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
Fixed EfficientNetV2's MBConvBlock output phase. #17364
Fixed EfficientNetV2's MBConvBlock output phase. #17364
Conversation
Thanks for the PR. What validation accuracy do you see with the modified model on the imagenet test set? CC @ianstenbit |
Thanks Sebastian and Francois -- looks like this fix will also need to be made in KerasCV's EfficientNetV2 (and it will be in keras-team/keras-cv#1146) |
Pending on another reply from @fchollet . |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks!
Fixes keras-team/tf-keras#329
Unindents output phase of MBConvBlock so that it is applied regardless of SE ratio.
To my knowledge, when inspecting the EfficientNetV2's configs, all MBConvBlocks use SE block part so the models and weights should be unchanged.