Spaces:
Sleeping
Apply for community grant: Academic project (gpu)
I am writing to apply for a GPU grant to support the project InstructCV. The aim of this project is to develop a universal model, which is also known as a vision generalist, capable of performing various visual tasks using different language prompts. This space is used as a demo for our paper.
As a student dedicated to making a positive impact on the research community, I plan to make this model accessible to everyone. The paper and source code will be released recently.
The inference time for processing a single image takes approximately 20 minutes, severely impacting the user experience. To unlock the model's full potential and ensure a seamless user experience, the use of GPU technology is crucial.
I am eagerly looking forward to the possibility of collaborating with your organization and sincerely appreciate your consideration of my application.
Thank you for your time and attention!
Hi @yulu2 , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus
Thank you so much!
I used T4 (grant free) for inference, but the speed is different from when I used the same T4 before. Previously, I used a paid T4 Small, and inference only took 20 seconds. But now, it's been over 200 seconds, and there are still no results. Do you know what might be the reason for this? Thank you!!
@yulu2 Looks like the inference is done on CPU. https://huggingface.co/spaces/alaa-lab/InstructCV/blob/9c6e7dc78697813074612ca3a8ea83e21e704b29/app.py#L40
Thanks a lot! I forgot to change that line : )