My input data consists of 2 modalities instead of 4

[olalla1999]

Hello!

I am Olalla, and I am a bit new in all this DL world. I am trying to implement your algorithm and I need to change the input_shape so that it only considers 2 modalities instead of 4. Also, I only have 1 label for the whole meningioma so the output_channels = 1 instead of 3. I think I have modified the whole code properly but, still, I get this error:

ValueError: Dimensions must be equal, but are 2 and 4 for '{{node loss_VAE/sub}} = Sub[T=DT_FLOAT](IteratorGetNext:2, model_3/Dec_VAE_Output/BiasAdd)' with input shapes: [1,2,80,96,64], [1,4,80,96,64]

Here I attach the model.py file modified:

model_modified_2inputs.zip

I hope someone can see what modification it lacks.

Thank you in advance!

Olalla