wangyu / rethink-audio-fsl

Who calls the shots? Rethinking Few-Shot Learning for Audio (WASPAA 2021)
MIT License
40 stars 6 forks source link

Update pred.py #14

Closed chester-w-xie closed 2 years ago

chester-w-xie commented 2 years ago

base_feats for scores_base

wangyu commented 2 years ago

score_base here means we predict all test tracks (feats_all) on base classes only, by not providing features_train and labels_train to the get_score function.