unzip-nets

A greedy approach for finding the optimal architecture (in terms of speed-accuracy tradeoff) for Multi-Task Learning. Although such kind of delicate graph manipulations are easier on PyTorch, we chose to use TensorFlow for its matureness on mobile platforms (TF-Lite).

Repository structure

This repo is divided into 3 main branches:

• master - for the main Unzip-Nets Multi-Task Learning code
• prototyping - for random Jupyter notebooks, small experiments, and prototyping snippets
• gh-pages - for the documentations and literature summaries (with LaTeX)