tinynn是一个轻量级的深度学习框架，用Python3（包括NumPy）编写

tinynn是一个轻量级的深度学习框架，用python3（包括NumPy）编写

tinynn

tinynn is a lightweight deep learning framework written in Python3 (with NumPy).

Getting Started

Install

pip install tinynn

Run examples

git clone https://github.com/borgwang/tinynn.gitcd tinynn/examples# MNIST classificationpython mnist/run.py # a toy regression taskpython nn_paint/run.py # reinforcement learning demo (gym environment required)python rl/run.py

Intuitive APIs

# define a modelnet = Net([Dense(50), ReLU(), Dense(100), ReLU(), Dense(10)]) model = Model(net=net, loss=MSE(), optimizer=Adam(lr))# trainfor batch in iterator(train_x, train_y): preds = model.forward(batch.inputs) loss, grads = model.backward(preds, batch.targets) model.apply_grads(grads)

Components

layers: Dense, Conv2D, ConvTranspose2D, RNN, MaxPool2D, Dropout, BatchNormalizationactivation: ReLU, LeakyReLU, Sigmoid, Tanh, Softpluslosses: SoftmaxCrossEntropy, SigmoidCrossEntropy, MAE, MSE, Huberoptimizer: RAdam, Adam, SGD, Momentum, RMSProp, Adagrad, Adadelta

Contribute

Please follow the Google Python Style Guide for Python coding style.

License

MIT

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。