2b 100644 --- a/configs/yolov5/README.md +++ b/configs/yolov5/README.md @@ -20,22 +20,27 @@ YOLOv5-l-P6 model structure ### COCO -| Backbone | Arch | size | Mask Refine | SyncBN | AMP | Mem (GB) | box AP | TTA box AP | Config | Download | -| :------: | :--: | :--: | :---------: | :----: | :-: | :------: | :---------: | :--------: | :-------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOv5-n | P5 | 640 | No | Yes | Yes | 1.5 | 28.0 | 30.7 | [config](../yolov5/yolov5_n-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_syncbn_fast_8xb16-300e_coco/yolov5_n-v61_syncbn_fast_8xb16-300e_coco_20220919_090739-b804c1ad.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_syncbn_fast_8xb16-300e_coco/yolov5_n-v61_syncbn_fast_8xb16-300e_coco_20220919_090739.log.json) | -| YOLOv5-n | P5 | 640 | Yes | Yes | Yes | 1.5 | 28.0 | | [config](../yolov5/mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_152706-712fb1b2.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_152706.log.json) | -| YOLOv5-s | P5 | 640 | No | Yes | Yes | 2.7 | 37.7 | 40.2 | [config](../yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700.log.json) | -| YOLOv5-s | P5 | 640 | Yes | Yes | Yes | 2.7 | 38.0 (+0.3) | | [config](../yolov5/mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230304_033134-8e0cd271.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230304_033134.log.json) | -| YOLOv5-m | P5 | 640 | No | Yes | Yes | 5.0 | 45.3 | 46.9 | [config](../yolov5/yolov5_m-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_syncbn_fast_8xb16-300e_coco/yolov5_m-v61_syncbn_fast_8xb16-300e_coco_20220917_204944-516a710f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_syncbn_fast_8xb16-300e_coco/yolov5_m-v61_syncbn_fast_8xb16-300e_coco_20220917_204944.log.json) | -| YOLOv5-m | P5 | 640 | Yes | Yes | Yes | 5.0 | 45.3 | | [config](../yolov5/mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_153946-44e96155.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_153946.log.json) | -| YOLOv5-l | P5 | 640 | No | Yes | Yes | 8.1 | 48.8 | 49.9 | [config](../yolov5/yolov5_l-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_syncbn_fast_8xb16-300e_coco/yolov5_l-v61_syncbn_fast_8xb16-300e_coco_20220917_031007-096ef0eb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_syncbn_fast_8xb16-300e_coco/yolov5_l-v61_syncbn_fast_8xb16-300e_coco_20220917_031007.log.json) | -| YOLOv5-l | P5 | 640 | Yes | Yes | Yes | 8.1 | 49.3 (+0.5) | | [config](../yolov5/mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154301-2c1d912a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154301.log.json) | -| YOLOv5-x | P5 | 640 | No | Yes | Yes | 12.2 | 50.2 | | [config](../yolov5/yolov5_x-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_x-v61_syncbn_fast_8xb16-300e_coco/yolov5_x-v61_syncbn_fast_8xb16-300e_coco_20230305_152943-00776a4b.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_x-v61_syncbn_fast_8xb16-300e_coco/yolov5_x-v61_syncbn_fast_8xb16-300e_coco_20230305_152943.log.json) | -| YOLOv5-x | P5 | 640 | Yes | Yes | Yes | 12.2 | 50.9 (+0.7) | | [config](../yolov5/mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154321-07edeb62.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154321.log.json) | -| YOLOv5-n | P6 | 1280 | No | Yes | Yes | 5.8 | 35.9 | | [config](../yolov5/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_224705-d493c5f3.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_224705.log.json) | -| YOLOv5-s | P6 | 1280 | No | Yes | Yes | 10.5 | 44.4 | | [config](../yolov5/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_215044-58865c19.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_215044.log.json) | -| YOLOv5-m | P6 | 1280 | No | Yes | Yes | 19.1 | 51.3 | | [config](../yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_230453-49564d58.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_230453.log.json) | -| YOLOv5-l | P6 | 1280 | No | Yes | Yes | 30.5 | 53.7 | | [config](../yolov5/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_234308-7a2ba6bf.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_234308.log.json) | +| Backbone | Arch | size | Mask Refine | SyncBN | AMP | Mem (GB) | box AP | TTA box AP | Config | Download | +| :-------: | :--: | :--: | :---------: | :----: | :-: | :------: | :---------: | :--------: | :-----------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOv5-n | P5 | 640 | No | Yes | Yes | 1.5 | 28.0 | 30.7 | [config](./yolov5_n-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_syncbn_fast_8xb16-300e_coco/yolov5_n-v61_syncbn_fast_8xb16-300e_coco_20220919_090739-b804c1ad.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_syncbn_fast_8xb16-300e_coco/yolov5_n-v61_syncbn_fast_8xb16-300e_coco_20220919_090739.log.json) | +| YOLOv5-n | P5 | 640 | Yes | Yes | Yes | 1.5 | 28.0 | | [config](./mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_152706-712fb1b2.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_n_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_152706.log.json) | +| YOLOv5u-n | P5 | 640 | Yes | Yes | Yes | | | | [config](./yolov5/yolov5u/yolov5_n_mask-refine_syncbn_fast_8xb16-300e_coco.py) | [model](<>) \| [log](<>) | +| YOLOv5-s | P5 | 640 | No | Yes | Yes | 2.7 | 37.7 | 40.2 | [config](./yolov5_s-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700-86e02187.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_syncbn_fast_8xb16-300e_coco/yolov5_s-v61_syncbn_fast_8xb16-300e_coco_20220918_084700.log.json) | +| YOLOv5-s | P5 | 640 | Yes | Yes | Yes | 2.7 | 38.0 (+0.3) | | [config](./mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230304_033134-8e0cd271.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_s_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230304_033134.log.json) | +| YOLOv5u-s | P5 | 640 | Yes | Yes | Yes | | | | [config](./yolov5/yolov5u/yolov5_s_mask-refine_syncbn_fast_8xb16-300e_coco.py) | [model](<>) \| [log](<>) | +| YOLOv5-m | P5 | 640 | No | Yes | Yes | 5.0 | 45.3 | 46.9 | [config](./yolov5_m-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_syncbn_fast_8xb16-300e_coco/yolov5_m-v61_syncbn_fast_8xb16-300e_coco_20220917_204944-516a710f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_syncbn_fast_8xb16-300e_coco/yolov5_m-v61_syncbn_fast_8xb16-300e_coco_20220917_204944.log.json) | +| YOLOv5-m | P5 | 640 | Yes | Yes | Yes | 5.0 | 45.3 | | [config](./mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_153946-44e96155.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_m_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_153946.log.json) | +| YOLOv5u-m | P5 | 640 | Yes | Yes | Yes | | | | [config](./yolov5/yolov5u/yolov5_m_mask-refine_syncbn_fast_8xb16-300e_coco.py) | [model](<>) \| [log](<>) | +| YOLOv5-l | P5 | 640 | No | Yes | Yes | 8.1 | 48.8 | 49.9 | [config](./yolov5_l-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_syncbn_fast_8xb16-300e_coco/yolov5_l-v61_syncbn_fast_8xb16-300e_coco_20220917_031007-096ef0eb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_syncbn_fast_8xb16-300e_coco/yolov5_l-v61_syncbn_fast_8xb16-300e_coco_20220917_031007.log.json) | +| YOLOv5-l | P5 | 640 | Yes | Yes | Yes | 8.1 | 49.3 (+0.5) | | [config](./mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154301-2c1d912a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_l_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154301.log.json) | +| YOLOv5u-l | P5 | 640 | Yes | Yes | Yes | | | | [config](./yolov5/yolov5u/yolov5_l_mask-refine_syncbn_fast_8xb16-300e_coco.py) | [model](<>) \| [log](<>) | +| YOLOv5-x | P5 | 640 | No | Yes | Yes | 12.2 | 50.2 | | [config](./yolov5_x-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_x-v61_syncbn_fast_8xb16-300e_coco/yolov5_x-v61_syncbn_fast_8xb16-300e_coco_20230305_152943-00776a4b.