Deepest Debug Challenge: can you squash them all?

WARNING: this model is implemented to NOT work correcly. DO NOT use this for your application. It will hurt you.

This is a quiz code for debugging a badly-implemented neural network.

The code runs fine and trains the model somehow, but not correctly.

You are given a task to fix all the ML-logical bugs in the code.

How to challenge yourself

Run train.py to train and test the model.

Do not use batch normalization.
Do not add network parameters. i.e. Do not stack more layers naively. It won't help.

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
README.md		README.md
dataloader.py		dataloader.py
definitely_mnist.npz		definitely_mnist.npz
model.py		model.py
train.py		train.py