-
Notifications
You must be signed in to change notification settings - Fork 6.9k
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
pretrained models for batch normalized version of vgg #152
Comments
I don't think you can take the weights from the model without batch norm and stick them in the model with batch normalization. The activation statistics will almost certainly be wrong at each batch-normalized layer if someone tries fine-tuning the model or otherwise continue training. |
Could we then also offer pretained weights for the batch normalized versions? Depending on how you obtain them anyway I could also look if I get a caffemodel converted to pytorch state dict. |
+1 for the request. |
According to here we should be able to reuse the retrained weight from e.g.
vgg16
and apply them tovgg16bn
we will just need to write a small conversion (as order infeatures
differs due to additionalnn.BatchNorm2d
layers).Do you agree? Are PR welcome on this?
The text was updated successfully, but these errors were encountered: