[work] Mxnet入门教程以及Gluon/Module教程

阳光穿透心脏的1/2处 2022-05-07 08:04 190阅读 0赞

`MXNet`的深度学习引擎有两个主要的高级接口：`Gluon API`和`Module API`。下面提供了每个教程。

两者之间的区别是命令式编程和符号式编程风格。`Gluon`可以很容易地原型、构建和训练深度学习模型，而不牺牲训练速度，通过启用（1）直觉命令的`Python`代码开发和（2）通过使用杂交特征自动生成符号执行图来更快地执行。

**TL;DR:**如果您不熟悉深度学习或`MXNet`，您应该从`Gluon`教程开始。

`Gluon`和`Module`教程使用`Python`，但您也可以在下面的其他语言`API`教程部分找到各种其他[MXNet教程][MXNet]，例如`R`，`Scala`和`C++` 。

[示例脚本][Link 1]和应用程序以及[贡献][Link 2]信息如下。

## Python API教程 ##

### 1、Gluon ###

(1)、Introductuon

(1)、Basics

*  [Manipulate data the MXNet way with ndarray][]
 *  [Automatic differentiation with autograd][]
 *  [Linear regression with gluon][]
 *  [Serialization - saving, loading and checkpointing][Serialization - saving_ loading and checkpointing]

(2)、Neural Networks

*  [Multilayer perceptrons in gluon][]
 *  [Multi-class object detection using CNNs in gluon][]
 *  [Advanced RNNs with gluon][]

(3)、Advanced

*  [Plumbing: A look under the hood of gluon][Plumbing_ A look under the hood of gluon]
 *  [Designing a custom layer with gluon][]
 *  [Fast, portable neural networks with Gluon HybridBlocks][Fast_ portable neural networks with Gluon HybridBlocks]
 *  [Training on multiple GPUs with gluon][]

(2)、Applications

*  [Creating custom operators with numpy][]
 *  [Handwritten digit recognition (MNIST)][Handwritten digit recognition _MNIST]
 *  [Hybrid network example][]
 *  [Neural network building blocks with gluon][]
 *  [Simple autograd example][]

### 2、Module ###

(1)、Introductuon

(1)、Basics

*  [Imperative tensor operations on CPU/GPU][Imperative tensor operations on CPU_GPU]
 *  [NDArray Indexing][]
 *  [Symbol API][]
 *  [Module API][]
 *  [Iterators - Loading data][]

(2)、Neural Networks

*  [Linear regression][]
 *  [MNIST - handwriting recognition][]
 *  [Large scale image classification][]

(3)、Advanced

*  [NDArray in Compressed Sparse Row Storage Format][]
 *  [Sparse Gradient Updates][]
 *  [Train a Linear Regression Model with Sparse Symbols][]

(2)、Applications

*  [Connectionist Temporal Classification][]
 *  [Distributed key-value store][]
 *  [Fine-tuning a pre-trained ImageNet model with a new dataset][]
 *  [Generative Adversarial Networks][]
 *  [Matrix factorization in recommender systems][]
 *  [Text classification (NLP) on Movie Reviews][Text classification _NLP_ on Movie Reviews]

2、Module

用ndarray操作MXNet的数据方式 使用autograd自动分化 用胶子线性回归 序列化 - 保存，加载和检查点 其他语言API教程

### 其他语言教程 ###

*  [MNIST with the MXNet C++ API][MNIST with the MXNet C_ API]
    
    Scala
 *  [Setup your MXNet with Scala on InelliJ][]
 *  [MNIST with the Scala API][]
 *  [Use Scala to build a Long Short-Term Memory network that generates Barack Obama’s speech patterns][Use Scala to build a Long Short-Term Memory network that generates Barack Obama_s speech patterns]

*  [NDArray: Vectorized Tensor Computations on CPUs and GPUs with R][NDArray_ Vectorized Tensor Computations on CPUs and GPUs with R]
 *  [Symbol API with R][]
 *  [Custom Iterator][]
 *  [Callback Function][]
 *  [Five minute neural network][]
 *  [MNIST with R][]
 *  [Classify images via R with a pre-trained model][]
 *  [Char RNN Example with R][]
 *  [Custom loss functions in R][]

原创文章，转载请注明 ：[Mxnet入门教程以及Gluon/Module教程 - MXNet中文网][Mxnet_Gluon_Module_ - MXNet]  
原文出处： https://mxnets.com/news/12.html  
问题交流群 ：168117787

