Skip to content

Commit a35e1c4

Browse files
MeowZhengMeowZheng
committed
Merge branch 'dev-1.x' of github.com:open-mmlab/mmsegmentation into 1.x
2 parents 1c836be + 7ac0888 commit a35e1c4

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

54 files changed

+321
-353
lines changed

‎.circleci/test.yml

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -61,9 +61,9 @@ jobs:
6161
command: |
6262
pip install git+https://github.com/open-mmlab/mmengine.git@main
6363
pip install -U openmim
64-
mim install 'mmcv==2.0.0rc3'
64+
mim install 'mmcv>=2.0.0rc4'
6565
pip install git+https://github.com/open-mmlab/[email protected]
66-
mim install 'mmdet==3.0.0rc5'
66+
pip install git+https://github.com/open-mmlab/[email protected]
6767
pip install -r requirements/tests.txt -r requirements/optional.txt
6868
- run:
6969
name: Build and install
@@ -97,6 +97,7 @@ jobs:
9797
command: |
9898
git clone -b main --depth 1 https://github.com/open-mmlab/mmengine.git /home/circleci/mmengine
9999
git clone -b dev-1.x --depth 1 https://github.com/open-mmlab/mmclassification.git /home/circleci/mmclassification
100+
git clone -b dev-3.x --depth 1 https://github.com/open-mmlab/mmdetection.git /home/circleci/mmdetection
100101
- run:
101102
name: Build Docker image
102103
command: |
@@ -107,9 +108,9 @@ jobs:
107108
command: |
108109
docker exec mmseg pip install -e /mmengine
109110
docker exec mmseg pip install -U openmim
110-
docker exec mmseg mim install 'mmcv==2.0.0rc3'
111+
docker exec mmseg mim install 'mmcv>=2.0.0rc4'
111112
docker exec mmseg pip install -e /mmclassification
112-
docker exec mmseg mim install 'mmdet==3.0.0rc5'
113+
docker exec mmseg pip install -e /mmdetection
113114
docker exec mmseg pip install -r requirements/tests.txt -r requirements/optional.txt
114115
- run:
115116
name: Build and install

‎.github/workflows/merge_stage_test.yml

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -44,9 +44,9 @@ jobs:
4444
python -V
4545
pip install -U openmim
4646
pip install git+https://github.com/open-mmlab/mmengine.git
47-
mim install 'mmcv==2.0.0rc3'
47+
mim install 'mmcv>=2.0.0rc4'
4848
pip install git+https://github.com/open-mmlab/[email protected]
49-
mim install 'mmdet==3.0.0rc5'
49+
pip install git+https://github.com/open-mmlab/[email protected]
5050
- name: Install unittest dependencies
5151
run: pip install -r requirements/tests.txt -r requirements/optional.txt
5252
- name: Build and install
@@ -100,9 +100,9 @@ jobs:
100100
python -V
101101
pip install -U openmim
102102
pip install git+https://github.com/open-mmlab/mmengine.git
103-
mim install 'mmcv==2.0.0rc3'
103+
mim install 'mmcv>=2.0.0rc4'
104104
pip install git+https://github.com/open-mmlab/[email protected]
105-
mim install 'mmdet==3.0.0rc5'
105+
pip install git+https://github.com/open-mmlab/[email protected]
106106
- name: Install unittest dependencies
107107
run: pip install -r requirements/tests.txt -r requirements/optional.txt
108108
- name: Build and install
@@ -166,9 +166,9 @@ jobs:
166166
python -V
167167
pip install -U openmim
168168
pip install git+https://github.com/open-mmlab/mmengine.git
169-
mim install 'mmcv==2.0.0rc3'
169+
mim install 'mmcv>=2.0.0rc4'
170170
pip install git+https://github.com/open-mmlab/[email protected]
171-
mim install 'mmdet==3.0.0rc5'
171+
pip install git+https://github.com/open-mmlab/[email protected]
172172
- name: Install unittest dependencies
173173
run: pip install -r requirements/tests.txt -r requirements/optional.txt
174174
- name: Build and install
@@ -209,9 +209,9 @@ jobs:
209209
python -V
210210
pip install -U openmim
211211
pip install git+https://github.com/open-mmlab/mmengine.git
212-
mim install 'mmcv==2.0.0rc3'
212+
mim install 'mmcv>=2.0.0rc4'
213213
pip install git+https://github.com/open-mmlab/[email protected]
214-
mim install 'mmdet==3.0.0rc5'
214+
pip install git+https://github.com/open-mmlab/[email protected]
215215
- name: Install unittest dependencies
216216
run: pip install -r requirements/tests.txt -r requirements/optional.txt
217217
- name: Build and install
@@ -244,9 +244,9 @@ jobs:
244244
python -V
245245
pip install -U openmim
246246
pip install git+https://github.com/open-mmlab/mmengine.git
247-
mim install 'mmcv==2.0.0rc3'
247+
mim install 'mmcv>=2.0.0rc4'
248248
pip install git+https://github.com/open-mmlab/[email protected]
249-
mim install 'mmdet==3.0.0rc5'
249+
pip install git+https://github.com/open-mmlab/[email protected]
250250
- name: Install unittest dependencies
251251
run: pip install -r requirements/tests.txt -r requirements/optional.txt
252252
- name: Build and install