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_x-v61_syncbn_fast_8xb16-300e_coco/yolov5_x-v61_syncbn_fast_8xb16-300e_coco_20230305_152943.log.json) | +| YOLOv5-x | P5 | 640 | Yes | Yes | Yes | 12.2 | 50.9 (+0.7) | | [config](./mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154321-07edeb62.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/mask_refine/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco/yolov5_x_mask-refine-v61_syncbn_fast_8xb16-300e_coco_20230305_154321.log.json) | +| YOLOv5u-x | P5 | 640 | Yes | Yes | Yes | | | | [config](./yolov5/yolov5u/yolov5_x_mask-refine_syncbn_fast_8xb16-300e_coco.py) | [model](<>) \| [log](<>) | +| YOLOv5-n | P6 | 1280 | No | Yes | Yes | 5.8 | 35.9 | | [config](./yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_224705-d493c5f3.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_n-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_224705.log.json) | +| YOLOv5-s | P6 | 1280 | No | Yes | Yes | 10.5 | 44.4 | | [config](./yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_215044-58865c19.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_s-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_215044.log.json) | +| YOLOv5-m | P6 | 1280 | No | Yes | Yes | 19.1 | 51.3 | | [config](./yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_230453-49564d58.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_m-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_230453.log.json) | +| YOLOv5-l | P6 | 1280 | No | Yes | Yes | 30.5 | 53.7 | | [config](./yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_234308-7a2ba6bf.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco/yolov5_l-p6-v62_syncbn_fast_8xb16-300e_coco_20221027_234308.log.json) | **Note**: @@ -46,15 +51,16 @@ YOLOv5-l-P6 model structure 5. The performance is unstable and may fluctuate by about 0.4 mAP and the highest performance weight in `COCO` training in `YOLOv5` may not be the last epoch. 6. `TTA` means that Test Time Augmentation. It's perform 3 multi-scaling transformations on the image, followed by 2 flipping transformations (flipping and not flipping). You only need to specify `--tta` when testing to enable. see [TTA](https://github.com/open-mmlab/mmyolo/blob/dev/docs/en/common_usage/tta.md) for details. 7. The performance of `Mask Refine` training is for the weight performance officially released by YOLOv5. `Mask Refine` means refining bbox by mask while loading annotations and transforming after `YOLOv5RandomAffine`, `Copy Paste` means using `YOLOv5CopyPaste`. +8. `YOLOv5u` models use the same loss functions and split Detect head as `YOLOv8` models for improved performance, but only requires 300 epochs. ### VOC -| Backbone | size | Batchsize | AMP | Mem (GB) | box AP(COCO metric) | Config | Download | -| :------: | :--: | :-------: | :-: | :------: | :-----------------: | :------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOv5-n | 512 | 64 | Yes | 3.5 | 51.2 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/voc/yolov5_n-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_fast_1xb64-50e_voc/yolov5_n-v61_fast_1xb64-50e_voc_20221017_234254-f1493430.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_fast_1xb64-50e_voc/yolov5_n-v61_fast_1xb64-50e_voc_20221017_234254.log.json) | -| YOLOv5-s | 512 | 64 | Yes | 6.5 | 62.7 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/voc/yolov5_s-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_fast_1xb64-50e_voc/yolov5_s-v61_fast_1xb64-50e_voc_20221017_234156-0009b33e.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_fast_1xb64-50e_voc/yolov5_s-v61_fast_1xb64-50e_voc_20221017_234156.log.json) | -| YOLOv5-m | 512 | 64 | Yes | 12.0 | 70.1 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/voc/yolov5_m-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_fast_1xb64-50e_voc/yolov5_m-v61_fast_1xb64-50e_voc_20221017_114138-815c143a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_fast_1xb64-50e_voc/yolov5_m-v61_fast_1xb64-50e_voc_20221017_114138.log.json) | -| YOLOv5-l | 512 | 32 | Yes | 10.0 | 73.1 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/voc/yolov5_l-v61_fast_1xb32-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_fast_1xb32-50e_voc/yolov5_l-v61_fast_1xb32-50e_voc_20221017_045500-edc7e0d8.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_fast_1xb32-50e_voc/yolov5_l-v61_fast_1xb32-50e_voc_20221017_045500.log.json) | +| Backbone | size | Batchsize | AMP | Mem (GB) | box AP(COCO metric) | Config | Download | +| :------: | :--: | :-------: | :-: | :------: | :-----------------: | :-------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOv5-n | 512 | 64 | Yes | 3.5 | 51.2 | [config](./yolov5/voc/yolov5_n-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_fast_1xb64-50e_voc/yolov5_n-v61_fast_1xb64-50e_voc_20221017_234254-f1493430.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_n-v61_fast_1xb64-50e_voc/yolov5_n-v61_fast_1xb64-50e_voc_20221017_234254.log.json) | +| YOLOv5-s | 512 | 64 | Yes | 6.5 | 62.7 | [config](./yolov5/voc/yolov5_s-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_fast_1xb64-50e_voc/yolov5_s-v61_fast_1xb64-50e_voc_20221017_234156-0009b33e.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_s-v61_fast_1xb64-50e_voc/yolov5_s-v61_fast_1xb64-50e_voc_20221017_234156.log.json) | +| YOLOv5-m | 512 | 64 | Yes | 12.0 | 70.1 | [config](./yolov5/voc/yolov5_m-v61_fast_1xb64-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_fast_1xb64-50e_voc/yolov5_m-v61_fast_1xb64-50e_voc_20221017_114138-815c143a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_m-v61_fast_1xb64-50e_voc/yolov5_m-v61_fast_1xb64-50e_voc_20221017_114138.log.json) | +| YOLOv5-l | 512 | 32 | Yes | 10.0 | 73.1 | [config](./yolov5/voc/yolov5_l-v61_fast_1xb32-50e_voc.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_fast_1xb32-50e_voc/yolov5_l-v61_fast_1xb32-50e_voc_20221017_045500-edc7e0d8.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov5/yolov5_l-v61_fast_1xb32-50e_voc/yolov5_l-v61_fast_1xb32-50e_voc_20221017_045500.log.json) | **Note**: @@ -68,10 +74,10 @@ YOLOv5-l-P6 model structure Since the `iscrowd` annotation of the COCO dataset is not equivalent to `ignore`, we use the CrowdHuman dataset to verify that the YOLOv5 ignore logic is correct. -| Backbone | size | SyncBN | AMP | Mem (GB) | ignore_iof_thr | box AP50(CrowDHuman Metric) | MR | JI | Config | Download | -| :------: | :--: | :----: | :-: | :------: | :------------: | :-------------------------: | :--: | :---: | :-----------------------------------------------------------------------------------------------------------------------------: | :------: | -| YOLOv5-s | 640 | Yes | Yes | 2.6 | -1 | 85.79 | 48.7 | 75.33 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/crowdhuman/yolov5_s-v61_fast_8xb16-300e_crowdhuman.py) | | -| YOLOv5-s | 640 | Yes | Yes | 2.6 | 0.5 | 86.17 | 48.8 | 75.87 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov5/crowdhuman/yolov5_s-v61_8xb16-300e_ignore_crowdhuman.py) | | +| Backbone | size | SyncBN | AMP | Mem (GB) | ignore_iof_thr | box AP50(CrowDHuman Metric) | MR | JI | Config | Download | +| :------: | :--: | :----: | :-: | :------: | :------------: | :-------------------------: | :--: | :---: | :------------------------------------------------------------------------: | :------: | +| YOLOv5-s | 640 | Yes | Yes | 2.6 | -1 | 85.79 | 48.7 | 75.33 | [config](./yolov5/crowdhuman/yolov5_s-v61_fast_8xb16-300e_crowdhuman.py) | | +| YOLOv5-s | 640 | Yes | Yes | 2.6 | 0.5 | 86.17 | 48.8 | 75.87 | [config](./yolov5/crowdhuman/yolov5_s-v61_8xb16-300e_ignore_crowdhuman.py) | | **Note**: diff --git a/configs/yolov5/yolov5u/yolov5u_l_mask-refine_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_l_mask-refine_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..60c11feb --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_l_mask-refine_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,59 @@ +_base_ = './yolov5u_m_mask-refine_syncbn_fast_8xb16-300e_coco.py' + +# This config will refine bbox by mask while loading annotations and +# transforming after `YOLOv5RandomAffine` + +# ========================modified parameters====================== +deepen_factor = 1.00 +widen_factor = 1.00 + +mixup_prob = 0.15 +copypaste_prob = 0.3 + +# =======================Unmodified in most cases================== +img_scale = _base_.img_scale +pre_transform = _base_.pre_transform +last_transform = _base_.last_transform +affine_scale = _base_.affine_scale + +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) + +mosaic_affine_transform = [ + dict( + type='Mosaic', + img_scale=img_scale, + pad_val=114.0, + pre_transform=pre_transform), + dict(type='YOLOv5CopyPaste', prob=copypaste_prob), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + max_aspect_ratio=100., + scaling_ratio_range=(1 - affine_scale, 1 + affine_scale), + # img_scale is (width, height) + border=(-img_scale[0] // 2, -img_scale[1] // 2), + border_val=(114, 114, 114), + min_area_ratio=_base_.min_area_ratio, + use_mask_refine=_base_.use_mask2refine) +] + +train_pipeline = [ + *pre_transform, *mosaic_affine_transform, + dict( + type='YOLOv5MixUp', + prob=mixup_prob, + pre_transform=[*pre_transform, *mosaic_affine_transform]), + *last_transform +] + +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) diff --git a/configs/yolov5/yolov5u/yolov5u_l_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_l_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..22b9e881 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_l_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,18 @@ +_base_ = './yolov5u_s_syncbn_fast_8xb16-300e_coco.py' + +# ========================modified parameters====================== +# TODO: Update the training hyperparameters +deepen_factor = 1.0 +widen_factor = 1.0 + +# =======================Unmodified in most cases================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov5/yolov5u/yolov5u_m_mask-refine_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_m_mask-refine_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..ecc86fdd --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_m_mask-refine_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,79 @@ +_base_ = './yolov5u_s_mask-refine_syncbn_fast_8xb16-300e_coco.py' + +# This config will refine bbox by mask while loading annotations and +# transforming after `YOLOv5RandomAffine` + +# ========================modified parameters====================== +deepen_factor = 0.67 +widen_factor = 0.75 + +affine_scale = 0.9 +mixup_prob = 0.1 +copypaste_prob = 0.1 + +# =======================Unmodified in most cases================== +img_scale = _base_.img_scale +pre_transform = _base_.pre_transform +last_transform = _base_.last_transform + +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) + +mosaic_affine_transform = [ + dict( + type='Mosaic', + img_scale=img_scale, + pad_val=114.0, + pre_transform=pre_transform), + dict(type='YOLOv5CopyPaste', prob=copypaste_prob), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + max_aspect_ratio=100., + scaling_ratio_range=(1 - affine_scale, 1 + affine_scale), + # img_scale is (width, height) + border=(-img_scale[0] // 2, -img_scale[1] // 2), + border_val=(114, 114, 114), + min_area_ratio=_base_.min_area_ratio, + use_mask_refine=_base_.use_mask2refine) +] + +train_pipeline = [ + *pre_transform, *mosaic_affine_transform, + dict( + type='YOLOv5MixUp', + prob=mixup_prob, + pre_transform=[*pre_transform, *mosaic_affine_transform]), + *last_transform +] + +train_pipeline_stage2 = [ + *pre_transform, + dict(type='YOLOv5KeepRatioResize', scale=img_scale), + dict( + type='LetterResize', + scale=img_scale, + allow_scale_up=True, + pad_val=dict(img=114.0)), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + scaling_ratio_range=(1 - affine_scale, 1 + affine_scale), + max_aspect_ratio=_base_.max_aspect_ratio, + border_val=(114, 114, 114), + min_area_ratio=_base_.min_area_ratio, + use_mask_refine=_base_.use_mask2refine), *last_transform +] + +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) +_base_.custom_hooks[1].switch_pipeline = train_pipeline_stage2 diff --git a/configs/yolov5/yolov5u/yolov5u_m_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_m_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..0cfb3324 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_m_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,18 @@ +_base_ = './yolov5u_s_syncbn_fast_8xb16-300e_coco.py' + +# ========================modified parameters====================== +# TODO: Update the training hyperparameters +deepen_factor = 0.67 +widen_factor = 0.75 + +# =======================Unmodified in most cases================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov5/yolov5u/yolov5u_n_mask-refine_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_n_mask-refine_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..1ca21b65 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_n_mask-refine_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,20 @@ +_base_ = './yolov5u_s_mask-refine_syncbn_fast_8xb16-300e_coco.py' + +# This config will refine bbox by mask while loading annotations and +# transforming after `YOLOv5RandomAffine` + +# ========================modified parameters====================== +deepen_factor = 0.33 +widen_factor = 0.25 + +# ===============================Unmodified in most cases==================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov5/yolov5u/yolov5u_n_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_n_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..ad6a9f2e --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_n_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,17 @@ +_base_ = './yolov5u_s_syncbn_fast_8xb16-300e_coco.py' + +# ========================modified parameters====================== +deepen_factor = 0.33 +widen_factor = 0.25 + +# =======================Unmodified in most cases================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov5/yolov5u/yolov5u_s_mask-refine_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_s_mask-refine_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..5159c428 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_s_mask-refine_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,80 @@ +_base_ = './yolov5u_s_syncbn_fast_8xb16-300e_coco.py' + +# This config will refine bbox by mask while loading annotations and +# transforming after `YOLOv5RandomAffine` + +# ========================modified parameters====================== +use_mask2refine = True +min_area_ratio = 0.01 # YOLOv5RandomAffine + +# ===============================Unmodified in most cases==================== +pre_transform = [ + dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args), + dict( + type='LoadAnnotations', + with_bbox=True, + with_mask=True, + mask2bbox=use_mask2refine) +] + +last_transform = [ + # Delete gt_masks to avoid more computation + dict(type='RemoveDataElement', keys=['gt_masks']), + dict( + type='mmdet.Albu', + transforms=_base_.albu_train_transforms, + bbox_params=dict( + type='BboxParams', + format='pascal_voc', + label_fields=['gt_bboxes_labels', 'gt_ignore_flags']), + keymap={ + 'img': 'image', + 'gt_bboxes': 'bboxes' + }), + dict(type='YOLOv5HSVRandomAug'), + dict(type='mmdet.RandomFlip', prob=0.5), + dict( + type='mmdet.PackDetInputs', + meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', + 'flip_direction')) +] + +train_pipeline = [ + *pre_transform, + dict( + type='Mosaic', + img_scale=_base_.img_scale, + pad_val=114.0, + pre_transform=pre_transform), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale), + # img_scale is (width, height) + border=(-_base_.img_scale[0] // 2, -_base_.img_scale[1] // 2), + border_val=(114, 114, 114), + min_area_ratio=min_area_ratio, + use_mask_refine=use_mask2refine), + *last_transform +] + +train_pipeline_stage2 = [ + *pre_transform, + dict(type='YOLOv5KeepRatioResize', scale=_base_.img_scale), + dict( + type='LetterResize', + scale=_base_.img_scale, + allow_scale_up=True, + pad_val=dict(img=114.0)), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + scaling_ratio_range=(1 - _base_.affine_scale, 1 + _base_.affine_scale), + max_aspect_ratio=_base_.max_aspect_ratio, + border_val=(114, 114, 114)), *last_transform +] + +train_dataloader = dict(dataset=dict(pipeline=train_pipeline)) +_base_.custom_hooks[1].switch_pipeline = train_pipeline_stage2 diff --git a/configs/yolov5/yolov5u/yolov5u_s_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_s_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..17635aca --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_s_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,326 @@ +_base_ = ['../../_base_/default_runtime.py', '../../_base_/det_p5_tta.py'] + +# ========================Frequently modified parameters====================== +# -----data related----- +data_root = 'data/coco/' # Root path of data +# Path of train annotation file +train_ann_file = 'annotations/instances_train2017.json' +train_data_prefix = 'train2017/' # Prefix of train image path +# Path of val annotation file +val_ann_file = 'annotations/instances_val2017.json' +val_data_prefix = 'val2017/' # Prefix of val image path + +num_classes = 80 # Number of classes for classification +# Batch size of a single GPU during training +train_batch_size_per_gpu = 16 +# Worker to pre-fetch data for each single GPU during training +train_num_workers = 8 +# persistent_workers must be False if num_workers is 0 +persistent_workers = True + +# -----train val related----- +# Base learning rate for optim_wrapper. Corresponding to 8xb16=128 bs +base_lr = 0.01 +max_epochs = 300 # Maximum training epochs +# Disable mosaic augmentation for final 10 epochs (stage 2) +close_mosaic_epochs = 10 + +model_test_cfg = dict( + # The config of multi-label for multi-class prediction. + multi_label=True, + # The number of boxes before NMS + nms_pre=30000, + score_thr=0.001, # Threshold to filter out boxes. + nms=dict(type='nms', iou_threshold=0.7), # NMS type and threshold + max_per_img=300) # Max number of detections of each image + +# ========================Possible modified parameters======================== +# -----data related----- +img_scale = (640, 640) # width, height +# Dataset type, this will be used to define the dataset +dataset_type = 'YOLOv5CocoDataset' +# Batch size of a single GPU during validation +val_batch_size_per_gpu = 1 +# Worker to pre-fetch data for each single GPU during validation +val_num_workers = 2 + +# Config of batch shapes. Only on val. +# It means not used if batch_shapes_cfg is None. +batch_shapes_cfg = dict( + type='BatchShapePolicy', + batch_size=val_batch_size_per_gpu, + img_size=img_scale[0], + # The image scale of padding should be divided by pad_size_divisor + size_divisor=32, + # Additional paddings for pixel scale + extra_pad_ratio=0.5) + +# -----model related----- +# The scaling factor that controls the depth of the network structure +deepen_factor = 0.33 +# The scaling factor that controls the width of the network structure +widen_factor = 0.5 +# Strides of multi-scale prior box +strides = [8, 16, 32] +num_det_layers = 3 # The number of model output scales +norm_cfg = dict(type='BN', momentum=0.03, eps=0.001) # Normalization config + +# -----train val related----- +tal_topk = 10 # Number of bbox selected in each level +tal_alpha = 0.5 # A Hyper-parameter related to alignment_metrics +tal_beta = 6.0 # A Hyper-parameter related to alignment_metrics + +affine_scale = 0.5 # YOLOv5RandomAffine scaling ratio +# YOLOv5RandomAffine aspect ratio of width and height thres to filter bboxes +max_aspect_ratio = 100 +# TODO: Automatically scale loss_weight based on number of detection layers +loss_cls_weight = 0.5 +loss_bbox_weight = 7.5 +# Since the dfloss is implemented differently in the official +# and mmdet, we're going to divide loss_weight by 4. +loss_dfl_weight = 1.5 / 4 +lr_factor = 0.01 # Learning rate scaling factor +weight_decay = 0.001 +# Save model checkpoint and validation intervals +save_checkpoint_intervals = 10 +# The maximum checkpoints to keep. +max_keep_ckpts = 3 +# Single-scale training is recommended to +# be turned on, which can speed up training. +env_cfg = dict(cudnn_benchmark=True) + +# ===============================Unmodified in most cases==================== +model = dict( + type='YOLODetector', + data_preprocessor=dict( + type='YOLOv5DetDataPreprocessor', + mean=[0., 0., 0.], + std=[255., 255., 255.], + bgr_to_rgb=True), + backbone=dict( + type='YOLOv5CSPDarknet', + deepen_factor=deepen_factor, + widen_factor=widen_factor, + norm_cfg=norm_cfg, + act_cfg=dict(type='SiLU', inplace=True)), + neck=dict( + type='YOLOv5PAFPN', + deepen_factor=deepen_factor, + widen_factor=widen_factor, + in_channels=[256, 512, 1024], + out_channels=[256, 512, 1024], + num_csp_blocks=3, + norm_cfg=norm_cfg, + act_cfg=dict(type='SiLU', inplace=True)), + bbox_head=dict( + type='YOLOv8Head', + head_module=dict( + type='YOLOv8HeadModule', + num_classes=num_classes, + in_channels=[256, 512, 1024], + widen_factor=widen_factor, + reg_max=16, + norm_cfg=norm_cfg, + act_cfg=dict(type='SiLU', inplace=True), + featmap_strides=strides), + prior_generator=dict( + type='mmdet.MlvlPointGenerator', offset=0.5, strides=strides), + bbox_coder=dict(type='DistancePointBBoxCoder'), + # scaled based on number of detection layers + loss_cls=dict( + type='mmdet.CrossEntropyLoss', + use_sigmoid=True, + reduction='none', + loss_weight=loss_cls_weight), + loss_bbox=dict( + type='IoULoss', + iou_mode='ciou', + bbox_format='xyxy', + reduction='sum', + loss_weight=loss_bbox_weight, + return_iou=False), + loss_dfl=dict( + type='mmdet.DistributionFocalLoss', + reduction='mean', + loss_weight=loss_dfl_weight)), + train_cfg=dict( + assigner=dict( + type='BatchTaskAlignedAssigner', + num_classes=num_classes, + use_ciou=True, + topk=tal_topk, + alpha=tal_alpha, + beta=tal_beta, + eps=1e-9)), + test_cfg=model_test_cfg) + +albu_train_transforms = [ + dict(type='Blur', p=0.01), + dict(type='MedianBlur', p=0.01), + dict(type='ToGray', p=0.01), + dict(type='CLAHE', p=0.01) +] + +pre_transform = [ + dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args), + dict(type='LoadAnnotations', with_bbox=True) +] + +last_transform = [ + dict( + type='mmdet.Albu', + transforms=albu_train_transforms, + bbox_params=dict( + type='BboxParams', + format='pascal_voc', + label_fields=['gt_bboxes_labels', 'gt_ignore_flags']), + keymap={ + 'img': 'image', + 'gt_bboxes': 'bboxes' + }), + dict(type='YOLOv5HSVRandomAug'), + dict(type='mmdet.RandomFlip', prob=0.5), + dict( + type='mmdet.PackDetInputs', + meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', + 'flip_direction')) +] + +train_pipeline = [ + *pre_transform, + dict( + type='Mosaic', + img_scale=img_scale, + pad_val=114.0, + pre_transform=pre_transform), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + scaling_ratio_range=(1 - affine_scale, 1 + affine_scale), + max_aspect_ratio=max_aspect_ratio, + # img_scale is (width, height) + border=(-img_scale[0] // 2, -img_scale[1] // 2), + border_val=(114, 114, 114)), + *last_transform +] + +train_pipeline_stage2 = [ + *pre_transform, + dict(type='YOLOv5KeepRatioResize', scale=img_scale), + dict( + type='LetterResize', + scale=img_scale, + allow_scale_up=True, + pad_val=dict(img=114.0)), + dict( + type='YOLOv5RandomAffine', + max_rotate_degree=0.0, + max_shear_degree=0.0, + scaling_ratio_range=(1 - affine_scale, 1 + affine_scale), + max_aspect_ratio=max_aspect_ratio, + border_val=(114, 114, 114)), *last_transform +] + +train_dataloader = dict( + batch_size=train_batch_size_per_gpu, + num_workers=train_num_workers, + persistent_workers=persistent_workers, + pin_memory=True, + sampler=dict(type='DefaultSampler', shuffle=True), + collate_fn=dict(type='yolov5_collate'), + dataset=dict( + type=dataset_type, + data_root=data_root, + ann_file=train_ann_file, + data_prefix=dict(img=train_data_prefix), + filter_cfg=dict(filter_empty_gt=False, min_size=32), + pipeline=train_pipeline)) + +test_pipeline = [ + dict(type='LoadImageFromFile', file_client_args=_base_.file_client_args), + dict(type='YOLOv5KeepRatioResize', scale=img_scale), + dict( + type='LetterResize', + scale=img_scale, + allow_scale_up=False, + pad_val=dict(img=114)), + dict(type='LoadAnnotations', with_bbox=True, _scope_='mmdet'), + dict( + type='mmdet.PackDetInputs', + meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', + 'scale_factor', 'pad_param')) +] + +val_dataloader = dict( + batch_size=val_batch_size_per_gpu, + num_workers=val_num_workers, + persistent_workers=persistent_workers, + pin_memory=True, + drop_last=False, + sampler=dict(type='DefaultSampler', shuffle=False), + dataset=dict( + type=dataset_type, + data_root=data_root, + test_mode=True, + data_prefix=dict(img=val_data_prefix), + ann_file=val_ann_file, + pipeline=test_pipeline, + batch_shapes_cfg=batch_shapes_cfg)) + +test_dataloader = val_dataloader + +param_scheduler = None +optim_wrapper = dict( + type='OptimWrapper', + optimizer=dict( + type='SGD', + lr=base_lr, + momentum=0.937, + weight_decay=weight_decay, + nesterov=True, + batch_size_per_gpu=train_batch_size_per_gpu), + constructor='YOLOv5OptimizerConstructor') + +default_hooks = dict( + param_scheduler=dict( + type='YOLOv5ParamSchedulerHook', + scheduler_type='linear', + lr_factor=lr_factor, + max_epochs=max_epochs, + warmup_epochs=3.0, + warmup_momentum=0.8, + warmup_bias_lr=0.1), + checkpoint=dict( + type='CheckpointHook', + interval=save_checkpoint_intervals, + save_best='auto', + max_keep_ckpts=max_keep_ckpts)) + +custom_hooks = [ + dict( + type='EMAHook', + ema_type='ExpMomentumEMA', + momentum=0.0001, + update_buffers=True, + strict_load=False, + priority=49), + dict( + type='mmdet.PipelineSwitchHook', + switch_epoch=max_epochs - close_mosaic_epochs, + switch_pipeline=train_pipeline_stage2) +] + +val_evaluator = dict( + type='mmdet.CocoMetric', + proposal_nums=(100, 1, 10), + ann_file=data_root + val_ann_file, + metric='bbox') +test_evaluator = val_evaluator + +train_cfg = dict( + type='EpochBasedTrainLoop', + max_epochs=max_epochs, + val_interval=save_checkpoint_intervals) +val_cfg = dict(type='ValLoop') +test_cfg = dict(type='TestLoop') diff --git a/configs/yolov5/yolov5u/yolov5u_x_mask-refine_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_x_mask-refine_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..33092aa6 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_x_mask-refine_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,17 @@ +_base_ = './yolov5u_l_mask-refine_syncbn_fast_8xb16-300e_coco.py' + +# ========================modified parameters====================== +deepen_factor = 1.33 +widen_factor = 1.25 + +# =======================Unmodified in most cases================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov5/yolov5u/yolov5u_x_syncbn_fast_8xb16-300e_coco.py b/configs/yolov5/yolov5u/yolov5u_x_syncbn_fast_8xb16-300e_coco.py new file mode 100644 index 00000000..fd471fd4 --- /dev/null +++ b/configs/yolov5/yolov5u/yolov5u_x_syncbn_fast_8xb16-300e_coco.py @@ -0,0 +1,18 @@ +_base_ = './yolov5u_l_syncbn_fast_8xb16-300e_coco.py' + +# ========================modified parameters====================== +# TODO: Update the training hyperparameters +deepen_factor = 1.33 +widen_factor = 1.25 + +# =======================Unmodified in most cases================== +model = dict( + backbone=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + neck=dict( + deepen_factor=deepen_factor, + widen_factor=widen_factor, + ), + bbox_head=dict(head_module=dict(widen_factor=widen_factor))) diff --git a/configs/yolov6/README.md b/configs/yolov6/README.md index 4dac37f4..7ecda276 100644 --- a/configs/yolov6/README.md +++ b/configs/yolov6/README.md @@ -26,13 +26,13 @@ YOLOv6-l model structure ### COCO -| Backbone | Arch | Size | Epoch | SyncBN | AMP | Mem (GB) | Box AP | Config | Download | -| :------: | :--: | :--: | :---: | :----: | :-: | :------: | :----: | :---------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOv6-n | P5 | 640 | 400 | Yes | Yes | 6.04 | 36.2 | [config](../yolov6/yolov6_n_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_n_syncbn_fast_8xb32-400e_coco/yolov6_n_syncbn_fast_8xb32-400e_coco_20221030_202726-d99b2e82.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_n_syncbn_fast_8xb32-400e_coco/yolov6_n_syncbn_fast_8xb32-400e_coco_20221030_202726.log.json) | -| YOLOv6-t | P5 | 640 | 400 | Yes | Yes | 8.13 | 41.0 | [config](../yolov6/yolov6_t_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_t_syncbn_fast_8xb32-400e_coco/yolov6_t_syncbn_fast_8xb32-400e_coco_20221030_143755-cf0d278f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_t_syncbn_fast_8xb32-400e_coco/yolov6_t_syncbn_fast_8xb32-400e_coco_20221030_143755.log.json) | -| YOLOv6-s | P5 | 640 | 400 | Yes | Yes | 8.88 | 44.0 | [config](../yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035-932e1d91.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035.log.json) | -| YOLOv6-m | P5 | 640 | 300 | Yes | Yes | 16.69 | 48.4 | [config](../yolov6/yolov6_m_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_m_syncbn_fast_8xb32-300e_coco/yolov6_m_syncbn_fast_8xb32-300e_coco_20221109_182658-85bda3f4.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_m_syncbn_fast_8xb32-300e_coco/yolov6_m_syncbn_fast_8xb32-300e_coco_20221109_182658.log.json) | -| YOLOv6-l | P5 | 640 | 300 | Yes | Yes | 20.86 | 51.0 | [config](../yolov6/yolov6_l_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_l_syncbn_fast_8xb32-300e_coco/yolov6_l_syncbn_fast_8xb32-300e_coco_20221109_183156-91e3c447.