├── .github └── ISSUE_TEMPLATE │ ├── bug.md │ ├── feature_request.md │ └── other.md ├── .gitignore ├── CITATION.cff ├── LICENSE ├── MODEL_ZOO.md ├── README.md ├── assets ├── k400.gif ├── ssv2.gif ├── videomae.jpg ├── view1.gif ├── view2.gif ├── view3.gif ├── view4.gif ├── view5.gif ├── view6.gif └── view7.gif ├── notebooks ├── reconstruction.ipynb └── retraining.ipynb ├── requirements.txt ├── setup.py └── videomae ├── __init__.py ├── blocks ├── __init__.py ├── basic.py ├── vit_decoder.py └── vit_encoder.py ├── layers ├── __init__.py ├── attention.py ├── drop_path.py ├── mlp.py └── patch_embed.py ├── model_configs.py ├── utils ├── __init__.py ├── masking_generator.py └── sinusoid_encoding_table.py ├── videomae_finetune.py └── videomae_pretrain.py /.github/ISSUE_TEMPLATE/bug.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/.github/ISSUE_TEMPLATE/bug.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/.github/ISSUE_TEMPLATE/feature_request.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/other.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/.github/ISSUE_TEMPLATE/other.md -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/.gitignore -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/CITATION.cff -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/LICENSE -------------------------------------------------------------------------------- /MODEL_ZOO.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/MODEL_ZOO.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/README.md -------------------------------------------------------------------------------- /assets/k400.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/k400.gif -------------------------------------------------------------------------------- /assets/ssv2.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/ssv2.gif -------------------------------------------------------------------------------- /assets/videomae.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/videomae.jpg -------------------------------------------------------------------------------- /assets/view1.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view1.gif -------------------------------------------------------------------------------- /assets/view2.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view2.gif -------------------------------------------------------------------------------- /assets/view3.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view3.gif -------------------------------------------------------------------------------- /assets/view4.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view4.gif -------------------------------------------------------------------------------- /assets/view5.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view5.gif -------------------------------------------------------------------------------- /assets/view6.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view6.gif -------------------------------------------------------------------------------- /assets/view7.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/assets/view7.gif -------------------------------------------------------------------------------- /notebooks/reconstruction.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/notebooks/reconstruction.ipynb -------------------------------------------------------------------------------- /notebooks/retraining.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/notebooks/retraining.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow>=2.12 2 | opencv-python>=4.1.2 3 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/setup.py -------------------------------------------------------------------------------- /videomae/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/__init__.py -------------------------------------------------------------------------------- /videomae/blocks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/blocks/__init__.py -------------------------------------------------------------------------------- /videomae/blocks/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/blocks/basic.py -------------------------------------------------------------------------------- /videomae/blocks/vit_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/blocks/vit_decoder.py -------------------------------------------------------------------------------- /videomae/blocks/vit_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/blocks/vit_encoder.py -------------------------------------------------------------------------------- /videomae/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/layers/__init__.py -------------------------------------------------------------------------------- /videomae/layers/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/layers/attention.py -------------------------------------------------------------------------------- /videomae/layers/drop_path.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/layers/drop_path.py -------------------------------------------------------------------------------- /videomae/layers/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/layers/mlp.py -------------------------------------------------------------------------------- /videomae/layers/patch_embed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/layers/patch_embed.py -------------------------------------------------------------------------------- /videomae/model_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/model_configs.py -------------------------------------------------------------------------------- /videomae/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/utils/__init__.py -------------------------------------------------------------------------------- /videomae/utils/masking_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/utils/masking_generator.py -------------------------------------------------------------------------------- /videomae/utils/sinusoid_encoding_table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/utils/sinusoid_encoding_table.py -------------------------------------------------------------------------------- /videomae/videomae_finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/videomae_finetune.py -------------------------------------------------------------------------------- /videomae/videomae_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/innat/VideoMAE/HEAD/videomae/videomae_pretrain.py --------------------------------------------------------------------------------