Skip to content

Latest commit

 

History

History

evaluation

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

Evaluation (Stage-5) -- Sec 3.5

How to evaluate your networks performance at a bin level

Pooled-MAE and std

This folder consists of link to a colab notebook that helps us evaluate the performance at a bin level. The txt files required for running the notebook are in this drive folder

The Demo plot as in Default Approach , SOTA for NWPU Dataset can be found here.

The Demo Plot as in Default Approach , Overall performance of networks in terms of Pooled MAE +/- std can be found here.

The Demo Plot as in Proposed Approach, Dataset-wise Analysis, RR sampling NWPU can be found here.

The Demo Plot as in Proposed Approach, Network-wise Analysis on DM Count network for NWPU dataset can be found here.

If you are interested in using the evaluation procedure for your network, you could make a copy of this colab notebook and use the same.

Thresholded Percentage Error Ratio (TPER)

The jupyter notebook percentage plot-single network_BL.ipynb provides demo for generating the TPER curves. The reuired txt files to run this notebook are also added to this repo inside the BL_txt folder.

Localised Metric - GAME

The game_metric.py contains the file which you can use to calculate the GAME metric.