- Data: Download and preprocessing
- MNIST: https://github.com/mgermain/MADE/releases/download/ICML2015/binarized_mnist.npz
- FOUR SHAPES https://www.kaggle.com/smeschke/four-shapes -> crop to (100,100) and turn to numpy file data.npy
- EMNIST: https://www.nist.gov/itl/products-and-services/emnist-dataset -> emnist-letters.mat
- Implement: Implement in MADE_pytorch.ipynb. All libs in this implementation are in the top line of codes.
- Ref: https://arxiv.org/abs/1502.03509 https://github.com/karpathy/pytorch-made http://bjlkeng.github.io/posts/autoregressive-autoencoders/ ... (See more at the end of the report)