Fix Squeeze for channel first network creation

keras-team / keras-applications

Reference implementations of popular deep learning models.

Other

2k stars 910 forks source link

Fix Squeeze for channel first network creation #178

Closed andreABbauer closed 4 years ago

andreABbauer commented 4 years ago

The current efficientnet implementation does not work in channel first mode, because the reshape dimensions are hardcoded to channel last. This fix adds full channel first support

taehoonlee commented 4 years ago

Thank you for the PR, @andreABbauer.