Yichuan Mo

Results 12 comments of Yichuan Mo

> In 111 line of the implementaion of infogan, nn.softmax is added to aux_layer. But the returned data of aux_layer is used to compute crossentropy loss in 277 line. Doesn`t...

Hi, AYUSH-ISHAN! Would you like to share the changes made in your code? I find this repo doesn't work well on my computer with CUDA==11.7, torch==1.8.0.

Thank you very much! It is quite kind of you! I try almost all the versions for Pytorch and none of them works. Finally, the problems are solved after replacing...

Same with my situation. Do you solve this issue?

Hello, Jaehoon. I encounter the same problem. I conjecture this is because your **Tensorflow** package is not installed correctly. I recommend that you should follow the tips provided by **https://www.tensorflow.org/install/pip**...

However, after solving the above issue, also as a 4*A100 user, I meet the **CUDA out of the Memory** issue. Do you encounter this issue for the code in this...

Ok, thank you very much!

Hi, Jaehoon! Does your training speed on 4A100 improve? After re-checking my experiment, I found it is still quite slow: for each GPU, the utilization rate is around 50%. Do...

Same question as @eslambakr, hope someone could merge two separate repositories together and share codes with the community.

Hi, guys, I would like to ask the number of iterations you adopt when you calculate FID. Is the high FID possibly due to the insufficient training?