mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

[Feature] Add Swin Large(Swin-L) Transformer models (#1471)

Browse Source 
* [Feature] Add Swin Large(Swin-L) Transformer models

* fix
This commit is contained in:
MengzhangLI 2022-07-08 17:29:17 +08:00 committed by GitHub
parent 0fa7c95fd9
commit 85569442b6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 89 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
configs/swin/README.md
View File

@ -53,24 +53,28 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
In our default setting, pretrained models and their corresponding [original models](https://github.com/microsoft/Swin-Transforme) models could be defined below:
| pretrained models | original models |
| ---------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- |
| pretrain/swin_tiny_patch4_window7_224.pth | [swin_tiny_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth) |
| pretrain/swin_small_patch4_window7_224.pth | [swin_small_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth) |
| pretrain/swin_base_patch4_window7_224.pth | [swin_base_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth) |
| pretrain/swin_base_patch4_window7_224_22k.pth | [swin_base_patch4_window7_224_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth) |
| pretrain/swin_base_patch4_window12_384.pth | [swin_base_patch4_window12_384.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth) |
| pretrain/swin_base_patch4_window12_384_22k.pth | [swin_base_patch4_window12_384_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22k.pth) |
| pretrained models | original models |
| ----------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| pretrain/swin_tiny_patch4_window7_224.pth | [swin_tiny_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth) |
| pretrain/swin_small_patch4_window7_224.pth | [swin_small_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth) |
| pretrain/swin_base_patch4_window7_224.pth | [swin_base_patch4_window7_224.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth) |
| pretrain/swin_base_patch4_window7_224_22k.pth | [swin_base_patch4_window7_224_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth) |
| pretrain/swin_base_patch4_window12_384.pth | [swin_base_patch4_window12_384.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth) |
| pretrain/swin_base_patch4_window12_384_22k.pth | [swin_base_patch4_window12_384_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22k.pth) |
| pretrain/swin_large_patch4_window7_224_22k.pth | [swin_large_patch4_window7_224_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22k.pth) |
| pretrain/swin_large_patch4_window12_384_22k.pth | [swin_large_patch4_window12_384_22k.pth](https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth) |
## Results and models
### ADE20K
| Method | Backbone | Crop Size | pretrain | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UPerNet | Swin-T | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 5.02 | 21.06 | 44.41 | 45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json) |
| UPerNet | Swin-S | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 6.17 | 14.72 | 47.72 | 49.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 7.61 | 12.65 | 47.99 | 49.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-22K | 224x224 | 16 | 160000 | - | - | 50.31 | 51.9 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-1K | 384x384 | 16 | 160000 | 8.52 | 12.10 | 48.35 | 49.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-22K | 384x384 | 16 | 160000 | - | - | 50.76 | 52.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json) |
| Method | Backbone | Crop Size | pretrain | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------- | -------- | --------- | ------------ | ----------------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| UPerNet | Swin-T | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 5.02 | 21.06 | 44.41 | 45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542.log.json) |
| UPerNet | Swin-S | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 6.17 | 14.72 | 47.72 | 49.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015-ee2fff1c.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_small_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192015.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 7.61 | 12.65 | 47.99 | 49.57 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340-593b0e13.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210526_192340.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-22K | 224x224 | 16 | 160000 | - | - | 50.31 | 51.9 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650-762e2178.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K/upernet_swin_base_patch4_window7_512x512_160k_ade20k_pretrain_224x224_22K_20210526_211650.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-1K | 384x384 | 16 | 160000 | 8.52 | 12.10 | 48.35 | 49.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020-05b22ea4.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_1K_20210531_132020.log.json) |
| UPerNet | Swin-B | 512x512 | ImageNet-22K | 384x384 | 16 | 160000 | - | - | 50.76 | 52.4 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459.log.json) |
| UPerNet | Swin-L | 512x512 | ImageNet-22K | 224x224 | 16 | 160000 | 10.98 | 8.23 | 51.17 | 52.99 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k_20220318_015320-48d180dd.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k_20220318_015320.log.json) |
| UPerNet | Swin-L | 512x512 | ImageNet-22K | 384x384 | 16 | 160000 | 12.42 | 7.57 | 52.25 | 54.12 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k_20220318_091743-9ba68901.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k_20220318_091743.log.json) |

44
configs/swin/swin.yml
View File

@ -115,3 +115,47 @@ Models:
mIoU(ms+flip): 52.4
Config: configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth
- Name: upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k
In Collection: UPerNet
Metadata:
backbone: Swin-L
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 121.51
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 10.98
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 51.17
mIoU(ms+flip): 52.99
Config: configs/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k_20220318_015320-48d180dd.pth
- Name: upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k
In Collection: UPerNet
Metadata:
backbone: Swin-L
crop size: (512,512)
lr schd: 160000
inference time (ms/im):
- value: 132.1
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (512,512)
Training Memory (GB): 12.42
Results:
- Task: Semantic Segmentation
Dataset: ADE20K
Metrics:
mIoU: 52.25
mIoU(ms+flip): 54.12
Config: configs/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k_20220318_091743-9ba68901.pth

10
configs/swin/upernet_swin_large_patch4_window12_512x512_pretrain_384x384_22K_160k_ade20k.py Normal file
View File

@ -0,0 +1,10 @@
_base_ = [
'upernet_swin_large_patch4_window7_512x512_'
'pretrain_224x224_22K_160k_ade20k.py'
]
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window12_384_22k_20220412-6580f57d.pth' # noqa
model = dict(
backbone=dict(
init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
pretrain_img_size=384,
window_size=12))

15
configs/swin/upernet_swin_large_patch4_window7_512x512_pretrain_224x224_22K_160k_ade20k.py Normal file
View File

@ -0,0 +1,15 @@
_base_ = [
'upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_'
'pretrain_224x224_1K.py'
]
checkpoint_file = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/swin/swin_large_patch4_window7_224_22k_20220412-aeecf2aa.pth' # noqa
model = dict(
backbone=dict(
init_cfg=dict(type='Pretrained', checkpoint=checkpoint_file),
pretrain_img_size=224,
embed_dims=192,
depths=[2, 2, 18, 2],
num_heads=[6, 12, 24, 48],
window_size=7),
decode_head=dict(in_channels=[192, 384, 768, 1536], num_classes=150),
auxiliary_head=dict(in_channels=768, num_classes=150))