Open cbodenst opened 4 years ago
The newest keras version allow us to save models not only as .h5 keras files, but also as saved model.
However, custom layers must be correctly declared to support this.
I.e the BatchNormalization layer should define its signature for "call" properly as: def call(self, inputs, **kwargs): instead of
def call(self, inputs, **kwargs):
def call(self, *args, **kwargs):
You can read more about this issue here: https://github.com/tensorflow/tensorflow/issues/38384
The newest keras version allow us to save models not only as .h5 keras files, but also as saved model.
However, custom layers must be correctly declared to support this.
I.e the BatchNormalization layer should define its signature for "call" properly as:
def call(self, inputs, **kwargs):
instead ofdef call(self, *args, **kwargs):
You can read more about this issue here: https://github.com/tensorflow/tensorflow/issues/38384