文章參考：ACM官網 編輯：王建

TensorFlow Examples

TensorFlown Tutorial with popular machine learning algorithms implementation. This ntutorial was designed for easily diving into TensorFlow, through nexamples.

Itn is suitable for beginners who want to find clear and concise examples nabout TensorFlow. For readability, the tutorial includes both notebook nand code with explanations.

Note: If you are using older TensorFlow version (before 0.12), please have a look here（aymericdamien/TensorFlow-Examples）

Tutorial index

0 - Prerequisite

• Introduction to Machine Learning

（notebook：aymericdamien/TensorFlow-Examples)

• Introduction to MNIST Dataset

(notebook：aymericdamien/TensorFlow-Examples)

1 - Introduction

• Hello World

(notebook) aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/helloworld.py

• Basic Operations

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/basic_operations.py

2 - Basic Models

• Nearest Neighbor

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/nearest_neighbor.py

• Linear Regression

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/linear_regression.py

• Logistic Regression

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/logistic_regression.py

3 - Neural Networks

• Multilayer Perceptron

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py

• Convolutional Neural Network

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py

• Recurrent Neural Network (LSTM)

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py

• Bidirectional Recurrent Neural Network (LSTM)

(notebook) aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/bidirectional_rnn.py

• Dynamic Recurrent Neural Network (LSTM)

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/dynamic_rnn.py

• AutoEncoder

(notebook) aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py

4 - Utilities

• Save and Restore a model

(notebook) aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/save_restore_model.py

• Tensorboard - Graph and loss visualization

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_basic.py

• Tensorboard - Advanced visualization

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_advanced.py

5 - Multi GPU

• Basic Operations on multi-GPU

(notebook)aymericdamien/TensorFlow-Examples

(code)https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_MultiGPU/multigpu_basics.py

Dataset

Somen examples require MNIST dataset for training and testing. Dont worry, nthis dataset will automatically be downloaded when running examples n(with input_data.py). MNIST is a database of handwritten digits, for a nquick description of that dataset, you can check this notebook.

aymericdamien/TensorFlow-Examples

Official Website: http://yann.lecun.com/exdb/mnist/

More Examples

The following examples are coming from TFLearn(tflearn/tflearn)

a library that provides a simplified interface for TensorFlow. You can have a look, there are many examples(tflearn/tflearn) and pre-built operations and layers(Index - TFLearn).

Tutorials

• TFLearnn Quickstart. Learn the basics of TFLearn through a concrete machine nlearning task. Build and train a deep neural network classifier.

tflearn/tflearn

Basics

• Linear Regression. Implement a linear regression using TFLearn.

https://github.com/tflearn/tflearn/blob/master/examples/basics/linear_regression.py

• Logical Operators. Implement logical operators with TFLearn (also includes a usage of merge).

https://github.com/tflearn/tflearn/blob/master/examples/basics/logical.py

• Weights Persistence. Save and Restore a model.

https://github.com/tflearn/tflearn/blob/master/examples/basics/weights_persistence.py

• Fine-Tuning. Fine-Tune a pre-trained model on a new task.

https://github.com/tflearn/tflearn/blob/master/examples/basics/finetuning.py

• Using HDF5. Use HDF5 to handle large datasets.

https://github.com/tflearn/tflearn/blob/master/examples/basics/use_hdf5.py

• Using DASK. Use DASK to handle large datasets.

https://github.com/tflearn/tflearn/blob/master/examples/basics/use_dask.py

Computer Vision

• Multi-layer perceptron. A multi-layer perceptron implementation for MNIST classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/dnn.py

• Convolutional Network (MNIST). A Convolutional neural network implementation for classifying MNIST dataset.

https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_mnist.py

• Convolutional Network (CIFAR-10). A Convolutional neural network implementation for classifying CIFAR-10 dataset.

https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_cifar10.py

• Network in Network. Network in Network implementation for classifying CIFAR-10 dataset.

https://github.com/tflearn/tflearn/blob/master/examples/images/network_in_network.py

• Alexnet. Apply Alexnet to Oxford Flowers 17 classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py

• VGGNet. Apply VGG Network to Oxford Flowers 17 classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network.py

• VGGNet Finetuning (Fast Training). Use a pre-trained VGG Network and retrain it on your own data, for fast training.

https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network_finetuning.py

• RNN Pixels. Use RNN (over sequence of pixels) to classify images.

