Jinghui Lu
Jinghui Lu
Great, cheers.
Hi, the caption "这段文字" {} "描述的是哪个区域？" fails to infer location tokens, just wondering which datasets are used for pretraining OFA_CN, so I can use the data from those datasets to...
Hi, I used pretrained large checkpoint as well as the finetuned refcocog checkpoint, in both cases, the model fails in inferring location tokens. Using pretrained large model as a demo....
Hi, this is probably the all I have, my desktop was withdrawn by the school. However, you can easily replicate the experiments by formatting the data according to the csv...
> 方便分享下用到的包的版本嘛？ - OS:CentOS Linux 7 (Core) - Python:3.8 - Transformers:4.29.0dev - PyTorch:2.0.0 - CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :11.7
I think you should change your loss to cross entropy loss instead of using binary cross entropy loss: line: criterion = nn.BCEWithLogitsLoss() -> criterion = nn.CrossEntropyLoss()
我也遇到这个问题了，请问你解决了吗，同cuda11.2
我试了cuda11.6，还是不行，torch也从2.0换成了1.13.1，不清楚问题是出在哪里