MXNet Documentation

MXNet.jl is the Julia package of dmlc/mxnet. MXNet.jl brings flexible and efficient GPU computing and state-of-art deep learning to Julia. Some highlight of features include:

• Efficient tensor/matrix computation across multiple devices, including multiple CPUs, GPUs and distributed server nodes.
• Flexible symbolic manipulation to composite and construct state-of-the-art deep learning models.

For more details, see documentation below. Please also checkout the examples directory.

Tutorials

• Digit Recognition on MNIST
  • Simple 3-layer MLP
  • Convolutional Neural Networks
  • Predicting with a trained model
• Generating Random Sentence with LSTM RNN
  • LSTM Cells
  • Unfolding LSTM
  • Data Provider for Text Sequences
  • Training the LSTM
  • Sampling Random Sentences
  • Visualizing the LSTM

User's Guide

• Installation Guide
  • Automatic Installation
  • Manual Compilation
• Overview
  • MXNet.jl Namespace
  • Low Level Interface
  • Intermediate Level Interface
  • High Level Interface
• FAQ
  • Running MXNet on AWS GPU instances

API Documentation

• Context
• NDArray API
  • Arithmetic Operations
  • Trigonometric Functions
  • Hyperbolic Functions
  • Activation Functions
  • Reference
• Symbolic API
• Model
• Evaluation Metrics
• Data Providers
  • AbstractDataProvider interface
  • AbstractDataBatch interface
  • Implemented providers and other methods
• Neural Network Factory
• Executor
• Network Visualization