[Benchmark] Add BiSeNetV1 COCO-Stuff 164k benchmark

configs/bisenetv1/README.md

@@ -35,8 +35,19 @@
 | BiSeNetV1 (No Pretrain) | R-50-D32 | 1024x1024  | 160000 | 15.39 | 7.71 | 76.92 | 78.87 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639-7b28a2a6.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_4x4_1024x1024_160k_cityscapes_20210923_222639.log.json) |
 | BiSeNetV1 | R-50-D32 | 1024x1024  | 160000 | 15.39 | 7.71 | 77.68 | 79.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628.log.json) |
 
+### COCO-Stuff 164k
+
+| Method    | Backbone  | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                  | download                                                                                                                                                                                                                                                       |
+| --------- | --------- | --------- | ------: | -------- | -------------- | ----: | ------------- | --------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| BiSeNetV1 (No Pretrain) | R-18-D32 | 512x512 | 160000 | - | - | 25.45 | 26.15 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328.log.json) |
+| BiSeNetV1| R-18-D32 | 512x512  | 160000 | 6.33 | 74.24 | 28.55 | 29.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100.log.json) |
+| BiSeNetV1 (No Pretrain) | R-50-D32 | 512x512  | 160000 | - | - | 29.82 | 30.33 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616.log.json) |
+| BiSeNetV1 | R-50-D32 | 512x512  | 160000 | 9.28 | 32.60 | 34.88 | 35.37 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932.log.json) |
+| BiSeNetV1(No Pretrain) | R-101-D32 | 512x512  | 160000 | - | - | 31.14 | 31.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147.log.json) |
+| BiSeNetV1 | R-101-D32 | 512x512  | 160000 | 10.36 | 25.25 | 37.38 | 37.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220.log.json) |
+
 Note:
 
 - `4x8`: Using 4 GPUs with 8 samples per GPU in training.
-- Default setting is 4 GPUs with 4 samples per GPU in training.
+- For BiSeNetV1 on Cityscapes dataset, default setting is 4 GPUs with 4 samples per GPU in training.
 - `No Pretrain` means the model is trained from scratch.

configs/bisenetv1/bisenetv1.yml

@@ -3,6 +3,7 @@ Collections:
   Metadata:
     Training Data:
     - Cityscapes
+    - COCO-Stuff 164k
   Paper:
     URL: https://arxiv.org/abs/1808.00897
     Title: 'BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation'
@@ -123,3 +124,111 @@ Models:
       mIoU(ms+flip): 79.57
   Config: configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes.py
   Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes/bisenetv1_r50-d32_in1k-pre_4x4_1024x1024_160k_cityscapes_20210917_234628-8b304447.pth
+- Name: bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-18-D32
+    crop size: (512,512)
+    lr schd: 160000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 25.45
+      mIoU(ms+flip): 26.15
+  Config: configs/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211022_054328-046aa2f2.pth
+- Name: bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-18-D32
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 13.47
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 6.33
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 28.55
+      mIoU(ms+flip): 29.26
+  Config: configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211023_013100-f700dbf7.pth
+- Name: bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-50-D32
+    crop size: (512,512)
+    lr schd: 160000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 29.82
+      mIoU(ms+flip): 30.33
+  Config: configs/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_040616-d2bb0df4.pth
+- Name: bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-50-D32
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 30.67
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 9.28
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 34.88
+      mIoU(ms+flip): 35.37
+  Config: configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_181932-66747911.pth
+- Name: bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-101-D32
+    crop size: (512,512)
+    lr schd: 160000
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 31.14
+      mIoU(ms+flip): 31.76
+  Config: configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211102_164147-c6b32c3b.pth
+- Name: bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k
+  In Collection: bisenetv1
+  Metadata:
+    backbone: R-101-D32
+    crop size: (512,512)
+    lr schd: 160000
+    inference time (ms/im):
+    - value: 39.6
+      hardware: V100
+      backend: PyTorch
+      batch size: 1
+      mode: FP32
+      resolution: (512,512)
+    memory (GB): 10.36
+  Results:
+  - Task: Semantic Segmentation
+    Dataset: COCO-Stuff 164k
+    Metrics:
+      mIoU: 37.38
+      mIoU(ms+flip): 37.99
+  Config: configs/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py
+  Weights: https://download.openmmlab.com/mmsegmentation/v0.5/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k_20211101_225220-28c8f092.pth

configs/bisenetv1/bisenetv1_r101-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,6 @@
+_base_ = './bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py'
+model = dict(
+    backbone=dict(
+        backbone_cfg=dict(
+            init_cfg=dict(
+                type='Pretrained', checkpoint='open-mmlab://resnet101_v1c'))))

configs/bisenetv1/bisenetv1_r101-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,18 @@
+_base_ = [
+    '../_base_/models/bisenetv1_r18-d32.py',
+    '../_base_/datasets/coco-stuff164k.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    backbone=dict(
+        context_channels=(512, 1024, 2048),
+        spatial_channels=(256, 256, 256, 512),
+        out_channels=1024,
+        backbone_cfg=dict(type='ResNet', depth=101)),
+    decode_head=dict(in_channels=1024, channels=1024, num_classes=171),
+    auxiliary_head=[
+        dict(in_channels=512, channels=256, num_classes=171),
+        dict(in_channels=512, channels=256, num_classes=171),
+    ])
+lr_config = dict(warmup='linear', warmup_iters=1000)
+optimizer = dict(lr=0.005)

configs/bisenetv1/bisenetv1_r18-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,6 @@
+_base_ = './bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py'
+model = dict(
+    backbone=dict(
+        backbone_cfg=dict(
+            init_cfg=dict(
+                type='Pretrained', checkpoint='open-mmlab://resnet18_v1c'))), )

configs/bisenetv1/bisenetv1_r18-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,13 @@
+_base_ = [
+    '../_base_/models/bisenetv1_r18-d32.py',
+    '../_base_/datasets/coco-stuff164k.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    decode_head=dict(num_classes=171),
+    auxiliary_head=[
+        dict(num_classes=171),
+        dict(num_classes=171),
+    ])
+lr_config = dict(warmup='linear', warmup_iters=1000)
+optimizer = dict(lr=0.005)

configs/bisenetv1/bisenetv1_r50-d32_in1k-pre_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,7 @@
+_base_ = './bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py'
+
+model = dict(
+    backbone=dict(
+        backbone_cfg=dict(
+            init_cfg=dict(
+                type='Pretrained', checkpoint='open-mmlab://resnet50_v1c'))))

configs/bisenetv1/bisenetv1_r50-d32_lr5e-3_4x4_512x512_160k_coco-stuff164k.py

@@ -0,0 +1,18 @@
+_base_ = [
+    '../_base_/models/bisenetv1_r18-d32.py',
+    '../_base_/datasets/coco-stuff164k.py', '../_base_/default_runtime.py',
+    '../_base_/schedules/schedule_160k.py'
+]
+model = dict(
+    backbone=dict(
+        context_channels=(512, 1024, 2048),
+        spatial_channels=(256, 256, 256, 512),
+        out_channels=1024,
+        backbone_cfg=dict(type='ResNet', depth=50)),
+    decode_head=dict(in_channels=1024, channels=1024, num_classes=171),
+    auxiliary_head=[
+        dict(in_channels=512, channels=256, num_classes=171),
+        dict(in_channels=512, channels=256, num_classes=171),
+    ])
+lr_config = dict(warmup='linear', warmup_iters=1000)
+optimizer = dict(lr=0.005)