SKBL5694

Can I ask more than 1 question simultaneously through the blip_vqa model?

5

I know how to ask the same question for multiple images at the same time and it will return different results to different images; how do I swap? I mean:...

Thanks for your great work and sorry for bothering you. Because I only have a single GPU with 6G memory(maybe I can borrow a 3090 for several days if I'm...

How to make action recognition result visualization

41

How to generate action recognition gif like the demo in ''mmskeleton/demo/recognition

OSError: CUDA is required to compile MMSkeleton!

4

I found the same issue in #310 . In that issue, the suggestion is to choose the correct CUDA version according to the pytorch version and the example is the...

How to organize the dataset

1

Thanks for the nice work. I would like to know how to organize the data. I currently have ucf101 data. The default data structure is: "ucf101_rawframes\rawframes\101 classes folder" Because I...

Some doubts about weights

2

I use train_vqa.py to finetune the origin weights "model_base_vqa_capfilt_large.pth" which file size is about 1.34GB. But when I finish the finetune, the new weight is about 4.04GB. Both weights can...

Finetune vqa by own data

2

Hi, I'm here again. This time I meet a new question. I want to finetune the vqa checkpoints with my own data. There are two questions confused me. The 1st...

无法在macos上运行 因为代码中有个参数只能在win上使用

1

‘from subprocess import Popen, CREATE_NEW_CONSOLE’ 中CREATE_NEW_CONSOLE这个函数仅在windows上可用，查了查mac上的平替版本，但因为本人太菜，没搞出来。 也就是说在创建新的终端的时候，mac上无法执行main.py中的代码，希望大佬有空大时候研究一下怎么办。

rt

How to make the code run using the local gpu

1

I run the notebook on my PC, when I use learn.fintune(), I found that the time consumed is far higher than mentioned in the notes, I found that this is...