Deep Dream Challenge code by @SIrajology on Youtube
##Overview
This is the code for the Deep Dream challenge for 'Learn Python for Data Science #5' by @Sirajology on YouTube. The code uses the Tensorflow Machine Learning library to generate a trippy image from a given input image.
##Dependencies
- numpy (http://www.numpy.org/)
- functools
- PIL (http://stackoverflow.com/questions/20060096/installing-pil-with-pip)
- tensorflow (https://www.tensorflow.org/versions/r0.10/get_started/os_setup.html#pip-installation)
- matplotlib (http://matplotlib.org/1.5.1/users/installing.html)
- urllib (https://pypi.python.org/pypi/urllib3)
- os
- zipfile
Install missing dependencies using pip
##Demo Usage
Once you have your dependencies installed via pip, run the demo script in terminal via
python deep_dream.py
##Challenge
The instructions are
- Add a function to the existing deep dream python file that converts not just an image, but a video clip to deep dream.
HINT Think of a video as a collection of images (frames).
If you want to use your own template, that's fine too. Submit your code in the comments section and I'll announce the winner in the next video. Good luck!
##Credits
Thanks Google and Liu I've reformatted this code to make it easier to grok.