Mocha Documentation

Mocha is a Deep Learning framework for Julia.

Tutorials

• Training LeNet on MNIST
• Alex’s CIFAR-10 tutorial in Mocha
• Image Classification with Pre-trained Model
• Pre-training with Stacked De-noising Auto-encoders

User’s Guide

• Networks
  • Overview
  • Network Architecture
  • Layer Implementation
  • Mocha Network Topology Tips
  • Debugging
• Layers
  • Overview
  • Data Layers
  • Computation Layers
  • Loss Layers
  • Statistics Layers
  • Utility Layers
• Neurons (Activation Functions)
• Initializers
• Regularizers
• Norm Constraints
• Data Transformers
• Solvers
  • General Solver Parameters
  • Solver Algorithms
  • Solver Coffee Breaks
• Mocha Backends
  • Pure Julia CPU Backend
  • CPU Backend with Native Extension
  • CUDA Backend
• Tools
  • Importing Trained Model from Caffe
  • Image Classifier

Developer’s Guide

• Blob
  • Constructors and Destructors
  • Accessing Properties of a Blob
  • Accessing Data of a Blob
• Layer
  • Defining a Layer
  • Characterizing a Layer
  • Layer Computation API
  • Layer Parameters
  • Layer Activation Function

Indices and tables

• Index
• Module Index
• Search Page