PIRM 2018 Spectral Image Super-Resolution Challenge- Track 1 Forum

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

> A potential bug in calculating MRAE

Currently, the MRAE measurement handles the zero values in ground truth images by adding the "np.finfo(float).eps".

However, this value is too small (i.e., about 10e-16) to handle huge loss/error when a certain predicted pixel is not exactly the ground truth zero, using the relative loss (e.g., MRAE).

Posted by: ChangC @ July 24, 2018, 7:54 a.m.

This bug may result in the failure of training with MRAE loss and significantly affect the evaluation of testing using MRAE metric.

It should be better to replace the "np.finfo(float).eps" (~2.2e-16) to a larger value such as 1/65536.

Posted by: ChangC @ July 24, 2018, 8:04 a.m.

Hi,
Thank you for noticing this. You are correct. I did change this value for track2 but apparently, I missed it for track1. This applies to all the participants so it shouldn't affect the ranking. However, I will rectify this as you suggested.

Thanks,
Mehrdad

Posted by: mehrdad.shoeiby @ July 24, 2018, 8:33 a.m.

Hi,
Thank you for noticing this. You are correct. I did change this value for track2 but apparently, I missed it for track1. This applies to all the participants so it shouldn't affect the ranking. However, I will rectify this as you suggested.

Thanks,
Mehrdad

Posted by: mehrdad.shoeiby @ July 24, 2018, 8:33 a.m.

Got it. Thanks for you reply.

Posted by: ChangC @ July 25, 2018, 11:43 a.m.
Post in this thread