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_l_syncbn_fast_8xb32-300e_coco/yolov6_l_syncbn_fast_8xb32-300e_coco_20221109_183156.log.json) | +| Backbone | Arch | Size | Epoch | SyncBN | AMP | Mem (GB) | Box AP | Config | Download | +| :------: | :--: | :--: | :---: | :----: | :-: | :------: | :----: | :-------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOv6-n | P5 | 640 | 400 | Yes | Yes | 6.04 | 36.2 | [config](./yolov6_n_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_n_syncbn_fast_8xb32-400e_coco/yolov6_n_syncbn_fast_8xb32-400e_coco_20221030_202726-d99b2e82.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_n_syncbn_fast_8xb32-400e_coco/yolov6_n_syncbn_fast_8xb32-400e_coco_20221030_202726.log.json) | +| YOLOv6-t | P5 | 640 | 400 | Yes | Yes | 8.13 | 41.0 | [config](./yolov6_t_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_t_syncbn_fast_8xb32-400e_coco/yolov6_t_syncbn_fast_8xb32-400e_coco_20221030_143755-cf0d278f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_t_syncbn_fast_8xb32-400e_coco/yolov6_t_syncbn_fast_8xb32-400e_coco_20221030_143755.log.json) | +| YOLOv6-s | P5 | 640 | 400 | Yes | Yes | 8.88 | 44.0 | [config](./yolov6_s_syncbn_fast_8xb32-400e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035-932e1d91.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_s_syncbn_fast_8xb32-400e_coco/yolov6_s_syncbn_fast_8xb32-400e_coco_20221102_203035.log.json) | +| YOLOv6-m | P5 | 640 | 300 | Yes | Yes | 16.69 | 48.4 | [config](./yolov6_m_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_m_syncbn_fast_8xb32-300e_coco/yolov6_m_syncbn_fast_8xb32-300e_coco_20221109_182658-85bda3f4.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_m_syncbn_fast_8xb32-300e_coco/yolov6_m_syncbn_fast_8xb32-300e_coco_20221109_182658.log.json) | +| YOLOv6-l | P5 | 640 | 300 | Yes | Yes | 20.86 | 51.0 | [config](./yolov6_l_syncbn_fast_8xb32-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_l_syncbn_fast_8xb32-300e_coco/yolov6_l_syncbn_fast_8xb32-300e_coco_20221109_183156-91e3c447.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov6/yolov6_l_syncbn_fast_8xb32-300e_coco/yolov6_l_syncbn_fast_8xb32-300e_coco_20221109_183156.log.json) | **Note**: diff --git a/configs/yolov7/README.md b/configs/yolov7/README.md index e4f81261..17003144 100644 --- a/configs/yolov7/README.md +++ b/configs/yolov7/README.md @@ -21,13 +21,13 @@ YOLOv7-l-P5 model structure ### COCO -| Backbone | Arch | Size | SyncBN | AMP | Mem (GB) | Box AP | Config | Download | -| :---------: | :--: | :--: | :----: | :-: | :------: | :----: | :----------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOv7-tiny | P5 | 640 | Yes | Yes | 2.7 | 37.5 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco/yolov7_tiny_syncbn_fast_8x16b-300e_coco_20221126_102719-0ee5bbdf.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco/yolov7_tiny_syncbn_fast_8x16b-300e_coco_20221126_102719.log.json) | -| YOLOv7-l | P5 | 640 | Yes | Yes | 10.3 | 50.9 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco/yolov7_l_syncbn_fast_8x16b-300e_coco_20221123_023601-8113c0eb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco/yolov7_l_syncbn_fast_8x16b-300e_coco_20221123_023601.log.json) | -| YOLOv7-x | P5 | 640 | Yes | Yes | 13.7 | 52.8 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco/yolov7_x_syncbn_fast_8x16b-300e_coco_20221124_215331-ef949a68.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco/yolov7_x_syncbn_fast_8x16b-300e_coco_20221124_215331.log.json) | -| YOLOv7-w | P6 | 1280 | Yes | Yes | 27.0 | 54.1 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco/yolov7_w-p6_syncbn_fast_8x16b-300e_coco_20221123_053031-a68ef9d2.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco/yolov7_w-p6_syncbn_fast_8x16b-300e_coco_20221123_053031.log.json) | -| YOLOv7-e | P6 | 1280 | Yes | Yes | 42.5 | 55.1 | [config](https://github.com/open-mmlab/mmyolo/tree/main/configs/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco/yolov7_e-p6_syncbn_fast_8x16b-300e_coco_20221126_102636-34425033.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco/yolov7_e-p6_syncbn_fast_8x16b-300e_coco_20221126_102636.log.json) | +| Backbone | Arch | Size | SyncBN | AMP | Mem (GB) | Box AP | Config | Download | +| :---------: | :--: | :--: | :----: | :-: | :------: | :----: | :----------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOv7-tiny | P5 | 640 | Yes | Yes | 2.7 | 37.5 | [config](./yolov7_tiny_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco/yolov7_tiny_syncbn_fast_8x16b-300e_coco_20221126_102719-0ee5bbdf.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco/yolov7_tiny_syncbn_fast_8x16b-300e_coco_20221126_102719.log.json) | +| YOLOv7-l | P5 | 640 | Yes | Yes | 10.3 | 50.9 | [config](./yolov7_l_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco/yolov7_l_syncbn_fast_8x16b-300e_coco_20221123_023601-8113c0eb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco/yolov7_l_syncbn_fast_8x16b-300e_coco_20221123_023601.log.json) | +| YOLOv7-x | P5 | 640 | Yes | Yes | 13.7 | 52.8 | [config](./yolov7_x_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco/yolov7_x_syncbn_fast_8x16b-300e_coco_20221124_215331-ef949a68.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco/yolov7_x_syncbn_fast_8x16b-300e_coco_20221124_215331.log.json) | +| YOLOv7-w | P6 | 1280 | Yes | Yes | 27.0 | 54.1 | [config](./yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco/yolov7_w-p6_syncbn_fast_8x16b-300e_coco_20221123_053031-a68ef9d2.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco/yolov7_w-p6_syncbn_fast_8x16b-300e_coco_20221123_053031.log.json) | +| YOLOv7-e | P6 | 1280 | Yes | Yes | 42.5 | 55.1 | [config](./yolov7_e-p6_syncbn_fast_8x16b-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco/yolov7_e-p6_syncbn_fast_8x16b-300e_coco_20221126_102636-34425033.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco/yolov7_e-p6_syncbn_fast_8x16b-300e_coco_20221126_102636.log.json) | **Note**: In the official YOLOv7 code, the `random_perspective` data augmentation in COCO object detection task training uses mask annotation information, which leads to higher performance. Object detection should not use mask annotation, so only box annotation information is used in `MMYOLO`. We will use the mask annotation information in the instance segmentation task. diff --git a/configs/yolov8/README.md b/configs/yolov8/README.md index 25899768..766aa991 100644 --- a/configs/yolov8/README.md +++ b/configs/yolov8/README.md @@ -20,18 +20,18 @@ YOLOv8-P5 model structure ### COCO -| Backbone | Arch | size | Mask Refine | SyncBN | AMP | Mem (GB) | box AP | TTA box AP | Config | Download | -| :------: | :--: | :--: | :---------: | :----: | :-: | :------: | :---------: | :--------: | :---------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOv8-n | P5 | 640 | No | Yes | Yes | 2.8 | 37.2 | | [config](../yolov8/yolov8_n_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_syncbn_fast_8xb16-500e_coco/yolov8_n_syncbn_fast_8xb16-500e_coco_20230114_131804-88c11cdb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_syncbn_fast_8xb16-500e_coco/yolov8_n_syncbn_fast_8xb16-500e_coco_20230114_131804.log.json) | -| YOLOv8-n | P5 | 640 | Yes | Yes | Yes | 2.5 | 37.4 (+0.2) | 39.9 | [config](../yolov8/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_101206-b975b1cd.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_101206.log.json) | -| YOLOv8-s | P5 | 640 | No | Yes | Yes | 4.0 | 44.2 | | [config](../yolov8/yolov8_s_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_syncbn_fast_8xb16-500e_coco/yolov8_s_syncbn_fast_8xb16-500e_coco_20230117_180101-5aa5f0f1.