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

bug: VGG16 without pretrained=True option? #54

Closed
CM-BF opened this issue Jul 24, 2019 · 3 comments
Closed

bug: VGG16 without pretrained=True option? #54

CM-BF opened this issue Jul 24, 2019 · 3 comments
Assignees
Labels
bug Something isn't working

Comments

@CM-BF
Copy link

CM-BF commented Jul 24, 2019

In train.py line 111 vgg16 = torchvision.models.vgg16(), there may be a missing option: pretrained=True.
By default, pretrained=False.
Thus, perhaps perceptual loss does not work.

@CM-BF CM-BF added the bug Something isn't working label Jul 24, 2019
@QianyeYang
Copy link

just found the same problem

@BostonLobster
Copy link

Also found it just now, could you please fix it?@avinashpaliwal

avinashpaliwal added a commit that referenced this issue Dec 3, 2019
@avinashpaliwal
Copy link
Owner

Thanks for pointing out the issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

4 participants