Please find the README's for each subquestion in the subfolders.
One thing to mention here is the general set up of files. Please download http://deeplearning.net/data/mnist/mnist.pkl.gz and store it with the same name in the root of this github directory. Furthermore, please download http://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz and unzip it in the root directory such that there exists the folder "cifar-10-batches-py" in the root directory of the repository.
All folder contain runnable python scripts. Those scripts can just be called via the terminal, e.g. in the subfolder latent: python2.7 auto_encoder.py
Problem 7: Dataset conversion & converting CIFAR to greystyle can be found in the utils.py file.