/DeepVisualInsight

DeepVisualInsight (DVI) is a time-travelling visualization solution for how the classification boundaries of a learned model is trained in two-dimensional space.

Primary LanguageJupyter Notebook

DeepVisualInsight (DVI): A visualization platform for debugging deep neural network models

DeepVisualInsight (DVI) is a time-travelling visualization solution for how the classification boundaries of a learned model is trained in two-dimensional space.

Requirement

To start playing with DVI, please run:

$ conda create -n DVI_newest python=3.6
$ git clone https://github.com/xianglinyang/DeepVisualInsight.git
$ pip -r install requirements.txt

Installation

Please follow Usage Instructions to use DVI.

For more details, please see our wiki.