This package contains python modules to reproduce deep learning scientific papers.
The general idea is to separate the dataset loading and pre-processing from the deep learning model implementation.
The dataset implementation should be independent from the deep learning framework and the model implementation should be independent from the dataset.
Initially this package will focus on image datasets and tensorflow models.
This work is part of Thomio Watanabe PhD project funded by grant: #2015/26293-0, São Paulo Research Foundation (FAPESP).
"Opinions, hypothesis and conclusions or recommendations expressed herein are the author(s) responsibility and do not necessarily conform with FAPESP vision."
Copyright © 2016 Thomio Watanabe