mirrors
/
mmdetection
mirror of https://github.com/open-mmlab/mmdetection.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Release YOLOX model (#6698) 

* Release YOLOX model

* update

* update

* update

* update
pull/6774/head^2
Haian Huang(深度眸) 2021-12-08 19:48:02 +08:00 committed by GitHub
parent d5f40aaeae
commit 246137532c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 43 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
configs/yolox/README.md
View File

@ -31,9 +31,14 @@ In this report, we present some experienced improvements to YOLO series, forming
| Backbone | size | Mem (GB) | box AP | Config | Download |
|:---------:|:-------:|:-------:|:-------:|:--------:|:------:|
| YOLOX-tiny | 416 | 3.5 | 32.0 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_tiny_8x8_300e_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_tiny_8x8_300e_coco/yolox_tiny_8x8_300e_coco_20211124_171234-b4047906.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_tiny_8x8_300e_coco/yolox_tiny_8x8_300e_coco_20211124_171234.log.json) |
| YOLOX-s | 640 | 7.6 | 40.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_s_8x8_300e_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_20211121_095711.log.json) |
| YOLOX-l | 640 | 19.9 | 49.4 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_l_8x8_300e_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_l_8x8_300e_coco/yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_l_8x8_300e_coco/yolox_l_8x8_300e_coco_20211126_140236.log.json) |
| YOLOX-x | 640 | 28.1 | 50.9 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_x_8x8_300e_coco.py) |[model](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254.log.json) |
**Note**:
1. The test score threshold is 0.001.
1. The test score threshold is 0.001, and the box AP indicates the best AP.
2. Due to the need for pre-training weights, we cannot reproduce the performance of the `yolox-nano` model. Please refer to https://github.com/Megvii-BaseDetection/YOLOX/issues/674 for more information.
3. We also trained the model by the official release of YOLOX based on [Megvii-BaseDetection/YOLOX#735](https://github.com/Megvii-BaseDetection/YOLOX/issues/735) with commit ID [38c633](https://github.com/Megvii-BaseDetection/YOLOX/tree/38c633bf176462ee42b110c70e4ffe17b5753208). We found that the best AP of `YOLOX-tiny`, `YOLOX-s`, `YOLOX-l`, and `YOLOX-x` is 31.8, 40.3, 49.2, and 50.9, respectively. The performance is consistent with that of our re-implementation (see Table above) but still has a gap (0.3~0.8 AP) in comparison with the reported performance in their [README](https://github.com/Megvii-BaseDetection/YOLOX/blob/38c633bf176462ee42b110c70e4ffe17b5753208/README.md#benchmark).

36
configs/yolox/metafile.yml
View File

@ -32,3 +32,39 @@ Models:
Metrics:
box AP: 40.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_s_8x8_300e_coco/yolox_s_8x8_300e_coco_20211121_095711-4592a793.pth
- Name: yolox_l_8x8_300e_coco
In Collection: YOLOX
Config: configs/yolox/yolox_l_8x8_300e_coco.py
Metadata:
Training Memory (GB): 19.9
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 49.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_l_8x8_300e_coco/yolox_l_8x8_300e_coco_20211126_140236-d3bd2b23.pth
- Name: yolox_x_8x8_300e_coco
In Collection: YOLOX
Config: configs/yolox/yolox_x_8x8_300e_coco.py
Metadata:
Training Memory (GB): 28.1
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 50.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_x_8x8_300e_coco/yolox_x_8x8_300e_coco_20211126_140254-1ef88d67.pth
- Name: yolox_tiny_8x8_300e_coco
In Collection: YOLOX
Config: configs/yolox/yolox_tiny_8x8_300e_coco.py
Metadata:
Training Memory (GB): 3.5
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 32.0
Weights: https://download.openmmlab.com/mmdetection/v2.0/yolox/yolox_tiny_8x8_300e_coco/yolox_tiny_8x8_300e_coco_20211124_171234-b4047906.pth

1
mmdet/datasets/pipelines/transforms.py
View File

@ -2201,6 +2201,7 @@ class MixUp:
"""MixUp data augmentation.
.. code:: text
mixup transform
+------------------------------+
| mixup image | |