search

Hzzone / Precipitation-Nowcasting

pytorch implemention of trajGRU.
547 stars 171 forks source link

Should use test set instead of valid set to report benchmarks #8

Closed bingo619 closed 4 years ago

bingo619 commented 4 years ago

Hi, I just realised that you are actually using the valid set to report the benchmarks, I think we should be using test set.

bingo619 commented 4 years ago

Sorry, my mistake.