Open SirZendom opened 5 years ago
Yes, as described in README,
Keras sequential model can be converted to convnet_drawer.Model (thanks to @wakamezake). Only Conv2D, MaxPooling2D, GlobalAveragePooling2D, Flatten, Dense layers are supported for this conversion.
Currently I have no plan to support the other layers now.
The Dropout-Layer doesnt seem to be represented. Error comes from the keras_util
NameError: name 'Dropout' is not defined