Skip to content

Commit a68e7c2

Browse files
MengzhangLIMengzhangLI
authored
[Fix] Fix PoolFormer mIoU result (open-mmlab#2190)
1 parent 04afdb3 commit a68e7c2

File tree

2 files changed

+15
-15
lines changed

2 files changed

+15
-15
lines changed

‎configs/poolformer/README.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -50,11 +50,11 @@ pip install mmcls>=0.23.0
5050

5151
| Method | Backbone | Crop Size | pretrain | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | mIoU\* | mIoU\*(ms+flip) | config | download |
5252
| ------ | -------------- | --------- | ----------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ------ | --------------: | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
53-
| 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) |
54-
| 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) |
55-
| 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) |
56-
| 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) |
57-
| 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) |
53+
| 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) |
54+
| 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) |
55+
| 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) |
56+
| 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) |
57+
| 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) |
5858

5959
Note:
6060

‎configs/poolformer/poolformer.yml‎

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -17,8 +17,8 @@ Models:
1717
- Task: Semantic Segmentation
1818
Dataset: ADE20K
1919
Metrics:
20-
mIoU: 36.0
21-
mIoU(ms+flip): 36.42
20+
mIoU: 36.68
21+
mIoU(ms+flip): 38.22
2222
Config: configs/poolformer/fpn_poolformer_s12_8x4_512x512_40k_ade20k.py
2323
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
2424
- Name: fpn_poolformer_s24_8x4_512x512_40k_ade20k
@@ -39,8 +39,8 @@ Models:
3939
- Task: Semantic Segmentation
4040
Dataset: ADE20K
4141
Metrics:
42-
mIoU: 39.35
43-
mIoU(ms+flip): 39.73
42+
mIoU: 40.12
43+
mIoU(ms+flip): 40.97
4444
Config: configs/poolformer/fpn_poolformer_s24_8x4_512x512_40k_ade20k.py
4545
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
4646
- Name: fpn_poolformer_s36_8x4_512x512_40k_ade20k
@@ -61,8 +61,8 @@ Models:
6161
- Task: Semantic Segmentation
6262
Dataset: ADE20K
6363
Metrics:
64-
mIoU: 40.64
65-
mIoU(ms+flip): 40.99
64+
mIoU: 41.61
65+
mIoU(ms+flip): 42.61
6666
Config: configs/poolformer/fpn_poolformer_s36_8x4_512x512_40k_ade20k.py
6767
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
6868
- Name: fpn_poolformer_m36_8x4_512x512_40k_ade20k
@@ -83,8 +83,8 @@ Models:
8383
- Task: Semantic Segmentation
8484
Dataset: ADE20K
8585
Metrics:
86-
mIoU: 40.91
87-
mIoU(ms+flip): 41.28
86+
mIoU: 41.95
87+
mIoU(ms+flip): 43.24
8888
Config: configs/poolformer/fpn_poolformer_m36_8x4_512x512_40k_ade20k.py
8989
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
9090
- Name: fpn_poolformer_m48_8x4_512x512_40k_ade20k
@@ -105,7 +105,7 @@ Models:
105105
- Task: Semantic Segmentation
106106
Dataset: ADE20K
107107
Metrics:
108-
mIoU: 41.82
109-
mIoU(ms+flip): 42.2
108+
mIoU: 42.43
109+
mIoU(ms+flip): 43.6
110110
Config: configs/poolformer/fpn_poolformer_m48_8x4_512x512_40k_ade20k.py
111111
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

0 commit comments

Comments
 (0)