Forums

The VoxCeleb Speaker Recognition Challenge 2019 - Audio speaker verification - FIXED training data Forum

Go back to competition Back to thread list Post in this thread

> python evaluate.py --ground_truth=label.txt --prediction=score.txt --positive=0

In the example, --positive=0, while in this challenge, it should be --positive=1? Am I right?

Posted by: shawn_thu @ Aug. 21, 2019, 1:09 p.m.

Hi, we are currently accepting either, just in case there is any misinterpretation. We will take the best between running the code with positive=0 or running with positive=1.

Posted by: vgg @ Aug. 23, 2019, 9:43 a.m.
Post in this thread