This preliminary session will cover the basics of working with image data in Python, and creating an image dataset. Please make sure you are running at least Python 3.4 and have Tensorflow 0.9.0 or higher installed. If you are unsure of how to do this, please make sure you have followed the installation instructions. We'll also cover loading images from a directory, resizing and cropping images, and changing an image datatype from unsigned int to float32. If you feel comfortable with all of this, please feel free to skip straight to Session 1. Otherwise, launch jupyter notebook and make sure you are reading the session-0.ipynb file.
Google Colaboratory is an in browser Jupyter Notebook environment which runs all code on their hosted GPU machines. Here is the notebook served on Google Drive which can be opened w/ Google's Colaboratory:
https://drive.google.com/file/d/0B1QbouMVDVFqek9IcXdJdWIxTW8/view?usp=sharing