Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hshindo/Merlin.jl
Deep Learning for Julia
https://github.com/hshindo/Merlin.jl
deep-learning julia machine-learning neural-networks
Last synced: 3 months ago
JSON representation
Deep Learning for Julia
- Host: GitHub
- URL: https://github.com/hshindo/Merlin.jl
- Owner: hshindo
- License: mit
- Created: 2015-11-25T09:12:06.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2019-11-25T10:44:17.000Z (almost 5 years ago)
- Last Synced: 2024-06-23T04:56:40.982Z (5 months ago)
- Topics: deep-learning, julia, machine-learning, neural-networks
- Language: Julia
- Homepage:
- Size: 32.2 MB
- Stars: 144
- Watchers: 24
- Forks: 10
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-julia - Deep Learning for Julia
- awesome-julia-datasciences - Merlin - Flexible Deep Learning Framework in Julia. (APL / General-Purpose Machine Learning)
README
# Merlin: deep learning framework for Julia
`Merlin` is a deep learning framework written in [Julia](http://julialang.org/).
It aims to provide a fast, flexible and compact deep learning library for machine learning.
`Merlin` is tested against Julia `1.0` on Linux, OS X, and Windows (x64).
It runs on CPU and CUDA GPU.[![Build Status](https://travis-ci.org/hshindo/Merlin.jl.svg?branch=master)](https://travis-ci.org/hshindo/Merlin.jl)
## Documentation
[![](https://img.shields.io/badge/docs-stable-blue.svg)](http://hshindo.github.io/Merlin.jl/stable/)
[![](https://img.shields.io/badge/docs-latest-blue.svg)](http://hshindo.github.io/Merlin.jl/latest/)## Requirements
- Julia 1.0## Installation
The Pkg REPL-mode is entered from the Julia REPL using the key `]`.
```julia
(v1.0) pkg> add Merlin
```## Quick Start
### MNIST
* See [MNIST](examples/mnist/)More examples can be found in [`examples`](examples/).
### GPU Support
The following are required:
* [CUDA](https://developer.nvidia.com/cuda-toolkit) 9+
* [cuDNN](https://developer.nvidia.com/cudnn)