Lead: This article is TensorFlow popular machine learning algorithms to achieve tutorial collection goal is to make the reader easily through a clear and concise understanding of the case TensorFlow. These cases suitable for beginners who want to achieve some TensorFlow cases. The Guide contains further comprising a tag with notes and annotations.
The first step: Tutorial Guide to TF novice
1: tf beginners need to understand Before Getting Started
-
Machine learning introductory notes:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/ml_introduction.ipynb
-
MNIST dataset entry notes
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/mnist_dataset_intro.ipynb
2: TF beginners need to know Start Basics
-
Hello World
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/helloworld.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/helloworld.py
-
Basic Operations
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/basic_operations.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/1_Introduction/basic_operations.py
3: tf beginners need to master the basic model
-
Nearest neighbor:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/nearest_neighbor.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/nearest_neighbor.py
-
Linear Regression:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/linear_regression.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/linear_regression.py
-
Logistic regression:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/2_BasicModels/logistic_regression.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/2_BasicModels/logistic_regression.py
4: tf beginners need to try neural network
-
Multilayer Perceptron:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/multilayer_perceptron.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/multilayer_perceptron.py
-
Convolution neural network:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/convolutional_network.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/convolutional_network.py
-
Recurrent Neural Network (LSTM):
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/recurrent_network.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
-
Bidirectional Recurrent Neural Network (LSTM):
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/bidirectional_rnn.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/bidirectional_rnn.py
-
Dynamic Recurrent Neural Networks (LSTM)
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/dynamic_rnn.py
-
From the encoder
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/autoencoder.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/autoencoder.py
5: A Practical Approach tf beginners need to be proficient in
-
Saving and restoring the model
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/save_restore_model.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/save_restore_model.py
-
FIG visual loss and
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/tensorboard_basic.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_basic.py
-
Tensorboard-- Advanced Visualization
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/4_Utils/tensorboard_advanced.py
5: t multi-GPU basic operation f beginners need to understand the
-
Basic operations on multi-GPU
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/5_MultiGPU/multigpu_basics.ipynb
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_MultiGPU/multigpu_basics.py
6: Case needed data sets
Some cases need MNIST training and testing data sets. When you run these cases, the data sets are automatically downloaded (using input_data.py).
MNIST datasets notes : https: //github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/0_Prerequisite/mnist_dataset_intro.ipynb
Official Website: http: //yann.lecun.com/exdb/mnist/
Step Two: To TF novice quasi each type of case preparation, models and data sets
Getting to Know: TFLearn TensorFlow
The following example from TFLearn, which provides a simplified interface library TensorFlow. There are many examples and operational layers and pre-built.
Tutorial : TFLearn quick start. Learn TFLearn basis by a specific machine learning tasks. Develop and train a neural network classifier depth.
TFLearn address: https: //github.com/tflearn/tflearn
Example: https: //github.com/tflearn/tflearn/tree/master/examples
Construction and operation of the pre-layer: http: //tflearn.org/doc_index/#api
Note: https: //github.com/tflearn/tflearn/blob/master/tutorials/intro/quickstart.md
The base model and data set
-
Linear regression, linear regression achieved using TFLearn
https://github.com/tflearn/tflearn/blob/master/examples/basics/linear_regression.py
-
Logical Operators. TFLearn implemented using logical operators
https://github.com/tflearn/tflearn/blob/master/examples/basics/logical.py
-
Weight holding. Save and restore a model
https://github.com/tflearn/tflearn/blob/master/examples/basics/weights_persistence.py
-
Fine-tuning. On a new task to fine-tune a pre-trained model
https://github.com/tflearn/tflearn/blob/master/examples/basics/finetuning.py
-
Use HDF5. Processing large data sets using HDF5
https://github.com/tflearn/tflearn/blob/master/examples/basics/use_hdf5.py
-
Use DASK. Processing large data sets using DASK
https://github.com/tflearn/tflearn/blob/master/examples/basics/use_dask.py
Computer Vision model and data set
-
Multilayer Perceptron. Multilayer for MNIST classification task of perception to achieve
https://github.com/tflearn/tflearn/blob/master/examples/images/dnn.py
-
Convolution Network (MNIST). One kind of convolutional neural network for classifying data sets achieved MNIST
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_mnist.py
-
Convolutional network (CIFAR-10). One kind of convolutional neural network for classification CIFAR-10 data sets to achieve
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_cifar10.py
-
Network of networks. Network for classifying data sets CIFAR-10 implemented in Network
https://github.com/tflearn/tflearn/blob/master/examples/images/network_in_network.py
-
Alexnet. The Alexnet applied Oxford Flowers 17 classification tasks
https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py
-
VGGNet. The VGGNet applied Oxford Flowers 17 classification tasks
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network.py
-
VGGNet Finetuning (Fast Training). Use a pre-trained VGG network and constrained to your own data, in order to achieve rapid training
https://github.com/tflearn/tflearn/blob/master/examples/images/vgg_network_finetuning.py
-
RNN Pixels. Use RNN (pixels in sequence) classification image
https://github.com/tflearn/tflearn/blob/master/examples/images/rnn_pixels.py
-
Highway Network. Highway Network used to classify data sets to achieve MNIST
https://github.com/tflearn/tflearn/blob/master/examples/images/highway_dnn.py
-
Highway Convolutional Network. Highway Convolutional Network for classifying data sets to achieve MNIST
https://github.com/tflearn/tflearn/blob/master/examples/images/convnet_highway_mnist.py
-
Residual Network (MNIST). Applied to the classification task MNIST a residual network bottlenecks (bottleneck residual network)
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_mnist.py
-
Residual Network (CIFAR-10). CIFAR-10 used in the classification task of a residual network
https://github.com/tflearn/tflearn/blob/master/examples/images/residual_network_cifar10.py
-
Google Inception (v3). Oxford Flowers 17 applies to the classification task Google Inception v3 network
https://github.com/tflearn/tflearn/blob/master/examples/images/googlenet.py
-
From the encoder. MNIST for handwritten digits from the encoder
https://github.com/tflearn/tflearn/blob/master/examples/images/autoencoder.py
Natural language processing models and data sets
-
Recurrent Neural Network (LSTM), LSTM applied to any classification IMDB emotion data set
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm.py
-
Two-way RNN (LSTM), will be a two-way LSTM applied to IMDB sentiment data set classification task:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/bidirectional_lstm.py
-
Dynamic RNN (LSTM), LSTM dynamic variable length text data set from IMDB Category:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/dynamic_lstm.py
-
City name generation, a new generation of American cities use the name LSTM network:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_cityname.py
-
Shakespeare manuscript generation, a new generation of Shakespeare manuscript use LSTM network:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/lstm_generator_shakespeare.py
-
Seq2seq, teaching example seq2seq cycle network:
https://github.com/tflearn/tflearn/blob/master/examples/nlp/seq2seq_example.py
-
CNN Seq, use a 1-D convolution data from a centralized network IMDB emotional classification sequence of words
https://github.com/tflearn/tflearn/blob/master/examples/nlp/cnn_sentence_classification.py
Reinforcement Learning Stories
-
Atari Pacman 1-step Q-Learning, use the 1-step Q-learning to teach a machine to play Atari games:
https://github.com/tflearn/tflearn/blob/master/examples/reinforcement_learning/atari_1step_qlearning.py
Step Three: Other aspects of preparation for the novice TF
-
Recommender-Wide & Deep Network, teaching examples recommendation system wide & deep network:
https://github.com/tflearn/tflearn/blob/master/examples/others/recommender_wide_and_deep.py
-
Spiral Classification Problem, TFLearn Stanford CS231n spiral classification problem of realization:
https://github.com/tflearn/tflearn/blob/master/examples/notebooks/spiral.ipynb
-
Layer, a layer with TensorFlow TFLearn:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
-
Trainer, training class training using TFLearn any TensorFlow map:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/layers.py
-
Bulit-in Ops, together with TensorFlow operation using TFLearn built-in:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/builtin_ops.py
-
Summaries, together with TensorFlow use TFLearn summarizers:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/summaries.py
-
Variables, along with TensorFlow use TFLearn Variables:
https://github.com/tflearn/tflearn/blob/master/examples/extending_tensorflow/variables.py
Open source software library TensorFlow most complete tutorial and a list of items
TensorFlow is an open source software library for data flow graph using numerical calculation. In other words, that is the best way to build depth learning model. This article compiled some excellent and a list of items related to TensorFlow tutorial.
