深度学习教程 TensorFlow and Deep Learning Tutorials
Google's Deep Learning Tutorials
- TensorFlow Official Deep Learning Tutorial [中文].
- MLP with Dropout TensorFlow [中文] TensorLayer [中文]
- Autoencoder TensorLayer [中文]
- Convolutional Neural Network TensorFlow [中文] TensorLayer [中文]
- Recurrent Neural Network TensorFlow [中文] TensorLayer [中文]
- Deep Reinforcement Learning TensorLayer [中文]
- Sequence to Sequence TensorFlow TensorLayer[中文]
- Word Embedding TensorFlow [中文] TensorLayer [中文]
Deep Learning Reading List
- MIT Deep Learning Book
- Karpathy Blog
- Stanford UFLDL Tutorials
- Colah's Blog - Word Embedding [中文]
- Colah's Blog - Understand LSTN [门函数]
Tutorial index
0 - Prerequisite
- Introduction to Machine Learning (notebook)
- Introduction to MNIST Dataset (notebook)
1 - Introduction
- Hello World (notebook) (code)
- Basic Operations (notebook) (code)
2 - Basic Models
- Nearest Neighbor (notebook) (code)
- Linear Regression (notebook) (code)
- Logistic Regression (notebook) (code)
3 - Neural Networks
- Multilayer Perceptron (notebook) (code)
- Convolutional Neural Network (notebook) (code)
- Recurrent Neural Network (LSTM) (notebook) (code)
- Bidirectional Recurrent Neural Network (LSTM) (notebook) (code)
- Dynamic Recurrent Neural Network (LSTM) (code)
- AutoEncoder (notebook) (code)
4 - Utilities
- Save and Restore a model (notebook) (code)
- Tensorboard - Graph and loss visualization (notebook) (code)
- Tensorboard - Advanced visualization (code)
5 - Multi GPU
- Basic Operations on multi-GPU (notebook) (code)
Dataset
Some examples require MNIST dataset for training and testing. Don't worry, this dataset will automatically be downloaded when running examples (with input_data.py). MNIST is a database of handwritten digits, for a quick description of that dataset, you can check this notebook.
Official Website: http://yann.lecun.com/exdb/mnist/
Selected Repositories
- jtoy/awesome-tensorflow
- nlintz/TensorFlow-Tutoirals
- adatao/tensorspark
- ry/tensorflow-resnet
Tricks
- Tricks to use TensorLayer
Examples
Basics
- Multi-layer perceptron (MNIST). A multi-layer perceptron implementation for MNIST classification task, see
tutorial_mnist_simple.py
here.
Computer Vision
- Denoising Autoencoder (MNIST). A multi-layer perceptron implementation for MNIST classification task, see
tutorial_mnist.py
here. - Stacked Denoising Autoencoder and Fine-Tuning (MNIST). A multi-layer perceptron implementation for MNIST classification task, see
tutorial_mnist.py
here. - Convolutional Network (MNIST). A Convolutional neural network implementation for classifying MNIST dataset, see
tutorial_mnist.py
here. - Convolutional Network (CIFAR-10). A Convolutional neural network implementation for classifying CIFAR-10 dataset, see
tutorial_cifar10.py
here. - VGG 16 (ImageNet). A Convolutional neural network implementation for classifying ImageNet dataset, see
tutorial_vgg16.py
here. - VGG 19 (ImageNet). A Convolutional neural network implementation for classifying ImageNet dataset, see
tutorial_vgg19.py
here.
Natural Language Processing
- Recurrent Neural Network (LSTM). Apply multiple LSTM to PTB dataset for language modeling, see
tutorial_ptb_lstm.py
here. - Word Embedding - Word2vec. Train a word embedding matrix, see
tutorial_word2vec_basic.py
here. - Restore Embedding matrix. Restore a pre-train embedding matrix, see
tutorial_generate_text.py
here. - Text Generation. Generates new text scripts, using LSTM network, see
tutorial_generate_text.py
here. - Machine Translation (WMT). Translate English to French. Apply Attention mechanism and Seq2seq to WMT English-to-French translation data, see
tutorial_translate.py
here.
Reinforcement Learning
- Deep Reinforcement Learning - Pong Game. Teach a machine to play Pong games, see
tutorial_atari_pong.py
here.
Useful Links
- Tricks to use TensorLayer
深度学习教程 TensorFlow and Deep Learning Tutorials相关推荐
- 深度学习编译器综述The Deep Learning Compiler
深度学习编译器综述The Deep Learning Compiler The Deep Learning Compiler: A Comprehensive Survey 参考文献: https:/ ...
