tommyzihao/mmgeneration_tutorials

Jupyter notebook tutorials for mmgeneration

MMGeneration 代码教程

环境配置须知（必看）

推荐代码运行环境（最省时间精力）：云GPU环境

云GPU环境参数：Ubuntu、GPU RTX 3060、CUDA V11.2

扩展链接

MMGeneration主页（点star的据说都发顶会了）：https://github.com/open-mmlab/mmgeneration

OpenMMLab主页：https://openmmlab.com/

视频教程：https://www.bilibili.com/video/BV1bY4y147kz

mmgeneration_tutorials's Issues

The Mac uses jupyter in vscode to install pytorch and reports an error

# 安装 Pytorch !pip install install torch==1.10.1+cu113 torchvision==0.11.2+cu113 torchaudio==0.10.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
error message:
ERROR: Could not find a version that satisfies the requirement torch==1.10.1+cu113 (from versions: 0.4.1, 1.0.0, 1.0.1, 1.0.1.post2, 1.1.0, 1.1.0.post2, 1.2.0, 1.3.0, 1.3.0.post2, 1.3.1, 1.4.0, 1.5.0, 1.5.1, 1.6.0, 1.7.0, 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1, 1.10.0, 1.10.1, 1.10.2, 1.11.0) ERROR: No matching distribution found for torch==1.10.1+cu113
My pip is python3.7, pip3 is python3.8

Error in using conda environment to install MMGeneration

Like this.
I try to alter src_relpath but it's not useful.

在训练cycle GAN时报错

在运行下下代码时：

出现错误：
/environment/miniconda3/lib/python3.10/site-packages/torch/distributed/launch.py:178: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects --local_rank argument to be set, please
change it to read from os.environ['LOCAL_RANK'] instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions

warnings.warn(
/environment/miniconda3/lib/python3.10/site-packages/mmcv/init.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
warnings.warn(
/home/featurize/styletransfer/mmgeneration/tools/train.py:97: UserWarning: Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
warnings.warn(
/home/featurize/styletransfer/mmgeneration/tools/train.py:107: UserWarning: Setting MKL_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
warnings.warn(
Traceback (most recent call last):
File "/home/featurize/styletransfer/mmgeneration/tools/train.py", line 228, in
main()
File "/home/featurize/styletransfer/mmgeneration/tools/train.py", line 169, in main
cfg.dump(osp.join(cfg.work_dir, osp.basename(args.config)))
File "/environment/miniconda3/lib/python3.10/site-packages/mmcv/utils/config.py", line 596, in dump
f.write(self.pretty_text)
File "/environment/miniconda3/lib/python3.10/site-packages/mmcv/utils/config.py", line 508, in pretty_text
text, _ = FormatCode(text, style_config=yapf_style, verify=True)
TypeError: FormatCode() got an unexpected keyword argument 'verify'
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 19076) of binary: /environment/miniconda3/bin/python
tools/dist_train.sh: line 20: 19069 Segmentation fault (core dumped) PYTHONPATH="$(dirname $0)/..":$PYTHONPATH python -m torch.distributed.launch --nnodes=$NNODES --node_rank=$NODE_RANK --master_addr=$MASTER_ADDR --nproc_per_node=$GPUS --master_port=$PORT $(dirname "$0")/train.py $CONFIG --seed 0 --launcher pytorch ${@:3}
​

When doing inference, why we use paired image in pix2pix?

HI,

I am following the tutorial of Pix2Pix. In the tutorial, when doing inference, the input is
"image_path = 'tests/data/paired/test/3.jpg', which is a paired image.

Then I began to train Pix2Pix using our own dataset, after the training, when we input paired image, the result is pretty good, however, when we input only the domain A image, the translated B fake image have different result.
In real life inference, we do not have the ground truth along side with the input image. My question is why we use Paired image as the input in the tutorial?

When input is paired image:

When input is unpaired image:

As a further question, can we train pix2pix using unpaired methods?

Thanks
Tao

咨询

这个过程持续这么长时间正常么？GPU型号是TITAN Xp 12G显存

这个MMGeneration安装问题

关于这个 最适合的python版本是不是3.8啊？