forked from open-mmlab/mmdetection
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add configs and benchmarks. (open-mmlab#2446)
* add configs for all models * fix some configs * Add benchmark models * update some benchmarks * Fix retina config * add more benchmarks * update MODEL_ZOO.md * fix cascade mask num_class bug * change caffe pretrained url * fix paramwise_cfg bug * fix paramwise cfg * restrict minimum h and w in crop_and_resize * add grad clip for fcos * add grad clip for ga retinanet * fix grad clip * fix img norm * fix rpn loss bbox * fix rpn proposal num * fix url * clean * update comparison * minor update * add grad clip for guided anchoring * fix some typos * add inference time details * clean Co-authored-by: ZwwWayne <wayne.zw@outlook.com>
- Loading branch information
Showing
192 changed files
with
1,840 additions
and
694 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| ## Results and Models | ||
|
|
||
| | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Download | | ||
| |:---------:|:-------:|:-------:|:--------:|:--------------:|:------:|:-------:|:--------:| | ||
| | R-50 | pytorch | 1x | 4.4 | 11.6 | 38.0 | 34.5 |[model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208-ab203bcd.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/albu_example/mask_rcnn_r50_fpn_albu_1x_coco/mask_rcnn_r50_fpn_albu_1x_coco_20200208_225520.log.json) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| # Cascade R-CNN: High Quality Object Detection and Instance Segmentation | ||
|
|
||
| ## Introduction | ||
| ``` | ||
| @article{Cai_2019, | ||
| title={Cascade R-CNN: High Quality Object Detection and Instance Segmentation}, | ||
| ISSN={1939-3539}, | ||
| url={http://dx.doi.org/10.1109/tpami.2019.2956516}, | ||
| DOI={10.1109/tpami.2019.2956516}, | ||
| journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, | ||
| publisher={Institute of Electrical and Electronics Engineers (IEEE)}, | ||
| author={Cai, Zhaowei and Vasconcelos, Nuno}, | ||
| year={2019}, | ||
| pages={1–1} | ||
| } | ||
| ``` | ||
|
|
||
| ## Results and models | ||
|
|
||
| ### Cascade R-CNN | ||
|
|
||
| | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Download | | ||
| | :-------------: | :-----: | :-----: | :------: | :------------: | :----: |:--------:| | ||
| | R-50-FPN | caffe | 1x | | | | | | ||
| | R-50-FPN | pytorch | 1x | 4.4 | 14.3 | 40.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco/cascade_rcnn_r50_fpn_1x_coco_20200316-3dc56deb.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco/cascade_rcnn_r50_fpn_1x_coco_20200316_214748.log.json) | | ||
| | R-50-FPN | pytorch | 20e | | | | | | ||
| | R-101-FPN | caffe | 1x | | | | | | ||
| | R-101-FPN | pytorch | 1x | 6.4 | 11.6 | 42.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco/cascade_rcnn_r101_fpn_1x_coco_20200317-0b6a2fbf.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco/cascade_rcnn_r101_fpn_1x_coco_20200317_101744.log.json) | | ||
| | R-101-FPN | pytorch | 20e | | | | | | ||
| | X-101-32x4d-FPN | pytorch | 1x | 7.6 | 10.2 | 43.7 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316-95c2deb6.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_1x_coco/cascade_rcnn_x101_32x4d_fpn_1x_coco_20200316_055608.log.json) | | ||
| | X-101-32x4d-FPN | pytorch | 20e | | | | | | ||
| | X-101-64x4d-FPN | pytorch | 1x | | | | | | ||
| | X-101-64x4d-FPN | pytorch | 20e | | | | | | ||
|
|
||
|
|
||
| ### Cascade Mask R-CNN | ||
|
|
||
| | Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Download | | ||
| | :-------------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :----------------: | | ||
| | R-50-C4 | caffe | 1x | | | | | | | ||
| | R-50-FPN | caffe | 1x | | | | | | | ||
| | R-50-FPN | pytorch | 1x | 6.0 | 8.5 | 41.2 | 35.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco/cascade_mask_rcnn_r50_fpn_1x_coco_20200203-9d4dcb24.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco/cascade_mask_rcnn_r50_fpn_1x_coco_20200203_170449.log.json) | | ||
| | R-50-FPN | pytorch | 20e | | | | | | | ||
| | R-101-FPN | caffe | 1x | | | | | | | ||
| | R-101-FPN | pytorch | 1x | 7.9 | 7.2 | 42.9 | 37.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco/cascade_mask_rcnn_r101_fpn_1x_coco_20200203-befdf6ee.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_r101_fpn_1x_coco/cascade_mask_rcnn_r101_fpn_1x_coco_20200203_092521.log.json) | | ||
| | R-101-FPN | pytorch | 20e | | | | | | | ||
| | X-101-32x4d-FPN | pytorch | 1x | 9.2 | 6.8 | 44.3 | 38.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco_20200201-0f411b1f.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_1x_coco_20200201_052416.log.json) | | ||
| | X-101-32x4d-FPN | pytorch | 20e | | | | | | | ||
| | X-101-64x4d-FPN | pytorch | 1x | 12.2 | 5.7 | 45.3 | 39.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco_20200203-9a2db89d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco/cascade_mask_rcnn_x101_64x4d_fpn_1x_coco_20200203_044059.log.json) | | ||
| | X-101-64x4d-FPN | pytorch | 20e | | | | | | | ||
|
|
||
| **Notes:** | ||
|
|
||
| - The `20e` schedule in Cascade (Mask) R-CNN indicates decreasing the lr at 16 and 19 epochs, with a total of 20 epochs. |
3 changes: 3 additions & 0 deletions
3
configs/cascade_rcnn/cascade_mask_rcnn_r101_caffe_fpn_1x_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,3 @@ | ||
| _base_ = './cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py' | ||
| model = dict( | ||
