Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pytorch model doesn't produce the intended output #63

Open
Samir55 opened this issue Dec 26, 2018 · 1 comment
Open

Pytorch model doesn't produce the intended output #63

Samir55 opened this issue Dec 26, 2018 · 1 comment

Comments

@Samir55
Copy link

Samir55 commented Dec 26, 2018

Hello authors,
I am encountering a problem that I couldn’t reproduce the same output by
training your model on the ILSVRC2012 training set. The model losses
(G_CE And G_entr) tend to stabilize around 3.1 across epochs. Also,
the colorized images tend to have a somehow yellowish color. I trained
the model for 6 epochs. I am using Python 3.5 and CUDA 9.1 with GTX
1060 GPU. Can you help me discover what’s going on? I am adding
here some output pictures and the loss graph. Thanks for your time and
efforts.

00000195_0p031_fake_reg
00000198_0p125_fake_reg
loss_graph

@richzhang
Copy link
Collaborator

I believe I did not do the initialization properly in the pytorch code. I am looking into it. Thanks for your patience.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants