search

penghao-wu / vstar

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"
https://vstar-seal.github.io/
MIT License
514 stars 33 forks source link

app.py #10

Open echo840 opened 7 months ago

echo840 commented 7 months ago

image

Hello, thanks for your great work. However, I ran app.py and encountered an error. How can I resolve it?

penghao-wu commented 7 months ago

Hi, could you please provide the error information in the terminal where you launch the app.py?

echo840 commented 7 months ago

Hi, could you please provide the error information in the terminal where you launch the app.py?

Thank you for your prompt response. It doesn't have any output, and it doesn't even enter the "inference" function.

penghao-wu commented 7 months ago

Could you please try it without demo.queue()?

echo840 commented 7 months ago

Could you please try it without demo.queue()?

image

penghao-wu commented 7 months ago

Maybe you can try to add the queue() back and turn off the proxy to see whether it would work. The latest error you encountered might be because the inference time is more than 60 seconds in this case so you need to use .queue().