I've seen some implementations of SimCLR, MoCo, BYOL and they have a python file that does linear evaluation. Simply, they froze the parameters of the trained encoder (resnet18 or resnet50) and only train a FC to see the top1 accuracy on test dataset. Do you do this testing? I'm asking because I'm not sured what does the kNN-acc do in this project.
Thank you and look forward to your reply.
I've seen some implementations of SimCLR, MoCo, BYOL and they have a python file that does linear evaluation. Simply, they froze the parameters of the trained encoder (resnet18 or resnet50) and only train a FC to see the top1 accuracy on test dataset. Do you do this testing? I'm asking because I'm not sured what does the kNN-acc do in this project. Thank you and look forward to your reply.