Wrong implementation in max_sensitivity.py

[Sangyu-Han]

Description

• Insert a clear and concise description of what the bug is.
  In max_sensitivity.py line 386, the denominator use a=x_batch[instance_id]. but It seems that it should be a_batch[instance_id], as the original code https://github.com/chihkuanyeh/saliency_evaluation/blob/master/infid_sen_utils.py, line 308 use normlization of explanation.

Steps to reproduce the behavior

• Insert a description of the steps one needs to take to be able to reproduce the issue.
  • Step 1
  • Step 2
  • Step 3
• Insert a clear and concise description of what you expected to happen.
• If applicable, add screenshots to help explain your problem.
• Add any other context about the problem here. For example, set-up to run example.

Minimum acceptance criteria

• Specify what is necessary for the issue to be closed.
• @mentions of the person that is apt to review these changes e.g., @annahedstroem

[annahedstroem]

Fixed in PR #289.