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

[Fix] batch size for citys in cfg file name (#1977)

Browse Source
This commit is contained in:
Miao Zheng 2022-08-26 20:49:43 +08:00 committed by GitHub
parent a3a144a361
commit c5bcf9991b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py
View File

@ -1,2 +1,2 @@
_base_ = './deeplabv3_r50-d8_4xb4-40k_cityscapes-512x1024.py'
_base_ = './deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
configs/deeplabv3/deeplabv3_r101-d8_4xb2-40k_cityscapes-769x769.py
View File

@ -1,2 +1,2 @@
_base_ = './deeplabv3_r50-d8_4xb4-40k_cityscapes-769x769.py'
_base_ = './deeplabv3_r50-d8_4xb2-40k_cityscapes-769x769.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-512x1024.py
View File

@ -1,2 +1,2 @@
_base_ = './deeplabv3_r50-d8_4xb4-80k_cityscapes-512x1024.py'
_base_ = './deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
configs/deeplabv3/deeplabv3_r101-d8_4xb2-80k_cityscapes-769x769.py
View File

@ -1,2 +1,2 @@
_base_ = './deeplabv3_r50-d8_4xb4-80k_cityscapes-769x769.py'
_base_ = './deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py'
model = dict(pretrained='open-mmlab://resnet101_v1c', backbone=dict(depth=101))

2
configs/deeplabv3/deeplabv3_r101-d8_4xb2-amp-80k_cityscapes-512x1024.py
View File

@ -1,4 +1,4 @@
_base_ = './deeplabv3_r101-d8_4xb4-40k_cityscapes-512x1024.py'
_base_ = './deeplabv3_r101-d8_4xb2-40k_cityscapes-512x1024.py'
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005)
optim_wrapper = dict(
_delete_=True,

2
configs/deeplabv3/deeplabv3_r18-d8_4xb2-80k_cityscapes-769x769.py
View File

@ -1,4 +1,4 @@
_base_ = './deeplabv3_r50-d8_4xb4-80k_cityscapes-769x769.py'
_base_ = './deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py'
model = dict(
pretrained='open-mmlab://resnet18_v1c',
backbone=dict(depth=18),

2
configs/deeplabv3/deeplabv3_r50b-d8_4xb2-80k_cityscapes-769x769.py
View File

@ -1,2 +1,2 @@
_base_ = './deeplabv3_r50-d8_4xb4-80k_cityscapes-769x769.py'
_base_ = './deeplabv3_r50-d8_4xb2-80k_cityscapes-769x769.py'
model = dict(pretrained='torchvision://resnet50', backbone=dict(type='ResNet'))

6
configs/fastfcn/README.md
View File

@ -40,11 +40,11 @@ year={2019}
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------------------------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FastFCN + DeepLabV3 | R-50-D32 | 512x1024 | 80000 | 5.67 | 2.64 | 79.12 | 80.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722.log.json) |
| FastFCN + DeepLabV3 (4x4) | R-50-D32 | 512x1024 | 80000 | 9.79 | - | 79.52 | 80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
| FastFCN + DeepLabV3 (4x4) | R-50-D32 | 512x1024 | 80000 | 9.79 | - | 79.52 | 80.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357.log.json) |
| FastFCN + PSPNet | R-50-D32 | 512x1024 | 80000 | 5.67 | 4.40 | 79.26 | 80.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722.log.json) |
| FastFCN + PSPNet (4x4) | R-50-D32 | 512x1024 | 80000 | 9.94 | - | 78.76 | 80.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json) |
| FastFCN + PSPNet (4x4) | R-50-D32 | 512x1024 | 80000 | 9.94 | - | 78.76 | 80.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841.log.json) |
| FastFCN + EncNet | R-50-D32 | 512x1024 | 80000 | 8.15 | 4.77 | 77.97 | 79.92 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036.log.json) |
| FastFCN + EncNet (4x4) | R-50-D32 | 512x1024 | 80000 | 15.45 | - | 78.6 | 80.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json) |
| FastFCN + EncNet (4x4) | R-50-D32 | 512x1024 | 80000 | 15.45 | - | 78.6 | 80.25 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217.log.json) |
### ADE20K

12
configs/fastfcn/fastfcn.yml
View File

@ -36,7 +36,7 @@ Models:
mIoU(ms+flip): 80.58
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes_20210928_053722-5d1a2648.pth
- Name: fastfcn_r50-d32_jpu_aspp_4xb4-80k_cityscapes-512x1024
- Name: fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Metadata:
backbone: R-50-D32
@ -49,7 +49,7 @@ Models:
Metrics:
mIoU: 79.52
mIoU(ms+flip): 80.91
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb4-80k_cityscapes-512x1024.py
Config: configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes_20210924_214357-72220849.pth
- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
@ -73,7 +73,7 @@ Models:
mIoU(ms+flip): 80.86
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes_20210928_053722-57749bed.pth
- Name: fastfcn_r50-d32_jpu_psp_4xb4-80k_cityscapes-512x1024
- Name: fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Metadata:
backbone: R-50-D32
@ -86,7 +86,7 @@ Models:
Metrics:
mIoU: 78.76
mIoU(ms+flip): 80.03
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb4-80k_cityscapes-512x1024.py
Config: configs/fastfcn/fastfcn_r50-d32_jpu_psp_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes_20210925_061841-77e87b0a.pth
- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
@ -110,7 +110,7 @@ Models:
mIoU(ms+flip): 79.92
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes_20210928_030036-78da5046.pth
- Name: fastfcn_r50-d32_jpu_enc_4xb4-80k_cityscapes-512x1024
- Name: fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024
In Collection: FastFCN
Metadata:
backbone: R-50-D32
@ -123,7 +123,7 @@ Models:
Metrics:
mIoU: 78.6
mIoU(ms+flip): 80.25
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb4-80k_cityscapes-512x1024.py
Config: configs/fastfcn/fastfcn_r50-d32_jpu_enc_4xb2-80k_cityscapes-512x1024.py
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fastfcn/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes/fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes_20210926_093217-e1eb6dbb.pth
- Name: fastfcn_r50-d32_jpu_aspp_4xb4-80k_ade20k-512x512
In Collection: FastFCN

2
docs/en/user_guides/1_config.md
View File

@ -13,7 +13,7 @@ The configs that are composed by components from `_base_` are called _primitive_
For all configs under the same folder, it is recommended to have only **one** _primitive_ config. All other configs should inherit from the _primitive_ config. In this way, the maximum of inheritance level is 3.
For easy understanding, we recommend contributors to inherit from existing methods.
For example, if some modification is made base on DeepLabV3, user may first inherit the basic DeepLabV3 structure by specifying `_base_ = ../deeplabv3/deeplabv3_r50-d8_4xb4-40k_cityscapes-512x1024.py`, then modify the necessary fields in the config files.
For example, if some modification is made base on DeepLabV3, user may first inherit the basic DeepLabV3 structure by specifying `_base_ = ../deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py`, then modify the necessary fields in the config files.
If you are building an entirely new method that does not share the structure with any of the existing methods, you may create a folder `xxxnet` under `configs`,