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_syncbn_fast_8xb16-500e_coco/yolov8_s_syncbn_fast_8xb16-500e_coco_20230117_180101.log.json) | -| YOLOv8-s | P5 | 640 | Yes | Yes | Yes | 4.0 | 45.1 (+0.9) | 46.8 | [config](../yolov8/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_095938-ce3c1b3f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_095938.log.json) | -| YOLOv8-m | P5 | 640 | No | Yes | Yes | 7.2 | 49.8 | | [config](../yolov8/yolov8_m_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_syncbn_fast_8xb16-500e_coco/yolov8_m_syncbn_fast_8xb16-500e_coco_20230115_192200-c22e560a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_syncbn_fast_8xb16-500e_coco/yolov8_m_syncbn_fast_8xb16-500e_coco_20230115_192200.log.json) | -| YOLOv8-m | P5 | 640 | Yes | Yes | Yes | 7.0 | 50.6 (+0.8) | 52.3 | [config](../yolov8/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_223400-f40abfcd.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_223400.log.json) | -| YOLOv8-l | P5 | 640 | No | Yes | Yes | 9.8 | 52.1 | | [config](../yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco/yolov8_l_syncbn_fast_8xb16-500e_coco_20230217_182526-189611b6.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco/yolov8_l_syncbn_fast_8xb16-500e_coco_20230217_182526.log.json) | -| YOLOv8-l | P5 | 640 | Yes | Yes | Yes | 9.1 | 53.0 (+0.9) | 54.4 | [config](../yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120100-5881dec4.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120100.log.json) | -| YOLOv8-x | P5 | 640 | No | Yes | Yes | 12.2 | 52.7 | | [config](../yolov8/yolov8_x_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_syncbn_fast_8xb16-500e_coco/yolov8_x_syncbn_fast_8xb16-500e_coco_20230218_023338-5674673c.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_syncbn_fast_8xb16-500e_coco/yolov8_x_syncbn_fast_8xb16-500e_coco_20230218_023338.log.json) | -| YOLOv8-x | P5 | 640 | Yes | Yes | Yes | 12.4 | 54.0 (+1.3) | 55.0 | [config](../yolov8/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120411-079ca8d1.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120411.log.json) | +| Backbone | Arch | size | Mask Refine | SyncBN | AMP | Mem (GB) | box AP | TTA box AP | Config | Download | +| :------: | :--: | :--: | :---------: | :----: | :-: | :------: | :---------: | :--------: | :-------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOv8-n | P5 | 640 | No | Yes | Yes | 2.8 | 37.2 | | [config](./yolov8_n_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_syncbn_fast_8xb16-500e_coco/yolov8_n_syncbn_fast_8xb16-500e_coco_20230114_131804-88c11cdb.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_syncbn_fast_8xb16-500e_coco/yolov8_n_syncbn_fast_8xb16-500e_coco_20230114_131804.log.json) | +| YOLOv8-n | P5 | 640 | Yes | Yes | Yes | 2.5 | 37.4 (+0.2) | 39.9 | [config](./yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_101206-b975b1cd.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_n_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_101206.log.json) | +| YOLOv8-s | P5 | 640 | No | Yes | Yes | 4.0 | 44.2 | | [config](./yolov8_s_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_syncbn_fast_8xb16-500e_coco/yolov8_s_syncbn_fast_8xb16-500e_coco_20230117_180101-5aa5f0f1.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_syncbn_fast_8xb16-500e_coco/yolov8_s_syncbn_fast_8xb16-500e_coco_20230117_180101.log.json) | +| YOLOv8-s | P5 | 640 | Yes | Yes | Yes | 4.0 | 45.1 (+0.9) | 46.8 | [config](./yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_095938-ce3c1b3f.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_s_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_095938.log.json) | +| YOLOv8-m | P5 | 640 | No | Yes | Yes | 7.2 | 49.8 | | [config](./yolov8_m_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_syncbn_fast_8xb16-500e_coco/yolov8_m_syncbn_fast_8xb16-500e_coco_20230115_192200-c22e560a.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_syncbn_fast_8xb16-500e_coco/yolov8_m_syncbn_fast_8xb16-500e_coco_20230115_192200.log.json) | +| YOLOv8-m | P5 | 640 | Yes | Yes | Yes | 7.0 | 50.6 (+0.8) | 52.3 | [config](./yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_223400-f40abfcd.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_m_mask-refine_syncbn_fast_8xb16-500e_coco_20230216_223400.log.json) | +| YOLOv8-l | P5 | 640 | No | Yes | Yes | 9.8 | 52.1 | | [config](./yolov8_l_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco/yolov8_l_syncbn_fast_8xb16-500e_coco_20230217_182526-189611b6.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco/yolov8_l_syncbn_fast_8xb16-500e_coco_20230217_182526.log.json) | +| YOLOv8-l | P5 | 640 | Yes | Yes | Yes | 9.1 | 53.0 (+0.9) | 54.4 | [config](./yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120100-5881dec4.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120100.log.json) | +| YOLOv8-x | P5 | 640 | No | Yes | Yes | 12.2 | 52.7 | | [config](./yolov8_x_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_syncbn_fast_8xb16-500e_coco/yolov8_x_syncbn_fast_8xb16-500e_coco_20230218_023338-5674673c.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_syncbn_fast_8xb16-500e_coco/yolov8_x_syncbn_fast_8xb16-500e_coco_20230218_023338.log.json) | +| YOLOv8-x | P5 | 640 | Yes | Yes | Yes | 12.4 | 54.0 (+1.3) | 55.0 | [config](./yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120411-079ca8d1.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_x_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120411.log.json) | **Note** diff --git a/configs/yolox/README.md b/configs/yolox/README.md index 11f9e307..d54bcf8c 100644 --- a/configs/yolox/README.md +++ b/configs/yolox/README.md @@ -19,16 +19,16 @@ YOLOX-l model structure ## 🥳 🚀 Results and Models -| Backbone | Size | Batch Size | AMP | RTMDet-Hyp | Mem (GB) | Box AP | Config | Download | -| :--------: | :--: | :--------: | :-: | :--------: | :------: | :---------: | :-----------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| YOLOX-tiny | 416 | 8xb8 | No | No | 2.8 | 32.7 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_tiny_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_8xb8-300e_coco/yolox_tiny_8xb8-300e_coco_20220919_090908-0e40a6fc.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_8xb8-300e_coco/yolox_tiny_8xb8-300e_coco_20220919_090908.log.json) | -| YOLOX-tiny | 416 | 8xb32 | Yes | Yes | 4.9 | 34.3 (+1.6) | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco_20230210_143637-4c338102.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco_20230210_143637.log.json) | -| YOLOX-s | 640 | 8xb8 | Yes | No | 2.9 | 40.7 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_s_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb8-300e_coco/yolox_s_fast_8xb8-300e_coco_20230213_142600-2b224d8b.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb8-300e_coco/yolox_s_fast_8xb8-300e_coco_20230213_142600.log.json) | -| YOLOX-s | 640 | 8xb32 | Yes | Yes | 9.8 | 41.9 (+1.2) | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco_20230210_134645-3a8dfbd7.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco_20230210_134645.log.json) | -| YOLOX-m | 640 | 8xb8 | Yes | No | 4.9 | 46.9 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_m_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb8-300e_coco/yolox_m_fast_8xb8-300e_coco_20230213_160218-a71a6b25.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb8-300e_coco/yolox_m_fast_8xb8-300e_coco_20230213_160218.log.json) | -| YOLOX-m | 640 | 8xb32 | Yes | Yes | 17.6 | 47.5 (+0.6) | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco_20230210_144328-e657e182.