Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

about git lfs pull #6

Open
Jingranxia opened this issue Jan 7, 2025 · 5 comments
Open

about git lfs pull #6

Jingranxia opened this issue Jan 7, 2025 · 5 comments

Comments

@Jingranxia
Copy link

Hello, I would like to ask if git lfs pull is necessary. It downloads very slowly. Is it downloading test data? Is there any interface that can avoid this situation and directly perform inference on a single image

@Johanan528
Copy link
Collaborator

Sorry, we did not set up any interface. By the way, you could try downloading models from this mirror website: export HF_ENDPOINT=https://hf-mirror.com.

@Jingranxia
Copy link
Author

Jingranxia commented Jan 7, 2025

Thank you for your reply, I downloaded it from the source address and successfully ran Infer. However, I have two questions. The Infer program loaded 5 weights. If we only need to derive the depth map completion function, can we give up which weight? The second question is, what are the camera intrinsic parameters of the sample in test_cases you provided? Can you provide them for me to visualize the 3D point cloud

@Jingranxia
Copy link
Author

Jingranxia commented Jan 7, 2025

The reason why I asked the first question is that the inference speed is too slow. It takes me a few minutes from running the infer to the end. Is this normal

@Johanan528
Copy link
Collaborator

Hello, for inference, it takes approximately tens of seconds on an 80GB A100.

@Johanan528
Copy link
Collaborator

Regarding model loading, we will later encapsulate it into a pipeline to reduce the number of models that need to be loaded. We apologize for any inconvenience this may have caused.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants