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: https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow-i/info
You can find python source code under the python directory, and associated notebooks under notebooks.
| Source code | Description | |
|---|---|---|
| 1 | basics.py | Setup with tensorflow and graph computation. |
| 2 | linear_regression.py | Performing regression with a single factor and bias. |
| 3 | polynomial_regression.py | Performing regression using polynomial factors. |
| 4 | logistic_regression.py | Performing logistic regression using a single layer neural network. |
| 5 | basic_convnet.py | Building a deep convolutional neural network. |
| 6 | modern_convnet.py | Building a deep convolutional neural network with batch normalization and leaky rectifiers. |
| 7 | autoencoder.py | Building a deep autoencoder with tied weights. |
| 8 | denoising_autoencoder.py | Building a deep denoising autoencoder which corrupts the input. |
| 9 | convolutional_autoencoder.py | Building a deep convolutional autoencoder. |
| 10 | residual_network.py | Building a deep residual network. |
| 11 | variational_autoencoder.py | Building an autoencoder with a variational encoding. |
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.
http://pkmital.com
See LICENSE.md