search

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

Question about Tent Offline Results #16

Open taeyeopl opened 1 year ago

taeyeopl commented 1 year ago

I have a simple question related to the offline tent experiment. What should I change if I want to get results of the offline tent (ex, Table 2)?
Should I change _C.MODEL.EPISODIC = True https://github.com/DequanWang/tent/blob/e9e926a668d85244c66a6d5c006efbd2b82e83e8/conf.py#L37-L39

Termination For online adaptation, no termination is necessary, and iteration continues as long as there is test data. For offline adaptation, the model is first updated and then inference is repeated. Adaptation may of course continue by updating for multiple epochs.

TIEHua commented 1 year ago

I have a simple question related to the offline tent experiment. What should I change if I want to get results of the offline tent (ex, Table 2)? Should I change _C.MODEL.EPISODIC = True

https://github.com/DequanWang/tent/blob/e9e926a668d85244c66a6d5c006efbd2b82e83e8/conf.py#L37-L39

Termination For online adaptation, no termination is necessary, and iteration continues as long as there is test data. For offline adaptation, the model is first updated and then inference is repeated. Adaptation may of course continue by updating for multiple epochs. I think we need to set _C.MODEL.EPISODIC = False and update evaluation function.