How to choose from which layer of a pretrained model (image classification) to start unfreezing?

  1. I’m wondering what steps people take to decide on the part of the model they’re going to unfreeze. Do you do multiple experiments? Since the use of GPU is expensive, you must have some guidelines.Note: I know the relationship between size of dataset, how close dataset is to the original dataset and how much that impacts whether or not we train more layers. However is there a rule of thumb involving the depth of the model to get the approximate layer?
    Example: Try unfreezing model starting from Layer number 169, or layers between 70-100

  2. How much does one need to know specifics of the pretrained model? Can I use it without knowing the architecture?

Hi @justAnotherUser,

I believe this forum would be able to help you better for this question: