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.

Sign up for GitHub

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

Fixed link to video processing pipeline code #2660

Merged
merged 2 commits into from
Feb 13, 2025
Merged

Fixed link to video processing pipeline code #2660

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b5fb2fc
Update smolvlm.md
bharathsivaram10 Feb 10, 2025
c318d61
Change path to video processing script to permalink
bharathsivaram10 Feb 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion smolvlm.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,7 +146,7 @@ SmolVLM's tiny memory footprint also implies that it requires far fewer computat

Given SmolVLM's long context and the possibility of tweaking the internal frame resizing of the model, we explored its suitability as an accessible option for basic video analysis tasks, particularly when computational resources are limited.

In our evaluation of SmolVLM's video understanding capabilities, we implemented a straightforward [video processing pipeline code](https://github.com/huggingface/smollm/blob/main/inference/smolvlm/SmolVLM_video_inference.py), extracting up to 50 evenly sampled frames from each video while avoiding internal frame resizing.
In our evaluation of SmolVLM's video understanding capabilities, we implemented a straightforward [video processing pipeline code](https://github.com/huggingface/smollm/blob/7dfcd81c046a946031291c11451e9398609a0aeb/tools/smolvlm_local_inference/SmolVLM_video_inference.py), extracting up to 50 evenly sampled frames from each video while avoiding internal frame resizing.
This simple approach yielded surprisingly competitive results on the CinePile benchmark, with a score of 27.14%, a performance that positions the model between InternVL2 (2B) and Video LlaVa (7B).


Expand Down