:et us build a simple GAN capable of generating handwritten digits $("$Deep Learning with TensorFlow $2$ and Keras" page $193.).$ We will use the MNIST

handwritten digits to train the network. We use the TensorFlow Keras dataset to access the MNIST data. The data contains $60,000$ training images of

handwritten digits each of size $2828.$

Then see page $399$ in Deep Learning with TensorFlow $2$ and Keras" for the example on variational autoencoder. Train that example VAE to generate new

images $($code is in the book$).$

For the submission send:

the code you used to build GAN

the images of handwritten digits generated by our GAN

Interpret the result of variational autoencoder after $100$ epochs; interpret the generated images with the input.