Skip to content

Latest commit

 

History

History
11 lines (7 loc) · 441 Bytes

README.md

File metadata and controls

11 lines (7 loc) · 441 Bytes

Relevance Heatmaps (deep-tayloy decomposition)

Exploring the work found at http://www.heatmapping.org/ in the context of congestion.

To run the network with a mnist data set fed in "manually":

  • clone the repo
  • extract the archive "mnist_csvs.zip"
  • run the python script "mnist_heatmap.py"

Files relating to tfl are located in "tfl_data" for tidyness. For now, you will need to move these up to the root directory or adjust pathing.