| pretrained='open-mmlab://resnet101_caffe_bgr', backbone=dict(depth=101)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,2 @@ | ||
| _base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py' | ||
| model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) |
38 changes: 38 additions & 0 deletions
38
configs/cascade_rcnn/cascade_mask_rcnn_r50_caffe_fpn_1x_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| _base_ = ['./cascade_mask_rcnn_r50_fpn_1x_coco.py'] | ||
|
|
||
| model = dict( | ||
| pretrained='open-mmlab://resnet50_caffe_bgr', | ||
| backbone=dict( | ||
| norm_cfg=dict(requires_grad=False), norm_eval=True, style='caffe')) | ||
|
|
||
| img_norm_cfg = dict( | ||
| mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) | ||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='LoadAnnotations', with_bbox=True, with_mask=True), | ||
| dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), | ||
| dict(type='RandomFlip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='DefaultFormatBundle'), | ||
| dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict( | ||
| type='MultiScaleFlipAug', | ||
| img_scale=(1333, 800), | ||
| flip=False, | ||
| transforms=[ | ||
| dict(type='Resize', keep_ratio=True), | ||
| dict(type='RandomFlip'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='ImageToTensor', keys=['img']), | ||
| dict(type='Collect', keys=['img']), | ||
| ]) | ||
| ] | ||
| data = dict( | ||
| train=dict(pipeline=train_pipeline), | ||
| val=dict(pipeline=test_pipeline), | ||
| test=dict(pipeline=test_pipeline)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| _base_ = [ | ||
| '../_base_/models/cascade_mask_rcnn_r50_fpn.py', | ||
| '../_base_/datasets/coco_instance.py', | ||
| '../_base_/schedules/schedule_20e.py', '../_base_/default_runtime.py' | ||
| ] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
13 changes: 13 additions & 0 deletions
13
configs/cascade_rcnn/cascade_mask_rcnn_x101_64x4d_fpn_20e_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,13 @@ | ||
| _base_ = './cascade_mask_rcnn_r50_fpn_20e_coco.py' | ||
| model = dict( | ||
| pretrained='open-mmlab://resnext101_64x4d', | ||
| backbone=dict( | ||
| type='ResNeXt', | ||
| depth=101, | ||
| groups=64, | ||
| base_width=4, | ||
| num_stages=4, | ||
| out_indices=(0, 1, 2, 3), | ||
| frozen_stages=1, | ||
| norm_cfg=dict(type='BN', requires_grad=True), | ||
| style='pytorch')) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,3 @@ | ||
| _base_ = './cascade_rcnn_r50_caffe_fpn_1x_coco.py' | ||
| model = dict( | ||
| pretrained='open-mmlab://resnet101_caffe_bgr', backbone=dict(depth=101)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,2 @@ | ||
| _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' | ||
| model = dict(pretrained='torchvision://resnet101', backbone=dict(depth=101)) |
38 changes: 38 additions & 0 deletions
38
configs/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,38 @@ | ||
| _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' | ||
|
|
||
| model = dict( | ||
| pretrained='open-mmlab://resnet50_caffe_bgr', | ||
| backbone=dict(norm_cfg=dict(requires_grad=False), style='caffe')) | ||
|
|
||
| # use caffe img_norm | ||
| img_norm_cfg = dict( | ||
| mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) | ||
| train_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict(type='LoadAnnotations', with_bbox=True), | ||
| dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), | ||
| dict(type='RandomFlip', flip_ratio=0.5), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='DefaultFormatBundle'), | ||
| dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']), | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict( | ||
| type='MultiScaleFlipAug', | ||
| img_scale=(1333, 800), | ||
| flip=False, | ||
| transforms=[ | ||
| dict(type='Resize', keep_ratio=True), | ||
| dict(type='RandomFlip'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='ImageToTensor', keys=['img']), | ||
| dict(type='Collect', keys=['img']), | ||
| ]) | ||
| ] | ||
| data = dict( | ||
| train=dict(pipeline=train_pipeline), | ||
| val=dict(pipeline=test_pipeline), | ||
| test=dict(pipeline=test_pipeline)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| _base_ = './cascade_rcnn_r50_fpn_1x_coco.py' | ||
| # learning policy | ||
| lr_config = dict(step=[16, 19]) | ||
| total_epochs = 20 |
13 changes: 13 additions & 0 deletions
13
configs/cascade_rcnn/cascade_rcnn_x101_32x4d_fpn_20e_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,13 @@ | ||
| _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' | ||
| model = dict( | ||
| pretrained='open-mmlab://resnext101_32x4d', | ||
| backbone=dict( | ||
| type='ResNeXt', | ||
| depth=101, | ||
| groups=32, | ||
| base_width=4, | ||
| num_stages=4, | ||
| out_indices=(0, 1, 2, 3), | ||
| frozen_stages=1, | ||
| norm_cfg=dict(type='BN', requires_grad=True), | ||
| style='pytorch')) |
14 changes: 14 additions & 0 deletions
14
configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn_20e_coco.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| _base_ = './cascade_rcnn_r50_fpn_20e_coco.py' | ||
| model = dict( | ||
| type='CascadeRCNN', | ||
| pretrained='open-mmlab://resnext101_64x4d', | ||
| backbone=dict( | ||
| type='ResNeXt', | ||
| depth=101, | ||
| groups=64, | ||
| base_width=4, | ||
| num_stages=4, | ||
| out_indices=(0, 1, 2, 3), | ||
| frozen_stages=1, | ||
| norm_cfg=dict(type='BN', requires_grad=True), | ||
| style='pytorch')) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.