First, the tutorial
TensorFlow the Tutorial 1 - from basic to more interesting TensorFlow application
TensorFlow the Tutorial 2 - based Google TensorFlow frame depth learning profile, these tutorials are Newmu of Theano direct port
TensorFlow Examples - to TensorFlow tutorials and beginners sample code
Sungjoon's TensorFlow -101 - write using Jupyter Notebook tutorial by Python TensorFlow
Terry's TensorFlow the Um Exercises - re-creating the code examples from other TensorFlow
Installing TensorFlow oN raspberry Pi 3 - TensorFlow come in raspberry compiles and runs correctly
Classification oN Time Series - used in TensorFlow LSTM phone sensor data recurrent neural network classification
Second, the model / item
Show, Attend and Tell - based on the focus mechanism image caption generator (focus mechanism "Attention Mechanism" is one of the current hot spots deep learning cutting-edge, can individually focus on different parts of the input and given a series of comprehension)
Neural Style - Neural Style realization (Neural Style is let the machine to imitate the style of painting has been painting a picture of the re-drawing algorithm)
Pretty Tensor - Pretty Tensor builder provides an advanced API
Neural style - Neural style achieve
TensorFlow White Paper Notes - notes and annotated the White Paper TensorFlow summary, and SVG graphics and document links
NeuralArt - to achieve the artistic style of the nervous algorithms
use TensorFlow and PyGame to strengthen the depth of learning table tennis
Generative a using TensorFlow handwriting Demo - try to implement Alex Graves handwritten papers randomly generated portion
neural Turing Machine in TensorFlow - nerve TensorFlow Turing machine to achieve
GoogleNet Convolutional Neural Network Groups Movie Scenes By Setting- Depending on the object, which displays the location and other content to search, filter and video description
Neural Machine - Search.com the BETWEEN MODERN at The writings of Shakespeare and a using TensorFlow English - translation monolingual, from Shakespeare to modern English, and vice versa
Chatbot - "a nerve conversation model "implementation
Colornet - neural the network to the colorize grayscale images - by the neural network to a grayscale image colored
with the Attention neural the Caption Generator - image understanding Tensorflow achieve
Weakly_detector -" deep learning feature to distinguish localized "to achieve TensorFlow
Dynamic Capacity networks - "dynamic capacity network" to achieve
the HMM in TensorFlow - the HMM Viterbi and forward / backward algorithm of
DeepOSM - TensorFlow neural network using OpenStreetMap features and satellite imagery training
DQN-tensorflow - use TensorFlow achieved DeepMind by OpenAI Gym of " by the depth of reinforcement learning levels of human control "
Highway Network - "depth network training," the TensorFlow achieve
Sentence Classification with CNN - TensorFlow achieve "sentence convolution neural network classification"
End the To-End-Memory Networks - end to end Memories
Character-Aware Neural Language Models - the perception of characters nerve TensorFlow language model to achieve
YOLO TensorFlow ++ - TensorFlow realization of "YOLO: real-time object detection" functional training and support on mobile devices running real-time
WaveNet - WaveNet generate neural network architecture TensorFlow achieved for generating audio
Mnemonic Descent method, - descent method mnemonic: reproduction process is applied to the aligned end to end
