profile
viewpoint

Ask questionsHow to valuate during traing

I notice the finnal R@1 after 200epoches in ReadMe is 60%, but there is no code to valuate the model in the repo, only training accuracy.

Can you help me that how to valuate the perfomance during the training?

facebookresearch/moco

Answer questions KaimingHe

I am not aware of a reliable way of validating during training. You may consider the kNN classifier adopted in the InstDisc paper.

useful!

Related questions

No questions were found.
source:https://uonfu.com/
Github User Rank List