Home

This is the documentation for cxxnet, a fast and short implementation for neural network in CPU/GPU

Getting started

• Read Tutorial to get started, play cxxnet on MNIST, run a feed forward neural network and convolution neural network in 3 minutes!

=

Parameter Setting

To understand more about cxxnet setting, this section will introduce all parameters of cxxnet and the effect of parameters. In general, cxxnet configuration file contains 4 parts: global setting for general running setting, data iterator for IO setting, updater for learning setting and layers setting for network configuration setting.

• Global Setting

• How to set global parameters for neural network, related to device selection, running control.

• Data Input Setting
  • How to set input data configurations.
• Updater Setting

• How to set parameters(learning rate, momentum) for learning procedure

• Layer Setting
  • How to configure network, and setup each layers.

=

Simple guide to train ImageNet

• Read the simple Guide to start train your own ImageNet Model.
• We will post a pretrained ImageNet Model very soon.

=

Code Layout

• core: core implementation of layers and updaters of neural net
• nnet: implementation of network that connects layers and updaters together
• io: handles data input and preprecessing
• utils: some utils to help simple tasks