kiwigrad 0.23

Mini deep learning framework

Kiwigrad

Kiwigrad? yes, it is another version of micrograd that was created just for fun and experimentation.

Install

To install the current release,

pip install kiwigrad

Kiwigrad Library

Kiwigrad library is a modified version of the micrograd and the minigrad packages with additional features. The main features added to Kiwigrad are:

• Training is faster due to the C implementation of the Value object.
• Methods for saving and loading the weights of a trained model.
• Support for RNN(1) feedforward neural networks.

Examples

• In the examples folder, you can find examples of models trained using the Kiwigrad library.
• Here is a declaration example of an MLP net using Kiwigrad:

from kiwigrad import MLP, Layer

class PotNet(MLP):
    def __init__(self):
        layers = [
            Layer(nin=2, nout=16, bias=True, activation="relu"),
            Layer(nin=16, nout=16, bias=True, activation="relu"),
            Layer(nin=16, nout=1, bias=True, activation="linear")
        ]
        super().__init__(layers=layers)

model = PotNet()

TODOS

• Include the activation functions tanh in the Value object.
• Add a notebook example for training a neural network on a regression problem.