Open whmrtm opened 7 years ago
load_model
is implemented in keras.models
. Try:
model = keras.models.load_model(model_path)
When I reload a saved model with keras.models.load_model(model_path)
I got a the following error:
TypeError: ('Keyword argument not understood:', 'freeze')
how can I overcome it?
@NicolettaK You got that error since keras_resnet library uses a custom BatchNormalization layer
The following code works for me: model = load_model(model_path, custom_objects={'BatchNormalization': keras_resnet.layers.BatchNormalization})
@NicolettaK You got that error since keras_resnet library uses a custom BatchNormalization layer
The following code works for me: model = load_model(model_path, custom_objects={'BatchNormalization': keras_resnet.layers.BatchNormalization})
@nhannguyen2709 it not works for me, I don't know why
Hi @0x00b1, when I was trying to load the saved resnet18, got the error: "ResNet18' object has no attribute 'load' . Can we have the load function implemented?