Yifei Yang

Hi @keys-zlc, Thx for your interest. You may pull the updated master branch of MMGen and FaceStylor, then try again.

Hi @yeqingmei123, Thx for your interest. `swap_layer` is not supposed to be larger than 7. You can try a smaller number. I will fix this bug later.

Hi @Emily0819, we hasn't provided a script for visualize `json` file. However, you can use visualization backend like tensorboard for your purpose. Just install tensorboard and add lines below. ```...

Hi @DCMJY , take `configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py` as an example, delete its `metrics` field and run ``` bash tools/eval.sh configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py CKPT_PATH --samples-path PATH_TO_SAVE_IMGS --num-samples 202599 ``` Then you will find images under...

@LeoXing1996 Sampling images this way seems not convenient for users. Maybe we can modify `xxx_demo.py` for this usage.

Hi @xiaojifu , you may modify the test_pipeline in your config this way. ``` test_pipeline = [ dict( type='LoadImageFromFile', io_backend='disk', key='pair', domain_a=domain_a, flag='color'), dict( type='Resize', keys=[f'img_{domain_a}'], scale=(256, 256), interpolation='bicubic'), dict(type='RescaleToZeroOne',...

Hi @oschan77, I'll reply to you after reproducing your problem and this [issue](https://github.com/pytorch/pytorch/issues/74437) may be helpful. And you are not supposed to run `train.py` directly since DP is not supported...

Thanks for your remind. We will appreciate it a lot if you'd like to make a PR to fix this typo.

Hi @KeranLi, can you run `gcc --version | head -n1` and show me the output?

Sure, you can set a separate learning rate in the optimizer. Example: https://github.com/open-mmlab/mmgeneration/blob/master/configs/_base_/models/biggan/biggan_128x128.py#L30-L32