kxgong
kxgong
> 确认一下代理开的有没有问题，比如端口是不是10808 你好，例如确认了端口是12345，是否只需要改成127.0.0.1:12345？
> > _No description provided > > Do you have the foggy cityscapes dataset?Can you share it with me?My email :[[email protected]](mailto:[email protected]). Thank you. Hi, have you got the shared dataset?...
The problem is caused by the ckpt is saved on 6 gpus but is reloaded with 4 gpus. Try torch.load(..., map_location=[torch.device('cpu'))
Thanks for your instant reply! Nasty teacher is a solid work!
It seems that I also met the same problem. I run DPLCLIP(VIT-B16) on DG using default configurations (i.e., hype-parameters like lr). The average accs are: 72.2 (VLCS), 95.12 (PACS), and...
> I have also encountered some difficulties in reproducing your results on the VLCS dataset. In Table 1 of the paper, the paper reported that DPLCLIP achieved an accuracy of...
> I attempt to choose the best performance (in early steps/epochs) to compute the average accuracy, and the performance is about 0.778 in the VLCS dataset. > > > >...
> Alright so this is the script I'm using for HF->DCP. It uses the safetensors weights (but can easily be converted to load a torch.save instead), which only exist in...
I got better results than you (not good results), and I can see the vague shapes. I used a smaller dataset.
Hi, I have a question. Why use images to train magvit-2? Should it designed for videos?