wangjianxiong-nreal

> For tiny backbones, pre-training is very important. @RangiLyu Thx for your reply. I will pre-train the backbone before using it on target datasets. I also read the tips from...

@yh-xxx You must have solved the problem, if somebody else need: change 1000 to 1 here: https://github.com/facebookresearch/DiT/blob/main/sample.py#L56 for example: before: y_null = torch.tensor([1000] * n, device=device) after: y_null = torch.tensor([args.num_classes]...