最佳神经网络Julia库


Answers:


7

Mocha.jl -Mocha是Julia的深度学习框架,灵感来自C ++框架Caffe。

具有良好文档和示例的项目。可以在CPU和GPU后端上运行。


1
我认为他们停止开发Mocha,而MXNet是前进的道路。此处请参阅malmaud的评论:github.com/pluskid/Mocha.jl/issues/157
niczky12 '16

我使用Mocha已有一段时间了,它存在一些问题并且缺乏社区,我同意MXNet是主动开发的地方。Tensorflow还有一个Julia包装器:github.com/malmaud/TensorFlow.jl (声明:我没有使用MXNet或TF Julia Wrapper)
davidparks16年



2

只是添加一个更新的(2019)答案:Flux

Flux is an elegant approach to machine learning. It's a 100% pure-Julia stack,
and provides lightweight abstractions on top of Julia's native GPU and
AD support. Flux makes the easy things easy while remaining fully hackable.

例如:

model = Chain(
  Dense(768, 128, σ),
  LSTM(128, 256),
  LSTM(256, 128),
  Dense(128, 10),
  softmax)

loss(x, y) = crossentropy(model(x), y)

Flux.train!(loss, data, ADAM(...))

By using our site, you acknowledge that you have read and understand our Cookie Policy and Privacy Policy.
Licensed under cc by-sa 3.0 with attribution required.