Layernorm in Prototype learning

[Trainingzy]

Thanks for your great work!
I notice you use layernorm for the final features before the classifier and also for the predictions. I think it is quite uncommon in prototype learning (correct me if i am wrong).

Could you please provide some explanation for this? And if removing the two layernorm, will the performance be degraded?

ProtoSeg/lib/models/nets/hrnet.py

Line 81 in 1c4a778

self.feat_norm = nn.LayerNorm(in_channels)

[kaigelee]

Have you solved it? I have the same problem