‎.github/workflows/pr_stage_test.yml

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -44,9 +44,9 @@ jobs:
4444
run: |
4545
pip install -U openmim
4646
pip install git+https://github.com/open-mmlab/mmengine.git
47-
mim install 'mmcv==2.0.0rc3'
47+
mim install 'mmcv>=2.0.0rc4'
4848
pip install git+https://github.com/open-mmlab/[email protected]
49-
mim install 'mmdet==3.0.0rc5'
49+
pip install git+https://github.com/open-mmlab/[email protected]
5050
- name: Install unittest dependencies
5151
run: pip install -r requirements/tests.txt -r requirements/optional.txt
5252
- name: Build and install
@@ -100,9 +100,9 @@ jobs:
100100
python -V
101101
pip install -U openmim
102102
pip install git+https://github.com/open-mmlab/mmengine.git
103-
mim install 'mmcv==2.0.0rc3'
103+
mim install 'mmcv>=2.0.0rc4'
104104
pip install git+https://github.com/open-mmlab/[email protected]
105-
mim install 'mmdet==3.0.0rc5'
105+
pip install git+https://github.com/open-mmlab/[email protected]
106106
- name: Install unittest dependencies
107107
run: pip install -r requirements/tests.txt -r requirements/optional.txt
108108
- name: Build and install
@@ -135,9 +135,9 @@ jobs:
135135
python -V
136136
pip install -U openmim
137137
pip install git+https://github.com/open-mmlab/mmengine.git
138-
mim install 'mmcv==2.0.0rc3'
138+
mim install 'mmcv>=2.0.0rc4'
139139
pip install git+https://github.com/open-mmlab/[email protected]
140-
mim install 'mmdet==3.0.0rc5'
140+
pip install git+https://github.com/open-mmlab/[email protected]
141141
- name: Install unittest dependencies
142142
run: pip install -r requirements/tests.txt -r requirements/optional.txt
143143
- name: Build and install

‎README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,7 @@ The 1.x branch works with **PyTorch 1.6+**.
6262

6363
## What's New
6464

65-
v1.0.0rc4 was released on 30/01/2023.
65+
v1.0.0rc5 was released on 01/02/2023.
6666
Please refer to [changelog.md](docs/en/notes/changelog.md) for details and release history.
6767

6868
- Support ISNet (ICCV'2021) in projects ([#2400](https://github.com/open-mmlab/mmsegmentation/pull/2400))

‎README_zh-CN.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ MMSegmentation 是一个基于 PyTorch 的语义分割开源工具箱。它是 O
6161

6262
## 更新日志
6363

64-
最新版本 v1.0.0rc4 在 2023.01.30 发布。
64+
最新版本 v1.0.0rc5 在 2023.02.01 发布。
6565
如果想了解更多版本更新细节和历史信息，请阅读[更新日志](docs/en/notes/changelog.md)。
6666