[MXNet]: https://mxnet.incubator.apache.org/tutorials/index.html#other-mxnet-api-tutorials
[Link 1]: https://mxnet.incubator.apache.org/tutorials/index.html#example-scripts-and-applications
[Link 2]: https://mxnet.incubator.apache.org/tutorials/index.html#contributing-tutorials
[Manipulate data the MXNet way with ndarray]: http://gluon.mxnet.io/chapter01_crashcourse/ndarray.html
[Automatic differentiation with autograd]: http://gluon.mxnet.io/chapter01_crashcourse/autograd.html
[Linear regression with gluon]: http://gluon.mxnet.io/chapter02_supervised-learning/linear-regression-gluon.html
[Serialization - saving_ loading and checkpointing]: http://gluon.mxnet.io/chapter03_deep-neural-networks/serialization.html
[Multilayer perceptrons in gluon]: http://gluon.mxnet.io/chapter03_deep-neural-networks/mlp-gluon.html
[Multi-class object detection using CNNs in gluon]: http://gluon.mxnet.io/chapter04_convolutional-neural-networks/cnn-gluon.html
[Advanced RNNs with gluon]: http://gluon.mxnet.io/chapter05_recurrent-neural-networks/rnns-gluon.html
[Plumbing_ A look under the hood of gluon]: http://gluon.mxnet.io/chapter03_deep-neural-networks/plumbing.html
[Designing a custom layer with gluon]: http://gluon.mxnet.io/chapter03_deep-neural-networks/custom-layer.html
[Fast_ portable neural networks with Gluon HybridBlocks]: http://gluon.mxnet.io/chapter07_distributed-learning/hybridize.html
[Training on multiple GPUs with gluon]: http://gluon.mxnet.io/chapter07_distributed-learning/multiple-gpus-gluon.html
[Creating custom operators with numpy]: http://mxnet.incubator.apache.org/tutorials/gluon/customop.html
[Handwritten digit recognition _MNIST]: http://mxnet.incubator.apache.org/tutorials/gluon/mnist.html
[Hybrid network example]: http://mxnet.incubator.apache.org/tutorials/gluon/hybrid.html
[Neural network building blocks with gluon]: http://mxnet.incubator.apache.org/tutorials/gluon/gluon.html
[Simple autograd example]: http://mxnet.incubator.apache.org/tutorials/gluon/autograd.html
[Imperative tensor operations on CPU_GPU]: http://mxnet.incubator.apache.org/tutorials/basic/ndarray.html
[NDArray Indexing]: https://mxnet.incubator.apache.org/tutorials/basic/ndarray_indexing.html
[Symbol API]: http://mxnet.incubator.apache.org/tutorials/basic/symbol.html
[Module API]: http://mxnet.incubator.apache.org/tutorials/basic/module.html
[Iterators - Loading data]: http://mxnet.incubator.apache.org/tutorials/basic/data.html
[Linear regression]: http://mxnet.incubator.apache.org/tutorials/python/linear-regression.html
[MNIST - handwriting recognition]: http://mxnet.incubator.apache.org/tutorials/python/mnist.html
[Large scale image classification]: http://mxnet.incubator.apache.org/tutorials/vision/large_scale_classification.html
[NDArray in Compressed Sparse Row Storage Format]: http://mxnet.incubator.apache.org/tutorials/sparse/csr.html
[Sparse Gradient Updates]: http://mxnet.incubator.apache.org/tutorials/sparse/row_sparse.html
[Train a Linear Regression Model with Sparse Symbols]: http://mxnet.incubator.apache.org/tutorials/sparse/train.html
[Connectionist Temporal Classification]: https://mxnet.incubator.apache.org/tutorials/speech_recognition/ctc.html
[Distributed key-value store]: http://mxnet.incubator.apache.org/tutorials/python/kvstore.html
[Fine-tuning a pre-trained ImageNet model with a new dataset]: http://mxnet.incubator.apache.org/faq/finetune.html
[Generative Adversarial Networks]: http://mxnet.incubator.apache.org/tutorials/unsupervised_learning/gan.html
[Matrix factorization in recommender systems]: http://mxnet.incubator.apache.org/tutorials/python/matrix_factorization.html
[Text classification _NLP_ on Movie Reviews]: http://mxnet.incubator.apache.org/tutorials/nlp/cnn.html
[MNIST with the MXNet C_ API]: http://mxnet.incubator.apache.org/tutorials/c%2B%2B/basics.html
[Setup your MXNet with Scala on InelliJ]: http://mxnet.incubator.apache.org/tutorials/scala/mxnet_scala_on_intellij.html
[MNIST with the Scala API]: http://mxnet.incubator.apache.org/tutorials/scala/mnist.html
[Use Scala to build a Long Short-Term Memory network that generates Barack Obama_s speech patterns]: http://mxnet.incubator.apache.org/tutorials/scala/char_lstm.html
[NDArray_ Vectorized Tensor Computations on CPUs and GPUs with R]: http://mxnet.incubator.apache.org/tutorials/r/ndarray.html
[Symbol API with R]: http://mxnet.incubator.apache.org/tutorials/r/symbol.html
[Custom Iterator]: http://mxnet.incubator.apache.org/tutorials/r/CustomIterator.html
[Callback Function]: http://mxnet.incubator.apache.org/tutorials/r/CallbackFunction.html
[Five minute neural network]: http://mxnet.incubator.apache.org/tutorials/r/fiveMinutesNeuralNetwork.html
[MNIST with R]: http://mxnet.incubator.apache.org/tutorials/r/mnistCompetition.html
[Classify images via R with a pre-trained model]: http://mxnet.incubator.apache.org/tutorials/r/classifyRealImageWithPretrainedModel.html
[Char RNN Example with R]: http://mxnet.incubator.apache.org/tutorials/r/charRnnModel.html
[Custom loss functions in R]: http://mxnet.incubator.apache.org/tutorials/r/CustomLossFunction.html
[Mxnet_Gluon_Module_ - MXNet]: https://mxnets.com/news/12.html