google / google/uvq

Results - Label distortion CSV file

Open
#3 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
155
Forks
35
PR merge metrics
No merged PRs in 30d

Description

Is there any way to change the output of the labe_distortion.csv file from the features folder. The Column name containing distortion type, with the values corresponding to 1s per row. As of now, my understanding is the columns are divided into 4 subregions/patches, with values containing B-Z (total 25 columns) showing 25 different distortion types. The first column is ignored as it is stated as 'Undefined'.

My requirement is focused only on the distortion and I want to see which distortion type has the most impact and try to correlate with the visual experience.
If I want to check and focus only on the distortion out put and want to take the average of each distortion type.
How should I proceed on it ?
Thank you.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.