Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".
BSD 2-Clause "Simplified" License
214
stars
20
forks
source link
General code refactoring/cleanup done to prepare adding CAV-MAE to HuggingFace #26
Open
rationalism opened 6 months ago
This is some general code refactoring and cleanup I've already done locally to prepare for a PR to add CAV-MAE to HuggingFace (https://github.com/huggingface/transformers/pull/28246). This uses the standard Python formatting tools suggested by the HuggingFace guide (https://huggingface.co/docs/transformers/add_new_model), black and ruff. Not critical, but figured I might as well send it over for simplicity's sake.
This should all be pure refactors, ie., it should have no impact on the model or code behavior, but please let me know if I missed anything. Thanks!
Tag @YuanGongND