Lemon Two
Lemon Two
> Hi @XiaominLi1997 The config is here https://github.com/NVlabs/GroupViT/blob/main/configs/default.yml#L90 Thanks. And I have another question, in the reference phase, can GroupViT only group the objects appearring in the training samples? If...
> @Suhail To generate features from the pretrained backbones, just use a transform similar to the standard one used for evaluating on image classification with the typical ImageNet normalization mean...
> Hi guys, the code is released. Hello, thanks for releasing the code of Dreamvideo, but I am not sure about the following questions: 1. Can I generate videos with...
> > > Hi guys, the code is released. > > > > > > Hello, thanks for releasing the code of Dreamvideo, but I am not sure about the...
Let me check it, thanks.
> Hi Xiaomin. Have you found the problem? hi, I trained on modelscope, and disable gradient_checkpointing, the GPU usage is always unstable. 
> @KaiyueSun98 Hello, I've downloaded the weight as what you mentioned and used the `configs/stable-diffusion/v1-finetune.yaml` for training. There is an error code like `Some weights of the model checkpoint at...
> > > In practice, to avoid rapid overfitting and stabilize the fine-tuning, we re-weight ReFL loss and regularize with pre-training loss. > > Our code is only used to...