nasaharvest/cropharvest

Brazil evaluation data

fmenat opened this issue · 1 comments

fmenat commented

Hello! I wanted to know whether I'm doing something wrong or not when accessing the Brazil evaluation data. In the CropHarvest paper Table 2 it said that Brazil benchmark has 682,559 samples (174,026 positives and 508,533 negatives). However, when I accessed the data I only got 537,454 (the 174,026 positives but only 363,428 negatives).

The code I used is the following:
image

I'll appreciate any comments on this, thanks!

gabrieltseng commented

Hi @fmenat - apologies for the delay in replying.

I'll take a closer look, but this could be a mistake in the paper. Apologies if this is the case.

  • 👍1