search

OpenGVLab / Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
https://vchat.opengvlab.com/
MIT License
3k stars 247 forks source link

Video Caption Model #54

Closed yinkangning0124 closed 1 year ago

yinkangning0124 commented 1 year ago

Hi, Thanks for your great work, I wanna know how can i use the video caption model?

Kangning

Andy1621 commented 1 year ago

I'm not sure about your specific problem, but to use VideoChat for caption, you can follow the demo in https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat/demo.ipynb

yinkangning0124 commented 1 year ago

sorry to bother, I wanna ask another question. When running video_chat_with_ChatGPT/app.py, I got this problem: RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasSgemmStridedBatched( handle, opa, opb, m, n, k, &alpha, a, lda, stridea, b, ldb, strideb, &beta, c, ldc, stridec, num_batches)

Could you tell me how to fix it?

yinkangning0124 commented 1 year ago

By the way, I upload the example video

yinkangning0124 commented 1 year ago

I find the solution, that is you should change the torch version to 1.12.1 and the torchvision version to 0.13.1

Andy1621 commented 1 year ago

Thanks for your try~