Open Sebastian514 opened 2 years ago
I used the default hyper-parameters and trained the model on a single Nvidia Titan Xp. And the training logs show that the loss didn't converge. It apparently leaded to a bad performance which evaluated on coco.
What should I do?
I used the default hyper-parameters and trained the model on a single Nvidia Titan Xp. And the training logs show that the loss
didn't converge. It apparently leaded to a bad performance which evaluated on coco.
What should I do?