You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Fix a bug that pooling layer is merged with convolution layer that does
not use that layer as input layer.
Fix ZeroPadding layers parsing in Keras so the layer that use it can
correctly get the padding info if the ZeroPadding is not directly
followed by the layer that use it.
There is one issue remain: The model uses Cropping2D layers, which is not supported by HW. It seems use the ZeroPadding and Cropping to ship pooling results and then concatenate those results. Since it is ignored by now, The converted network will be less precise.
Hi, all
I faced the below error on converting NASNetMobile by Keras application for DV.
nasnetmobile.zip contains the following files.
Best regards,
Kobayashi
The text was updated successfully, but these errors were encountered: