0

I have a sequential model with a custom loss function for training. For prediction and validation however, I want to remove one layer. Is there any way to do this? The easiest thing I could think would be within a custom metric by being able to get the value of output from a previous layer without access to the input. Alternatively, I could run prediction and verification on a separate model, but I worry about constructing a separate model because I want the weights to be saved. Any suggestions? I have spent a lot of time with this and any thing I try has involved scope issues. I took a look at this: Keras, How to get the output of each layer? but every answer I see requires me to know the inputs.

SA3709
  • 192
  • 2
  • 11
  • Have a look at [this](https://stackoverflow.com/questions/41668813/how-to-add-and-remove-new-layers-in-keras-after-loading-weights) , if this does not help, i think you need to give more detail. – Abdirahman Nov 18 '19 at 21:07
  • Yeah that is what I had started out with, then I started following guidance from somebody who said that the second model in that solution wouldn't have the same weights... I eventually gave up and tested it myself and he was wrong. – SA3709 Nov 18 '19 at 21:59

1 Answers1

1

You can create separate models. Each model will need to be compiled. My solution was of this form...

inputs = Input(input_shape)
model = Conv2D(32, [3,3])(inputs)
# pass the model through some layers
# finish the model
model = Model(inputs=inputs, outputs=model)

input_2 = Input(input_shape)
second_model = model(input_2)
# pass the second model through some layers
second_model = Model(inputs=inputs, outputs=second_model)

model.compile(...
second_model.compile(...

Now any training done to second_model affects the weights of model, allowing you to do training off of second_model and predictions with model.

SA3709
  • 192
  • 2
  • 11