Merge branch 'open-mmlab:master' into custom/face_occlusion

README.md

@@ -226,6 +226,7 @@ MMSegmentation is released under the Apache 2.0 license, while some specific fea
 - [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab image classification toolbox and benchmark.
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab detection toolbox and benchmark.
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab's next-generation platform for general 3D object detection.
+- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO series toolbox and benchmark.
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab rotated object detection toolbox and benchmark.
 - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab semantic segmentation toolbox and benchmark.
 - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab text detection, recognition, and understanding toolbox.

README_zh-CN.md

@@ -220,6 +220,7 @@ MMSegmentation 是一个由来自不同高校和企业的研发人员共同参
 - [MMClassification](https://github.com/open-mmlab/mmclassification): OpenMMLab 图像分类工具箱
 - [MMDetection](https://github.com/open-mmlab/mmdetection): OpenMMLab 目标检测工具箱
 - [MMDetection3D](https://github.com/open-mmlab/mmdetection3d): OpenMMLab 新一代通用 3D 目标检测平台
+- [MMYOLO](https://github.com/open-mmlab/mmyolo): OpenMMLab YOLO 系列工具箱和基准测试
 - [MMRotate](https://github.com/open-mmlab/mmrotate): OpenMMLab 旋转框检测工具箱与测试基准
 - [MMSegmentation](https://github.com/open-mmlab/mmsegmentation): OpenMMLab 语义分割工具箱
 - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具包

configs/mobilenet_v2/deeplabv3_m-v2-d8_512x1024_80k_cityscapes.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/deeplabv3_m-v2-d8_512x512_160k_ade20k.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x1024_80k_cityscapes.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320, c1_in_channels=24),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/deeplabv3plus_m-v2-d8_512x512_160k_ade20k.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320, c1_in_channels=24),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/fcn_m-v2-d8_512x1024_80k_cityscapes.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/fcn_m-v2-d8_512x512_160k_ade20k.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/pspnet_m-v2-d8_512x1024_80k_cityscapes.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/mobilenet_v2/pspnet_m-v2-d8_512x512_160k_ade20k.py

@@ -7,6 +7,7 @@
  widen_factor=1.,
  strides=(1, 2, 2, 1, 1, 1, 1),
  dilations=(1, 1, 1, 2, 2, 4, 4),
- out_indices=(1, 2, 4, 6)),
+ out_indices=(1, 2, 4, 6),
+ norm_cfg=dict(type='SyncBN', requires_grad=True)),
  decode_head=dict(in_channels=320),
  auxiliary_head=dict(in_channels=96))

configs/poolformer/README.md

@@ -50,11 +50,11 @@ pip install mmcls>=0.23.0
 
 | Method | Backbone | Crop Size | pretrain | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config | download |
 | ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ------ | --------------: | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| FPN | PoolFormer-S12 | 512x512 | ImageNet-1K | 32 | 40000 | 4.17 | 23.48 | 36.0 | 36.42 | 37.07 | 38.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
-| FPN | PoolFormer-S24 | 512x512 | ImageNet-1K | 32 | 40000 | 5.47 | 15.74 | 39.35 | 39.73 | 40.36 | 41.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
-| FPN | PoolFormer-S36 | 512x512 | ImageNet-1K | 32 | 40000 | 6.77 | 11.34 | 40.64 | 40.99 | 41.81 | 42.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
-| FPN | PoolFormer-M36 | 512x512 | ImageNet-1K | 32 | 40000 | 8.59 | 8.97 | 40.91 | 41.28 | 42.35 | 43.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
-| FPN | PoolFormer-M48 | 512x512 | ImageNet-1K | 32 | 40000 | 10.48 | 6.69 | 41.82 |  42.2 | 42.76 | 43.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
+| FPN | PoolFormer-S12 | 512x512 | ImageNet-1K | 32 | 40000 | 4.17 | 23.48 | 36.68 | 38.22 | 37.07 | 38.44 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154.log.json) |
+| FPN | PoolFormer-S24 | 512x512 | ImageNet-1K | 32 | 40000 | 5.47 | 15.74 | 40.12 | 40.97 | 40.36 | 41.08 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049.log.json) |
+| FPN | PoolFormer-S36 | 512x512 | ImageNet-1K | 32 | 40000 | 6.77 | 11.34 | 41.61 | 42.61 | 41.81 | 42.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122.log.json) |
+| FPN | PoolFormer-M36 | 512x512 | ImageNet-1K | 32 | 40000 | 8.59 | 8.97 | 41.95 | 43.24 | 42.35 | 43.34 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230.log.json) |
+| FPN | PoolFormer-M48 | 512x512 | ImageNet-1K | 32 | 40000 | 10.48 | 6.69 | 42.43 | 43.60 | 42.76 | 43.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923.log.json) |
 
 Note:
 

configs/poolformer/poolformer.yml

@@ -17,8 +17,8 @@ Models:
  - Task: Semantic Segmentation
  Dataset: ADE20K
  Metrics:
- mIoU: 36.0
- mIoU(ms+flip): 36.42
+ mIoU: 36.68
+ mIoU(ms+flip): 38.22
  Config: configs/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k/fpn_poolformer_s12_8x4_512x512_40k_ade20k_20220501_115154-b5aa2f49.pth
 - Name: fpn_poolformer_s24_8x4_512x512_40k_ade20k
@@ -39,8 +39,8 @@ Models:
  - Task: Semantic Segmentation
  Dataset: ADE20K
  Metrics:
- mIoU: 39.35
- mIoU(ms+flip): 39.73
+ mIoU: 40.12
+ mIoU(ms+flip): 40.97
  Config: configs/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k/fpn_poolformer_s24_8x4_512x512_40k_ade20k_20220503_222049-394a7cf7.pth
 - Name: fpn_poolformer_s36_8x4_512x512_40k_ade20k
@@ -61,8 +61,8 @@ Models:
  - Task: Semantic Segmentation
  Dataset: ADE20K
  Metrics:
- mIoU: 40.64
- mIoU(ms+flip): 40.99
+ mIoU: 41.61
+ mIoU(ms+flip): 42.61
  Config: configs/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k/fpn_poolformer_s36_8x4_512x512_40k_ade20k_20220501_151122-b47e607d.pth
 - Name: fpn_poolformer_m36_8x4_512x512_40k_ade20k
@@ -83,8 +83,8 @@ Models:
  - Task: Semantic Segmentation
  Dataset: ADE20K
  Metrics:
- mIoU: 40.91
- mIoU(ms+flip): 41.28
+ mIoU: 41.95
+ mIoU(ms+flip): 43.24
  Config: configs/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k/fpn_poolformer_m36_8x4_512x512_40k_ade20k_20220501_164230-3dc83921.pth
 - Name: fpn_poolformer_m48_8x4_512x512_40k_ade20k
@@ -105,7 +105,7 @@ Models:
  - Task: Semantic Segmentation
  Dataset: ADE20K
  Metrics:
- mIoU: 41.82
- mIoU(ms+flip): 42.2
+ mIoU: 42.43
+ mIoU(ms+flip): 43.6
  Config: configs/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k.py
  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k/fpn_poolformer_m48_8x4_512x512_40k_ade20k_20220504_003923-64168d3b.pth