Counting 3,742 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

UPDATE (July 12, 2016)

New free MOOC course covering all of this material in much more depth, as well as much more including combined variational autoencoders + generative adversarial networks, visualizing gradients, deep dream, style net, and recurrent networks:

TensorFlow Tutorials

You can find python source code under the python directory, and associated notebooks under notebooks.

Source code Description
1 Setup with tensorflow and graph computation.
2 Performing regression with a single factor and bias.
3 Performing regression using polynomial factors.
4 Performing logistic regression using a single layer neural network.
5 Building a deep convolutional neural network.
6 Building a deep convolutional neural network with batch normalization and leaky rectifiers.
7 Building a deep autoencoder with tied weights.
8 Building a deep denoising autoencoder which corrupts the input.
9 Building a deep convolutional autoencoder.
10 Building a deep residual network.
11 Building an autoencoder with a variational encoding.

Installation Guides

For Ubuntu users using python3.4+ w/ CUDA 7.5 and cuDNN 7.0, you can find compiled wheels under the wheels directory. Use pip3 install tensorflow-0.8.0rc0-py3-none-any.whl to install, e.g. and be sure to add: export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64" to your .bashrc. Note, this still requires you to install CUDA 7.5 and cuDNN 7.0 under /usr/local/cuda.



Parag K. Mital, Jan. 2016.



Latest Releases
 Feb. 2 2016