Is my trained loss value reasonable?
deyingk opened this issue · comments
deyingk commented
Hi,
Could you please help me confirm my trained unsupervised loss function is in a reasonable range?
(Since the supervised training code is not released, I could't verify it on the FreiHand.)
The following is the loss function from the stage of unsupervised training. The backbone is ResNet152. After 100 epochs, the loss is around 3.60.
Thanks so much!
Adrian Spurr commented
Yes this looks reasonable.