https://github.com/jsmith/gnn

Golang neural network framework
https://github.com/jsmith/gnn

Last synced: 28 days ago
JSON representation

Golang neural network framework

• Host: GitHub
• URL: https://github.com/jsmith/gnn
• Owner: jsmith
• License: mit
• Created: 2017-12-13T02:00:46.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2018-09-25T20:55:12.000Z (over 7 years ago)
• Last Synced: 2026-05-12T18:38:49.982Z (about 1 month ago)
• Language: Go
• Size: 58.6 KB
• Stars: 2
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
[![Build Status](https://travis-ci.org/jsmith/gnn.png?branch=master)](https://travis-ci.org/jsmith/gnn)

# GNN

Golang Neural Network (GNN) framework! GNN was built for educational purposes to learn about neural networks & goland! Currently this framework is able to implement simple fully connected networks.

# Example

```go

net := Net{

  NewFC(2, 4),

  &ReLU{},

  InitFC(4, 1),

  &Sigmoid{},

}

trainer = Trainer{

  Net:          net,

  Cost:         SE{}, // Standard Error Loss

  LearningRate: 0.1,

  Epochs:       10000,

  BatchSize:    4,

}

xor = data.Init(

  mat.InitRows(

    vec.Init(0, 0, 1, 1),

    vec.Init(0, 1, 1, 0),

  ),

  mat.InitRows(

    vec.Init(0, 1, 1, 0),

  ),

)

trainer.Train(xor)

predictions := trainer.Predict(xor.Data())

```

See `trainer_test.go:TestTrainer` for a worker example.

*[anynet](https://github.com/unixpickle/anynet) used as reference*