Closed yarkable closed 3 years ago
Thanks for your nice work, and, I wonder that when distilling, is student initialized with a pretrained model(e.g. after training for 12 epochs) or just with a pretrained backbone?
Just with an ImageNet pretrained backbone (provided by MMDet).
Got it, thanks.
Thanks for your nice work, and, I wonder that when distilling, is student initialized with a pretrained model(e.g. after training for 12 epochs) or just with a pretrained backbone?