search

yinboc / few-shot-meta-baseline

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021
MIT License
615 stars 107 forks source link

loss/acc averaging #6

Closed fmu2 closed 4 years ago

fmu2 commented 4 years ago

In train_meta.py, when the average train/val loss and accuracy get updated, it seems like the argument n in add() should be set to the number of episodes per mini-batch.

yinboc commented 4 years ago

I think it should be equivalent since #episodes per mini-batch is a fixed number. (Please let me know if I am wrong.)

fmu2 commented 4 years ago

That's right :) Thanks!