DequanWang / tent

ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization
https://arxiv.org/abs/2006.10726
MIT License
344 stars 43 forks source link

Problem of scenario: episodic and step=1 #20

Open xuyingzhongguo opened 11 months ago

xuyingzhongguo commented 11 months ago

Hello! I have a problem understanding the code when it is online (episodic) and step=1. The output of the old model(before adaptation) is used for both backprop and accuracy calculation. So the online scenario doesn't actually output the results after the test adaptation, instead it outputs the results before the test adaptation.

Thank you in advance!