Environments

These interpretability tools are functioanl with both the tensorflow ML package and the pytorch ML package. These two packages don’t tend to play nice with each other, so typically they must be kept in seperate enviorments. The user is responsible for activating the correct enviroments for the package they want to run.

Here is a list of non-machinelearning packages used by the scripts. These should be installed regardless of which ML package is being used. This list may not contain all necessary packages; defer to what is imported in the scripts.

• os

• sys

• glob

• argparse

• numpy

• pandas

• matplotlib

• pingouin

• scikit-image (skimage)