DeepVisualInsight (DVI) is a time-travelling visualization solution for how the classification boundaries of a learned model is trained in two-dimensional space.
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.txtPlease follow Usage Instructions to use DVI.
For more details, please see our wiki.