Open risingClouds opened 6 months ago
the log as follow:
I have the exact same issue. I don't seem to understand why loss does not drop.
How many epochs did you train it for?
The problem was solved. This happened because I was not using copy.deepcopy to define the student and teacher in the beginning.
When I try to trian resnet50 by dino on on X-Ray dataset with 1000 images, the loss is not drop, even increase some time. Have anyone met the same issue and solve it. the config as follow:(at first, I make all the hyper parmeter default, but the loss is not decrease)