Unofficial keras(tensorflow) implementation of MAE model described in ‘Masked Autoencoders Are Scalable Vision Learners’.
This work has been done on the basis of,,

Currently, only pre-training model is supported. But you can easily fine-tune the model using its encoder part.
It is not complete, flawless implementation, so its performance could be different from the paper.
If there is anything to modify, please make it right 🙂 Thanks.

Contact on my bio: [email protected]


View Github