GIZ NLP Agricultural Keyword Spotter
Helping Uganda
$7 000 USD
Completed (over 5 years ago)
Classification
Automatic Speech Recognition
Natural Language Processing
739 joined
253 active
Start
Sep 11, 20
Close
Nov 29, 20
Reveal
Nov 29, 20
Evaluation metric
Help · 30 Oct 2020, 12:59 · edited ~6 hours later · 3
Hi,
I am wondering how zindi is evaluating the model. Given the example of zindi :
fn Pump Spinach abalimi
audio_files/009WL0S.wav 0.73 0.19 0.01
audio_files/00AH117.wav 0.03 0.45 0.99
Let's say the true label is Pump and abalimi for the 1st and 2nd item.
Are we computing the logloss for each class and then average all of them ? So we end up with 193 logloss then average them ?
I could be wrong but I think that if the evaluation was class wise, it needs to be declared in the evaluation part which is not the case.
yes but as there are no example I am not sure how they compute it. Can @zindi explain how they evaluate an item ?
Try read this thread - https://zindi.africa/competitions/iclr-workshop-challenge-1-cgiar-computer-vision-for-crop-disease/discussions/743