Keras replacing input layer

Question

The code that I have (that I can\'t change) uses the Resnet with my_input_tensor as the input_tensor.

model1 = keras.applications.resnet50.ResNe         


        

Answer 1

For tf.keras in Tensorflow 2, using tfsurgeon did not work as I had custom layers.

What did work was changing layer._batch_input_size (note the underscore)

Hacky, but got the job done.