- MATLAB与深度学习(一)— Deep Learning Toolbox
MATLAB与深度学习(一)- Deep Learning Toolbox 最近,我在学习基于matlab的深度学习的内容,并整理出如下学习笔记.本文借鉴和引用了网上许多前辈的经验和代码,如有冒犯,请 ...
- 深度学习编译与优化Deep Learning Compiler and Optimizer
深度学习编译与优化Deep Learning Compiler and Optimizer
- Python深度学习:基于PyTorch [Deep Learning with Python and PyTorch]
作者:吴茂贵,郁明敏,杨本法,李涛,张粤磊 著 出版社:机械工业出版社 品牌:机工出版 出版时间:2019-11-01 Python深度学习:基于PyTorch [Deep Learning with ...
- 深度学习还没入门?看看深度学习三巨头的Deep Learning综述(4)
深度学习还没入门?看看深度学习三巨头的Deep Learning综述(1) 深度学习还没入门?看看深度学习三巨头的Deep Learning综述(2) 深度学习还没入门?看看深度学习三巨头的Deep ...
- 深度学习还没入门?看看深度学习三巨头的Deep Learning综述(1)
深度学习还没入门?看看深度学习三巨头的Deep Learning综述(1) 深度学习还没入门?看看深度学习三巨头的Deep Learning综述(2) 深度学习还没入门?看看深度学习三巨头的Deep ...
- 动手学深度学习(Dive into Deep Learning,D2L)
动手学深度学习(Dive into Deep Learning,D2L) 本书网址:zh.d2l.ai | 如何安装和使用书中源代码 理解深度学习的最佳方法是学以致用. 本开源项目代表了我们的一种尝试 ...
- 第一门课 神经网络和深度学习(Neural Networks and Deep Learning)
第一门课 神经网络和深度学习(Neural Networks and Deep Learning) 文章目录 第一门课 神经网络和深度学习(Neural Networks and Deep Learn ...
- 干货丨科普丨大牛的《深度学习》笔记,Deep Learning速成教程
深度学习,即Deep Learning,是一种学习算法(Learning algorithm),亦是人工智能领域的一个重要分支.从快速发展到实际应用,短短几年时间里,深度学习颠覆了语音识别.图像分类. ...
最新文章
- Jquery真的不难~第五回 JQ中的遍历(遍历中的性能知识点)
- Nginx Http认证 实现访问网站或目录密码认证保护
- 【EasyUI tree】Python 异步菜单树的实现
- 【无标题】线程池中阻塞队列的作用,为什么是先添加队列而不是先创建最大线程
- 第六十五期:IBM净利润下降38%,旧时代巨头如何自救?
- A20 init.sun7i.rc 文件
- Android 快速实现微信支付(真的!很快!)
- pv原语模拟实现_并发编程信号量的使用方法和其实现原理
- iOS 编译百度地图静态库-合二为一
- java变量类型概念_java变量类型
- 辐射校正:像元DN值—辐照度—表观反射率—地表反射率
- 学习笔记1:迟滞电压比较器
- 常用元器件使用方法12:单节锂电池充电管理芯片XT2055的使用方法
- java.lang.NoSuchMethodError: com.xxx.xxx.xxx.po.xxxPo.setXXX(D)V
- 如何快速查询大量发票?
- 佳明比华为的手表好在哪
- Graph Visualization and Navigation in Information Visualization: A Survey 译文
- python32位和64位有什么区别_python32位和64位的区别是什么
- 案例解读 | 重蹈美国制造业空心化老路,波音数字化出了啥问题?
- 互联网化的年代程序员追女孩
热门文章
- springMVC项目在jboss7中配置应用自己的log4j--转载
- kafka Windows客户端Linux服务器---转
- 基于 Java 2 运行时安全模型的线程协作--转
- Lesson 13.4 Dead ReLU Problem与学习率优化
- 建模准备一定要做的这几件事
- Transformer 模型详解
- 阿里2020 净利润约: 2000亿元 腾讯2020 净利润约: 1000亿元 百度2020 净利润约: 300亿元 美团2020 净利润约: 150亿元 --互联网一响,黄金万两
- jQuery快速入门
- 基于Java语言构建区块链(六)—— 交易(Merkle Tree)
- 数据科学教程:R语言与DataFrame[2016版]