GengDavid
GengDavid
Thanks for your great work. Find that you have provided [codes for ADE20K](https://github.com/uber-research/UPSNet/blob/master/upsnet/dataset/ade20k.py), but I can find results neither in the paper nor here. Have you tested your model on...
Hi, thanks for your great work! I am interested in training the once-for-all network but I met some problems when diving into your training code. [Line 198 in train_ofa_net.py](https://github.com/mit-han-lab/once-for-all/blob/0807662ec0354c98c808496d540518badb6b9a9b/train_ofa_net.py#L198) loads...
Thanks for your great work! Wonder that whether you would update it to PyTorch in your short-term plan? Thanks.
Hi, thanks for your great work. In configs, I see ```use_cls_token = True``` and ```vit_classifier = "prompt"```. While in vit.py [line 447](https://github.com/google-research/l2p/blob/e575cde9d77aed67e5cba8e47d5f5e5a2337a5ae/models/vit.py#L447), ``` elif self.classifier == 'prompt': x = x[:,...
Hi @Doubiiu, I am trying to train DynamiCrafter by myself. According to your paper, the second stage is based on VideoCrafter. Do I need to download VideoCrafter's checkpoint and load...
When runing ```scripts/finetune_cls.sh```, the following error occurs. ```ValueError: Some specified arguments are not used by the HfArgumentParser: ['--eval_path', './data/val.json', '--eval_image_folder', './data/image']```