-
Notifications
You must be signed in to change notification settings - Fork 500
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
dimension is not compatible with "net" model. #21
Comments
Here is how a tensor looks at this point in the code when using the
|
The flag |
Thank you for your answer @richzhang ! Out of curiosity, is there any way to train the CNN weights instead of only the linear layer on top with your code ? Thanks! |
Yes. Use |
Ok got it! That's what I thought, great to have the confirmation. Thanks again! |
When using
--model net
for using an off-the-shelf network,train.py
breaks here:PerceptualSimilarity/models/networks_basic.py
Line 194 in 2416334
because the dimensionality don't match. When using
net-lin
models, the dimensionality is [50, 1, 1, 1] while this wrapping into arrays doesn't happen when usingnet
models.Is there a reason for this wrapping under the
net-lin
model?The text was updated successfully, but these errors were encountered: