A tiny deep learning framework using numpy as backend. It has a tensor autograd engine inspired by Andrej Karpathy's micrograd and a pytorch like API
There's no need to for a new deep learning framework but it is useful as a learning tool.
The file demo.ipynb has a demo classification problem. And in
demo-mnist.ipynb a demo of classifying MNIST digits.
Run test against pytorch
python test.py
- Add sigmoid, softmax and train with cross entropy
- Add convolutional layers
- Test on MNIST
- Add optimizers