AOT-GAN-for-Inpainting

AOT-GAN-for-Inpainting copied to clipboard

Dominic-ZZ

Fixed conda environment error and 'num_samples=0' error

1

When trying to create a conda venv, I kept getting errors about the libraries not being found. To fix this I removed the build string from the environment.yml file. Code...

Dutra-Apex

Confuse about the my_layer_norm function and GAN loss function

4

Hi, thank you for your excellent work, I get a good result when run the demo. But when I read the source code, I get some problems about GAN loss...

SeeU1119

Cannot reproduce results from paper with pre-trained model

1

Hi ! Thanks for your work, the demo code is neat 🤗 I tried the `celebahq` pre-trained models on images and noticed it doesn't really "complete" parts of the face...

clementabary

Hey there, Loving the paper! Noobie question: I'm wondering, in case I want to choose a random image (not knowing the content) and matching the right pre-trained model to it,...

roimulia2

Style Loss is the major player for good results and not Adversarial Loss.

1

Hi! Thanks for the excellent codebase! I ran a few experiments to measure the importance of GAN in the current network. It turns out if we **don't use style loss**,...

praeclarumjj3

abhishek7467

Own dataset

1

I get the following error: `images_masked = (images * (1 - masks).float()) + masks ` `RuntimeError: The size of tensor a (256) must match the size of tensor b (455)...

aniol6

Cannot train the model

2

got the following error: 2024-03-10 10:12:48.171105: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-03-10 10:12:48.171155: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607]...

deepu-rajesh

c++

2

Very great work, does it support c++ inference?

xiangw369