Akshay Nagpal
Akshay Nagpal
I am facing similar problem with my model. Training loss is stuck at the margin with very low learning rate as well. Is there any solution yet?
I was facing the same issue with hard batching. I lowered the learning rate and made the change in hard batch function suggested in https://github.com/omoindrot/tensorflow-triplet-loss/issues/18#issuecomment-455031523 It started working. In my...