开源神经网络库 [英] Open Source Neural Network Library

问题描述

我正在寻找一个开源的神经网络库.到目前为止，我已经研究了FANN，WEKA和OpenNN.是我应该看看的其他人吗?当然，标准是文档，示例和易用性.

I am looking for an open source neural network library. So far, I have looked at FANN, WEKA, and OpenNN. Are the others that I should look at? The criteria, of course, is documentation, examples, and ease of use.

推荐答案

最后更新:2020/03/24 (我将不时更新此答案...)

Last update: 2020/03/24 (I will update this answer from time to time...)

• FANN 是C/C ++中非常流行的实现，并且具有许多其他语言的绑定.
• 在scikit-learn(Python)0.18(当前开发版本)中，将实现前馈神经网络( OpenANN (

• FANN is a very popular implementation in C/C++ and has bindings for many other languages.
• In scikit-learn (Python) 0.18 (current developement version) there will be an implementation of feed-forward neural networks (API documentation).
• And I must mention my own project, which is called OpenANN (Documentation). It is written in C++ and has Python bindings.

由于神经网络在当前的研究和行业(深度学习")中非常流行，因此有许多可用的研究库.它们中的大多数都易于设置，集成和使用.尽管不如上面提到的库那么容易.它们提供了领先的功能和高性能(使用GPU等).这些库大多数还具有自动区分功能.您可以轻松地指定新的体系结构，损失函数等，而不必手动指定反向传播.

Because neural networks are quite popular in research and industry at the moment ("deep learning") there are many research libraries available. Most of them are kind of easy to set up, integrate, and use. Although not as easy as the libraries mentioned above. They provide leading edge functionality and high performance (with GPUs etc.). Most of these libraries also have automatic differentiation. You can easily specify new architectures, loss functions etc. and don't have to specify the backpropagation manually.

• TensorFlow 来自Google(C ++/Python)
来自Facebook的
• PyTorch 可以在Python中使用C/C ++扩展
• mxnet (C ++，Python，R，Scala，Julia，Matlab，Javascript)
• Deeplearning4j (Java)
来自Microsoft的
• CNTK (Python培训/C ++/C#/Java/Python中的评估)
• Chainer (Python)
• PaddlePaddle 来自CUDA/C ++中的Python绑定
Sony的
• NNabla 来自Cuda/C ++ 11，带有Python绑定

• TensorFlow from Google (C++/Python)
• PyTorch from Facebook, in Python, can be extended with C/C++
• mxnet (C++, Python, R, Scala, Julia, Matlab, Javascript)
• Deeplearning4j (Java)
• CNTK from Microsoft (training in Python / evaluation in C++/C#/Java/Python)
• Chainer (Python)
• PaddlePaddle from Baidu in CUDA/C++ with Python bindings
• NNabla from Sony in Cuda/C++11 with Python bindings

可以在此处中找到GPU加速库的性能比较(不幸的是有些过时了).可以在此处找到GPU和库版本的比较.

A performance comparison for GPU-accelerated libraries can be found here (a bit outdated unfortunately). A comparison of GPUs and library versions can be found here.

无效:

• Keras :它可以使用 Theano 和 CNTK 作为后端. (现在，tensorflow的一部分作为其高级接口.)
• Caffe 来自C ++的Berkeley视觉和学习中心，具有Python绑定
• Darknet :C语言中的CNN，以YOLO对象检测器的实现而闻名.
来自Intel Nervana的
• Neon 提供了非常有效的实现(Python)
• MatConvNet (Matlab)
• Theano (Python)及其高级API:
  • Pylearn 2
  • Theanets
  • scikit-神经网络
  • 千层面
  • 基于Theano(Python)的块
  • Keras: It could use Tensorflow, Theano, and CNTK as a backend. (Now part of tensorflow as its high-level interface.)
  • Caffe from Berkeley Vision and Learning Center in C++ with Python bindings
  • Darknet: CNNs in C, known for the implementations of the YOLO object detector.
  • Neon from Intel Nervana provides very efficient implementations (Python)
  • MatConvNet (Matlab)
  • Theano (Python) and its high-level APIs:
    • Pylearn 2
    • Theanets
    • scikit-neuralnetwork
    • Lasagne
    • Blocks based on Theano (Python)

    这篇关于开源神经网络库的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！