This tutorial was designed for easily diving into TensorFlow, through examples. For readability, it includes both notebooks and source codes with explanation.

65 Achegas

6 Branches

0 Lanzamentos

Aymeric Damien 23530cf3f9 Added input_data to notebook folder		%!s(int64=9) %!d(string=hai) anos
examples	80197e6dbc replace tf.types.xxx with tf.xxx	%!s(int64=9) %!d(string=hai) anos
notebooks	23530cf3f9 Added input_data to notebook folder	%!s(int64=9) %!d(string=hai) anos
LICENSE	4fbed84d52 change project layout	%!s(int64=9) %!d(string=hai) anos
README.md	889a287001 Fixed typos in README	%!s(int64=9) %!d(string=hai) anos
Setup_TensorFlow.md	f5e3be5a50 Update Setup_TensorFlow.md	%!s(int64=9) %!d(string=hai) anos
input_data.py	908f7cc24c added mnist data script	%!s(int64=9) %!d(string=hai) anos
multigpu_basics.py	530dc64989 added basic operations with multi GPU	%!s(int64=9) %!d(string=hai) anos

TensorFlow Examples

Code examples for some popular machine learning algorithms, using TensorFlow library. This tutorial is designed to easily dive into TensorFlow, through examples. It includes both notebook and code with explanations.

Tutorial index

1 - Introduction

Hello World (notebook) (code)
Basic Operations (notebook) (code)

2 - Basic Classifiers

Nearest Neighbor (notebook) (code)
Linear Regression (notebook) (code)
Logistic Regression (notebook) (code)

3 - Neural Networks

Multilayer Perceptron (notebook) (code)
Convolutional Neural Network (notebook) (code)
AlexNet (notebook) (code)
Recurrent Neural Network (LSTM) (notebook) (code)
Bidirectional Recurrent Neural Network (LSTM) (notebook) (code)

4 - Multi GPU

Basic Operations on multi-GPU (notebook) (code)

5 - User Interface (Tensorboard)

Graph Visualization (notebook) (code)
Loss Visualization (notebook) (code)

Dependencies

tensorflow
numpy
matplotlib
cuda (to run examples on GPU)

For more details about TensorFlow installation, you can check Setup_TensorFlow.md

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, with 60,000 examples for training and 10,000 examples for testing. (Website: http://yann.lecun.com/exdb/mnist/)

Other tutorials are coming soon....

README.md