Peterou

>  What module is this? I lack this module after installing the environment，Thank you for your reply! Sorry, it's my fault. You could fix the error by removing the...

> Thank you for reading my message. I am very impressive by your work of CIPS. If you have time, please reply to me. Thank you very much.I am very...

 There are three interpolated models above. Which model do you want?

No problem. I plan to write a demo in next week.

OK, I have updated the repo. Preparing AFHQ dataset: ```bash # Prepare training dataset. python scripts/dataset_tool.py \ --source=datasets/AFHQv2/AFHQv2 \ --dest=datasets/AFHQv2/AFHQv2_stylegan2.zip ``` The pre-trained FFHQ checkpoints: [https://github.com/PeterouZh/CIPS-3D#pre-trained-checkpoints-including-generator-and-discriminator](https://github.com/PeterouZh/CIPS-3D#pre-trained-checkpoints-including-generator-and-discriminator). The start script: `exp/cips3d/bash/finetuning_exp/finetune_afhq.sh`....

Hi. Thanks for your interest in our work! "Class supervision" refers to the class label of an image. In fact, both projection-based loss and omni-loss employ class labels. But projection-based...

 Suppose there is a real image (x_real, y_real) and a generated image (x_fake, y_fake). y is the corresponding class label of x. Note that the original projection-based discriminator is...

> Sorry for the late reply. It is more common to calculate the FID between all training data and 50k generated data. Please refer to this site https://github.com/NVlabs/stylegan2-ada-pytorch#quality-metrics

I fix this issue by replacing "f3 = self.frame.iloc[:, 1:] > 0" [url](https://github.com/yingcong/HomoInterpGAN/blob/4b61ad1c2810f4bf129942bbd7d5a351d15526d1/data/attributeDataset.py#L220) with "f3 = self.frame.iloc[:, 3:-1] > 0".

Change the target_network_pkl to "AFHQ_r256_v1".