Skip to content

Commit 6d629b7

Browse files
authored
Bump version to 0.5.0 (#214)
* dumps to 0.5.0 * fix known issue * fix bug * update chenge log * update chenge log
1 parent 5959c64 commit 6d629b7

File tree

6 files changed

+30
-5
lines changed

6 files changed

+30
-5
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ MMGeneration is a powerful toolkit for generative models, especially for GANs no
6161
* Mixed-precision training (FP16) for StyleGAN2 has been supported. Please check [the comparison](configs/styleganv2/README.md) between different implementations.
6262
## Changelog
6363

64-
v0.4.0 was released on 03/11/2021. Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
64+
v0.5.0 was released on 12/01/2022. Please refer to [changelog.md](docs/en/changelog.md) for details and release history.
6565

6666
## ModelZoo
6767

README_zh-CN.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,7 @@ MMGeneration 是一个基于 PyTorch 和[MMCV](https://github.com/open-mmlab/mmc
6262
* 混合精度训练已经在 `StyleGAN2` 中进行了初步支持,请到[这里](configs/styleganv2/README.md)查看各种实现方式的详细比较。
6363
## 更新日志
6464

65-
v0.3.0 在 02/08/2021 发布。 关于细节和发布历史,请参考 [changelog.md](docs/changelog.md)
65+
v0.5.0 在 12/02/2022 发布。 关于细节和发布历史,请参考 [changelog.md](docs/zh_cn/changelog.md)
6666

6767
## 模型库
6868

docker/Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ RUN apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build
1515
# Install MMCV
1616
RUN pip install mmcv-full==1.3.16 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.0/index.html
1717

18-
# Install MMFlow
18+
# Install MMGeneration
1919
RUN conda clean --all
2020
RUN git clone https://github.com/open-mmlab/mmgeneration.git /mmgen
2121
WORKDIR /mmgen

docs/en/changelog.md

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,7 @@
1717
## v0.2.0 (30/05/2021)
1818

1919
#### Highlights
20+
2021
- Support new methods: LSGAN, GGAN.
2122
- Support mixed-precision training (FP16): official PyTorch Implementation and APEX (#11, #20)
2223

@@ -37,6 +38,7 @@
3738
## v0.3.0 (02/08/2021)
3839

3940
#### Highlights
41+
4042
- Support conditional GANs: Projection GAN, SNGAN, SAGAN, and BigGAN
4143

4244
#### New Features
@@ -54,6 +56,7 @@
5456
## v0.4.0 (03/11/2021)
5557

5658
#### Highlights
59+
5760
- Add more experiments for conditional GANs: SNGAN, SAGAN, and BigGAN
5861
- Refact Translation Model (#88, #126, #127, #145)
5962

@@ -67,3 +70,25 @@
6770
- Add CI for python3.9 #110
6871
- Add support for PyTorch1.9 #115
6972
- Add pre-commit hook for spell checking #135
73+
74+
75+
## v0.5.0 (12/01/2022)
76+
77+
#### Highlights
78+
79+
- Support BigGAN style's Spectral Norm and update BigGAN with best FID and IS (#159)
80+
- Support import projected latent and export video in interpolation (#167)
81+
- Support Improved-DDPM model (#205)
82+
- One face editing application build upon MMGen is released
83+
84+
#### New Features
85+
86+
- Support evaluation in distributed mode (#151)
87+
- Support `presistent_work` in validation dataloader (#179)
88+
- Support dockerfile (#200)
89+
- Support `mim` (#176)
90+
91+
#### Fix bugs and Improvements
92+
93+
- Fix bug in SinGAN dataset (#192)
94+
- Fix SAGAN, SNGAN and BigGAN's default `sn_style` (#199, #213)

mmgen/version.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Copyright (c) OpenMMLab. All rights reserved.
2-
__version__ = '0.4.0'
2+
__version__ = '0.5.0'
33

44

55
def parse_version_info(version_str):

requirements/mminstall.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,2 @@
11
mmcls>=0.18.0,<=0.18.0
2-
mmcv-full>=1.3.0,<=1.4.0
2+
mmcv-full>=1.3.0,<=1.5.0

0 commit comments

Comments
 (0)