https://github.com/tflearn/tflearn/blob/master/examples/images/rnn_pixels.py

• Highway Network. Highway Network implementation for classifying MNIST dataset.

https://github.com/tflearn/tflearn/blob/master/examples/images/highway_dnn.py

• Highway Convolutional Network. Highway Convolutional Network implementation for classifying MNIST dataset.

https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_highway_mnist.py

• Residual Network (MNIST). A bottleneck residual network applied to MNIST classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_mnist.py

• Residual Network (CIFAR-10). A residual network applied to CIFAR-10 classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_cifar10.py

• Google Inception (v3). Googles Inception v3 network applied to Oxford Flowers 17 classification task.

https://github.com/tflearn/tflearn/blob/master/examples/images/googlenet.py

• Auto Encoder. An auto encoder applied to MNIST handwritten digits.

https://github.com/tflearn/tflearn/blob/master/examples/images/autoencoder.py

Natural Language Processing

• Recurrent Neural Network (LSTM). Apply an LSTM to IMDB sentiment dataset classification task.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm.py

• Bi-Directional RNN (LSTM). Apply a bi-directional LSTM to IMDB sentiment dataset classification task.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/bidirectional_lstm.py

• Dynamic RNN (LSTM). Apply a dynamic LSTM to classify variable length text from IMDB dataset.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/dynamic_lstm.py

• City Name Generation. Generates new US-cities name, using LSTM network.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_cityname.py

• Shakespeare Scripts Generation. Generates new Shakespeare scripts, using LSTM network.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_shakespeare.py

• Seq2seq. Pedagogical example of seq2seq reccurent network. See this repo for full instructions.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/seq2seq_example.py

https://github.com/ichuang/tflearn_seq2seq

• CNN Seq. Apply a 1-D convolutional network to classify sequence of words from IMDB sentiment dataset.

https://github.com/tflearn/tflearn/blob/master/examples/nlp/cnn_sentence_classification.py

Reinforcement Learning

• Atari Pacman 1-step Q-Learning. Teach a machine to play Atari games (Pacman by default) using 1-step Q-learning.

https://github.com/tflearn/tflearn/blob/master/examples/reinforcement_learning/atari_1step_qlearning.py

Others

• Recommender - Wide & Deep Network. Pedagogical example of wide & deep networks for recommender systems.

https://github.com/tflearn/tflearn/blob/master/examples/others/recommender_wide_and_deep.py

Notebooks

• Spiral Classification Problem. TFLearn implementation of spiral classification problem from Stanford CS231n.

tflearn/tflearn

Extending TensorFlow

• Layers. Use TFLearn layers along with TensorFlow.

https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py

• Trainer. Use TFLearn trainer class to train any TensorFlow graph.

https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/trainer.py

• Built-in Ops. Use TFLearn built-in operations along with TensorFlow.

https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/builtin_ops.py

• Summaries. Use TFLearn summarizers along with TensorFlow.

https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/summaries.py

• Variables. Use TFLearn variables along with TensorFlow.

https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/variables.py

Dependencies

tensorflow 1.0alphannumpynmatplotlibncudantflearn (if using tflearn examples)n

For more details about TensorFlow installation, you can check TensorFlow Installation Guide

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/g3doc/get_started/os_setup.md

兼職翻譯 招聘

《全球人工智慧》面向全球招聘多名：圖像技術、語音技術、自然語言、機器學習、數據挖掘等專業技術領域的兼職翻譯，工作內容及待遇請在公眾號內回復「兼職+個人微信號」聯繫工作人員。

恐怖|50 億條用戶隱私信息泄露，嫌犯竟是互聯網名企工程師

乾貨|周志華揭開機器學習本質的57張PPT

重磅|百度PaddlePaddle發布最新API 從三大方面優化了性能

重磅|NVIDIA發布兩款"深度神經網路訓練"開發者產品：DIGITS 5 和 TensorRT

重磅|「薩德」——不怕！我國的人工智慧巡航導彈可破解

重磅|MIT發布腦控機器人:用腦電波（10毫秒分類）糾正機器人錯誤

重磅|谷歌預言：2029年通過納米機器人和器官再造 或將實現人類永生

重磅|Messenger bot錯誤率高達70% Facebook被迫削減AI投資

招聘|騰訊大規模招聘AI開發工程師 年薪30-80W

討論|周志華教授gcForest論文的價值與技術討論（微信群）