search

VQAssessment / FAST-VQA-and-FasterVQA

[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/1225_ECCV_2022_paper.php
Other
244 stars 24 forks source link

final output score: qlt_score in the line 36 of fastvqa/models/head.py is a small decimal which is < 0 #8

Closed Mmmmmmmag closed 1 year ago

Mmmmmmmag commented 2 years ago

Hi, In line 36 of fastvqa/models/head.py, the qlt_score seems to be the final output score tensor, but it is a small decimal which is < 0, so should I do math.exp(qlt_score) or something else? So that I can get the final score in the range of (0,100)? Thanks a lot and looking forward to your apply!

teowu commented 2 years ago

Yes you may need some rescaling, and a possible rescaling factor can be 

a1, a2, a3, a4 = -0.08283314, 0.037915636, 17.057644220869555, 63.291117743589744
def rescale(x):
    return ((x - a1) / a2) * a3 + a4

where x is the original output score of the model. Best.