triplet-reid icon indicating copy to clipboard operation
triplet-reid copied to clipboard

Published 20 hours ago • verified publisher icon VisualComputingInstitute

Transfer Learning, freezing layers

Open mazatov opened this issue 5 years ago • 0 comments

I'm trying to do a transfer learning for my dataset. I have only ~30 persons, but I do have a lot of images per person (~500 - 2000) . I wanted to freeze the initial layers of the model and just train the head as I'm worried about overfitting.

Would I only need to change is_training = False on this line of code?

https://github.com/VisualComputingInstitute/triplet-reid/blob/a538696b89654180f69f19d17679fa48a0346d88/train.py#L286

mazatov avatar Feb 28 '20 13:02 mazatov