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco_20230210_144328.log.json) | -| YOLOX-l | 640 | 8xb8 | Yes | No | 8.0 | 50.1 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_l_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_l_fast__8xb8-300e_coco/yolox_l_fast_8xb8-300e_coco_20230213_160715-c731eb1c.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_l_fast_8xb8-300e_coco/yolox_l_fast_8xb8-300e_coco_20230213_160715.log.json) | -| YOLOX-x | 640 | 8xb8 | Yes | No | 9.8 | 51.4 | [config](https://github.com/open-mmlab/mmyolo/tree/dev/configs/yolox/yolox_x_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_x_fast_8xb8-300e_coco/yolox_x_fast_8xb8-300e_coco_20230215_133950-1d509fab.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_x_fast_8xb8-300e_coco/yolox_x_fast_8xb8-300e_coco_20230215_133950.log.json) | +| Backbone | Size | Batch Size | AMP | RTMDet-Hyp | Mem (GB) | Box AP | Config | Download | +| :--------: | :--: | :--------: | :-: | :--------: | :------: | :---------: | :-------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | +| YOLOX-tiny | 416 | 8xb8 | No | No | 2.8 | 32.7 | [config](./yolox_tiny_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_8xb8-300e_coco/yolox_tiny_8xb8-300e_coco_20220919_090908-0e40a6fc.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_8xb8-300e_coco/yolox_tiny_8xb8-300e_coco_20220919_090908.log.json) | +| YOLOX-tiny | 416 | 8xb32 | Yes | Yes | 4.9 | 34.3 (+1.6) | [config](./yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco_20230210_143637-4c338102.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco/yolox_tiny_fast_8xb32-300e-rtmdet-hyp_coco_20230210_143637.log.json) | +| YOLOX-s | 640 | 8xb8 | Yes | No | 2.9 | 40.7 | [config](./yolox_s_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb8-300e_coco/yolox_s_fast_8xb8-300e_coco_20230213_142600-2b224d8b.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb8-300e_coco/yolox_s_fast_8xb8-300e_coco_20230213_142600.log.json) | +| YOLOX-s | 640 | 8xb32 | Yes | Yes | 9.8 | 41.9 (+1.2) | [config](./yolox_s_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco_20230210_134645-3a8dfbd7.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco/yolox_s_fast_8xb32-300e-rtmdet-hyp_coco_20230210_134645.log.json) | +| YOLOX-m | 640 | 8xb8 | Yes | No | 4.9 | 46.9 | [config](./yolox_m_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb8-300e_coco/yolox_m_fast_8xb8-300e_coco_20230213_160218-a71a6b25.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb8-300e_coco/yolox_m_fast_8xb8-300e_coco_20230213_160218.log.json) | +| YOLOX-m | 640 | 8xb32 | Yes | Yes | 17.6 | 47.5 (+0.6) | [config](./yolox_m_fast_8xb32-300e-rtmdet-hyp_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco_20230210_144328-e657e182.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco/yolox_m_fast_8xb32-300e-rtmdet-hyp_coco_20230210_144328.log.json) | +| YOLOX-l | 640 | 8xb8 | Yes | No | 8.0 | 50.1 | [config](./yolox_l_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_l_fast__8xb8-300e_coco/yolox_l_fast_8xb8-300e_coco_20230213_160715-c731eb1c.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_l_fast_8xb8-300e_coco/yolox_l_fast_8xb8-300e_coco_20230213_160715.log.json) | +| YOLOX-x | 640 | 8xb8 | Yes | No | 9.8 | 51.4 | [config](./yolox_x_fast_8xb8-300e_coco.py) | [model](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_x_fast_8xb8-300e_coco/yolox_x_fast_8xb8-300e_coco_20230215_133950-1d509fab.pth) \| [log](https://download.openmmlab.com/mmyolo/v0/yolox/yolox_x_fast_8xb8-300e_coco/yolox_x_fast_8xb8-300e_coco_20230215_133950.log.json) | YOLOX uses a default training configuration of `8xbs8` which results in a long training time, we expect it to use `8xbs32` to speed up the training and not cause a decrease in mAP. We modified `train_batch_size_per_gpu` from 8 to 32, `batch_augments_interval` from 10 to 1 and `base_lr` from 0.01 to 0.04 under YOLOX-s default configuration based on the linear scaling rule, which resulted in mAP degradation. Finally, I found that using RTMDet's training hyperparameter can improve performance in YOLOX Tiny/S/M, which also validates the superiority of RTMDet's training hyperparameter. diff --git a/tools/model_converters/yolov5u_to_mmyolo.py b/tools/model_converters/yolov5u_to_mmyolo.py new file mode 100644 index 00000000..806c76cb --- /dev/null +++ b/tools/model_converters/yolov5u_to_mmyolo.py @@ -0,0 +1,88 @@ +# Copyright (c) OpenMMLab. All rights reserved. +import argparse +from collections import OrderedDict + +import torch + +convert_dict_p5 = { + 'model.0': 'backbone.stem', + 'model.1': 'backbone.stage1.0', + 'model.2': 'backbone.stage1.1', + 'model.3': 'backbone.stage2.0', + 'model.4': 'backbone.stage2.1', + 'model.5': 'backbone.stage3.0', + 'model.6': 'backbone.stage3.1', + 'model.7': 'backbone.stage4.0', + 'model.8': 'backbone.stage4.1', + 'model.9': 'backbone.stage4.2', + 'model.10': 'neck.reduce_layers.2', + 'model.13': 'neck.top_down_layers.0.0', + 'model.14': 'neck.top_down_layers.0.1', + 'model.17': 'neck.top_down_layers.1', + 'model.18': 'neck.downsample_layers.0', + 'model.20': 'neck.bottom_up_layers.0', + 'model.21': 'neck.downsample_layers.1', + 'model.23': 'neck.bottom_up_layers.1', + 'model.24': 'bbox_head.head_module', +} + + +def convert(src, dst): + """Convert keys in pretrained YOLOv5u models to mmyolo style.""" + convert_dict = convert_dict_p5 + + print('Converting P5 model') + try: + yolov5_model = torch.load(src)['model'] + blobs = yolov5_model.state_dict() + except ModuleNotFoundError: + raise RuntimeError( + 'This script must be placed under the ultralytics repo,' + ' because loading the official pretrained model need' + ' `model.py` to build model.') + state_dict = OrderedDict() + + for key, weight in blobs.items(): + + num, module = key.split('.')[1:3] + prefix = f'model.{num}' + new_key = key.replace(prefix, convert_dict[prefix]) + + if '.m.' in new_key: + new_key = new_key.replace('.m.', '.blocks.') + new_key = new_key.replace('.cv', '.conv') + elif 'bbox_head.head_module' in new_key: + new_key = new_key.replace('.cv2', '.reg_preds') + new_key = new_key.replace('.cv3', '.cls_preds') + elif 'backbone.stage4.2' in new_key: + new_key = new_key.replace('.cv', '.conv') + else: + new_key = new_key.replace('.cv1', '.main_conv') + new_key = new_key.replace('.cv2', '.short_conv') + new_key = new_key.replace('.cv3', '.final_conv') + + if 'bbox_head.head_module.dfl.conv.weight' == new_key: + print('Drop "bbox_head.head_module.dfl.conv.weight", ' + 'because it is useless') + continue + state_dict[new_key] = weight + print(f'Convert {key} to {new_key}') + + # save checkpoint + checkpoint = dict() + checkpoint['state_dict'] = state_dict + torch.save(checkpoint, dst) + + +# Note: This script must be placed under the ultralytics repo to run. +def main(): + parser = argparse.ArgumentParser(description='Convert model keys') + parser.add_argument( + '--src', default='yolov5su.pt', help='src yolov5u model path') + parser.add_argument('--dst', default='mmyolov5su.pth', help='save path') + args = parser.parse_args() + convert(args.src, args.dst) + + +if __name__ == '__main__': + main() diff --git a/tools/model_converters/yolov8_to_mmyolo.py b/tools/model_converters/yolov8_to_mmyolo.py index d1541367..df0c514b 100644 --- a/tools/model_converters/yolov8_to_mmyolo.py +++ b/tools/model_converters/yolov8_to_mmyolo.py @@ -75,7 +75,7 @@ def convert(src, dst): torch.save(checkpoint, dst) -# Note: This script must be placed under the YOLOv8 repo to run. +# Note: This script must be placed under the ultralytics repo to run. def main(): parser = argparse.ArgumentParser(description='Convert model keys') parser.add_argument(