tinynn is a lightweight deep learning framework written in pure Python3 (with NumPy).
There are two branches (master and mini) in thie repo. The mini branch contains the minimal components to run a neural network. The master branch holds the latest stable code with more components and features. See Components down below.
git clone https://github.com/borgwang/tinynn.git
cd tinynn
pip install -r requirements.txtcd tinynn
# MNIST classification
python examples/mnist/run.py
# a toy regression task
python examples/nn_paint/run.py
# reinforcement learning demo (gym environment required)
python examples/rl/run.py- layers: Dense, Convolution2D, MaxPool2D, Dropout
- activation: ReLU, LeakyReLU, Sigmoid, Tanh
- losses: SoftmaxCrossEntropy, SigmoidCrossEntropy, MAE, MSE, Huber
- optimizer: SGD, Adam, Momentum, RMSProp
Please follow the Google Python Style Guide for Python coding style.
In addition, please sort the module import order alphabetically in each file. To do this, one can use tools like isort (be sure to use --force-single-line-imports option to enforce the coding style).
MIT