6767
## 安装

‎configs/_base_/datasets/ade20k.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/ade20k_640x640.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/chase_db1.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@
2626
]
2727
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2828
tta_pipeline = [
29-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
29+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3030
dict(
3131
type='TestTimeAug',
3232
transforms=[

‎configs/_base_/datasets/cityscapes.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/coco-stuff10k.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/coco-stuff164k.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/drive.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@
2626
]
2727
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2828
tta_pipeline = [
29-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
29+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3030
dict(
3131
type='TestTimeAug',
3232
transforms=[

‎configs/_base_/datasets/hrf.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@
2626
]
2727
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2828
tta_pipeline = [
29-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
29+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3030
dict(
3131
type='TestTimeAug',
3232
transforms=[

‎configs/_base_/datasets/isaid.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@
3232
]
3333
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
3434
tta_pipeline = [
35-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
35+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3636
dict(
3737
type='TestTimeAug',
3838
transforms=[

‎configs/_base_/datasets/loveda.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/pascal_context_59.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -28,7 +28,7 @@
2828
]
2929
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
3030
tta_pipeline = [
31-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
31+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3232
dict(
3333
type='TestTimeAug',
3434
transforms=[

‎configs/_base_/datasets/pascal_voc12.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/pascal_voc12_aug.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@
2727
]
2828
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2929
tta_pipeline = [
30-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
30+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3131
dict(
3232
type='TestTimeAug',
3333
transforms=[

‎configs/_base_/datasets/potsdam.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/_base_/datasets/stare.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@
2626
]
2727
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2828
tta_pipeline = [
29-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
29+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
3030
dict(
3131
type='TestTimeAug',
3232
transforms=[

‎configs/_base_/datasets/vaihingen.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,7 +25,7 @@
2525
]
2626
img_ratios = [0.5, 0.75, 1.0, 1.25, 1.5, 1.75]
2727
tta_pipeline = [
28-
dict(type='LoadImageFromFile', file_client_args=dict(backend='disk')),
28+
dict(type='LoadImageFromFile', backend_args=dict(backend='local')),
2929
dict(
3030
type='TestTimeAug',
3131
transforms=[

‎configs/erfnet/README.md

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -41,12 +41,14 @@ Semantic segmentation is a challenging task that addresses most of the perceptio
4141

4242
### Cityscapes
4343

44-
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
45-
| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
46-
| ERFNet | ERFNet | 512x1024 | 160000 | 6.04 | 15.26 | 71.08 | 72.6 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20211126_082056-03d333ed.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20211126_082056.log.json) |
44+
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
45+
| ------ | -------- | --------- | ------: | -------- | -------------- | ---: | ------------- | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
46+
| ERFNet | ERFNet | 512x1024 | 160000 | 6.04 | 15.26 | 72.5 | 74.75 | [config](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth) \| [log](https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145.log.json) |
4747

4848
Note:
4949

5050
- The model is trained from scratch.
5151

5252
- Last deconvolution layer in the [original paper](https://github.com/Eromera/erfnet_pytorch/blob/master/train/erfnet.py#L123) is replaced by a naive `FCNHead` decoder head and a bilinear upsampling layer, found more effective and efficient.
53+
54+
- This model performance is sensitive to the seed values used, please refer to the log file for the specific settings of the seed. If you choose a different seed, the results might differ from the table results.

‎configs/erfnet/erfnet.yml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ Models:
3131
- Task: Semantic Segmentation
3232
Dataset: Cityscapes
3333
Metrics:
34-
mIoU: 71.08
35-
mIoU(ms+flip): 72.6
34+
mIoU: 72.5
35+
mIoU(ms+flip): 74.75
3636
Config: configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py
37-
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20211126_082056-03d333ed.pth
37+
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/erfnet/erfnet_fcn_4x4_512x1024_160k_cityscapes/erfnet_fcn_4x4_512x1024_160k_cityscapes_20220704_162145-dc90157a.pth

0 commit comments

Comments
 (0)