Keras is an open source neural network library written in Python. It is capable of running on top of TensorFlow. TensorFlow is an open-source software library for dataflow programming across a range of tasks.

Please follow the official instruction to install TensorFlow HERE:

 https://www.tensorflow.org/install/

For this course, you are welcome to use either Python 2 or Python 3 for the assignments. You don't need GPU for most code examples in this course, though having GPU won't hurt. 

There are a few things to note:

• As of version 1.2, TensorFlow no longer provides GPU support on macOS.
• On macOS, Python 3.6 might gives warning but still works.
• TensorFlow with GPU support will only work with CUDA® Toolkit 8.0 and cuDNN v6.0, not the newest CUDA and cnDNN version. Make sure that you install the correct CUDA and cuDNN versions to avoid frustrating issues.
• On Windows, TensorFlow supports only 64-bit Python 3.5 anx Python 3.6.

1. The high-level Keras API provides building blocks to create and train deep learning models. Please read the tutorial below first:

    https://www.tensorflow.org/guide/keras

2. Train your first neural network for the basic classification problem:

    https://www.tensorflow.org/tutorials/keras/basic_classification

3. Train the second model for the regression: 

    https://www.tensorflow.org/tutorials/keras/basic_regression