TinyTensor: Deep Learning Library in Python

What is TinyTensor?

TinyTensor is an open-source deep learning library built from scratch in Python, inspired by Joel Grus' approach. This project includes 2 examples for creating a Non-Linear Neural Network and training it in order to predict the common XOR and FizzBuzz problems.

Getting Started

To use this deep learning library locally, you have 2 methods available:

1. Install locally
2. Use the Docker Image

Method 1: Install Locally

1. Clone the Repository:

git clone https://github.com/michaelradu/tinytensor.git

2. Import the Library files:

# Example of basic imports for training a Neural Network
from tinytensor.train import train
from tinytensor.nn import NeuralNet
from tinytensor.layers import Linear, Tanh
from tinytensor.optim import SGD

Optional. Export your model:

import pickle

with open('./models/trained_pipeline-0.1.0.pk1', 'wb') as f:
    pickle.dump(net, f)

3. Build Awesome Things!

Method 2: Use the Docker Image

1. Clone the Repository:

git clone https://github.com/michaelradu/tinytensor.git

2. Build Docker Image:

cd tinytensor
docker build -t tinytensor-app .

3. Run Docker Container:

docker run tinytensor-app

2. Import the Library files:

# Example of basic imports for training a Neural Network
from tinytensor.train import train
from tinytensor.nn import NeuralNet
from tinytensor.layers import Linear, Tanh
from tinytensor.optim import SGD

Optional. Export your model:

import pickle

with open('./models/trained_pipeline-0.1.0.pk1', 'wb') as f:
    pickle.dump(net, f)

3. Build Awesome Things!

Dependencies

• Numpy
• Docker (Optional)

Project Structure

• tinytensor: This directory contains the deep learning library files.
  • tinytensor/_init_.py: Default init file for python libraries.
  • tinytensor/data.py: Tools for iterating over data in batches.
  • tinytensor/layers.py: Layers for training Neural Networks.