Leviosa

We were lagging some commits behind master. Fixing that too.

Reparo

What's new

• Major bug fixes
• Check for frozen graph added
• Cleaner output folder structure
• Deep dream now supports single channel inputs
• More generic setup.py
• Examples updated

Thanks to our contributors:

@csggnn , @b8horpet, @SebastienDebia , @javiribera @BhagyeshVikani @falaktheoptimist

Alohomora

Supported Convolutional Neural Network visualization techniques :

1. Based on the paper Visualizing and Understanding Convolutional Networks by Matthew D. Zeiler and Rob Fergus. The goal here is to reconstruct the input image from the information contained in any given layers of the convolutional neural network.
2. CNN visualization based on Deep dream. Here's the relevant blog post explaining the technique. In essence, it attempts to construct an input image that maximizes the activation for a given output.