├── .github └── intro.png ├── .gitignore ├── LICENSE ├── README.md ├── notebooks ├── llm_inference.py ├── llm_only.ipynb ├── sf_vlm.ipynb ├── utils.py └── vlm_inference.py ├── requirements.txt └── src ├── localize_objects.py ├── model_frame_selection.py └── model_video_infer.py /.github/intro.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/.github/intro.png -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/README.md -------------------------------------------------------------------------------- /notebooks/llm_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/notebooks/llm_inference.py -------------------------------------------------------------------------------- /notebooks/llm_only.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/notebooks/llm_only.ipynb -------------------------------------------------------------------------------- /notebooks/sf_vlm.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/notebooks/sf_vlm.ipynb -------------------------------------------------------------------------------- /notebooks/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/notebooks/utils.py -------------------------------------------------------------------------------- /notebooks/vlm_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/notebooks/vlm_inference.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | git+https://github.com/haotian-liu/LLaVA.git 2 | decord==0.6.0 3 | av==11.0.0 -------------------------------------------------------------------------------- /src/localize_objects.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/src/localize_objects.py -------------------------------------------------------------------------------- /src/model_frame_selection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/src/model_frame_selection.py -------------------------------------------------------------------------------- /src/model_video_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kahnchana/mvu/HEAD/src/model_video_infer.py --------------------------------------------------------------------------------