When the shape of input is [1,3,112,96], the shape of output is [2,10574]?

[yBeOne]

A torch.randn[1,3,112,96] is as the input ,but the output is shape of [2,10574]? Why not [1,10574]?

[njuaplusplus]

The output is a tuple, according to the code.

But I don't know how to use this repo as a classifier.

[clcarwin]

please read lfw_eval.py: set net.feature = True for eval.
fc5 is the embedding, fc6 is only used for train.

[njuaplusplus]

Thank you for your reply.
I understand that for face verification (compute the distances), we need to set net.feature=True.
My question is if I want to use the fc6 so the network functions as a classifier, what should I do?
I think it's reasonable since it's trained as a classifier.

[njuaplusplus]

More specifically, could you give me some hints on how to get the prediction confidence of a given image with your pre-trained network.
Thanks a lot.