This repository contains a Keras implementation using the MNIST digits dataset.
It improves upon the results demonstrated in the Keras blog.
To achieve better performance, the model employs:
- deeper convolutional architecture
- batch normalization layers
- max pooling rather than strided convolutions
Latent Space Embedding:
A requirements.txt file has been provided.
Once the repository has been cloned, create a new conda environment:
cd DeepConvolutionalVariationalAutoencoder
conda create env --name DCVAE --file requirements.txt
conda activate DCVAERun training from the command line:
cd code
python train.pyRun training with jupyter notebook:
cd notebook
jupyter notebook