Hi Stackoverflow community,
I am solving a problem here where I have to skip some layers of a Keras model during the Evaluation/Validation phase. "Cutom_VGG_Model" output should directly go to "Classifier" (since output and input shapes for both are the same, respectively). This would be a new evaluation strategy. Training is performed on the same model without any change. Kindly suggest some ways to solve it.
I found some solution on Keras documentation where they create Custom Model and override the "test_step" method. But I am not able to formulate the code. Below is the link to the documentation I am referring to :
https://keras.io/guides/customizing_what_happens_in_fit/
I am using Tensorflow Keras.
My requirement is to calculate the validation loss on this NEW modified Evaluation strategy after each epoch. Also, the final evaluation will also be performed with this new modified evaluation strategy.
Thanks in advance!