zhl98

accuracy variation depending on the number of GPUs used

10

Hello,Thank you very much for your code！ I used the setting of dytox in the code for 10 steps of training, but I failed to achieve the accuracy in the...

数据集放哪

8

下载的test2k数据集应该放在什么目录下面

an inplace operation

5

Hello, I encountered this problem during the training process. Do you know where the problem is? The dimension of torch. cuda. LongTensor is [1,25] 

I saw install_ pytorch17.sh, it is pytorch=1.7.0 torchvision=0.8.1 cudatoolkit=10.2. But this cuda version cannot run on A6000. I have changed it to a new version of pytorch and cuda, but...

Finetuning VQA on BLIP2

9

Hi, Can you add the VQA fine-tuning function of BLIP2? In the paper, when you fine-tune the VQA task, you will fine-tune the image encoder. When I use the `freeze_vit:...