weight_diff is treated differently in sphereface and in LargeMargin_softmax_loss about sphereface HOT 2 OPEN

SINGLE, DOUBLE, etc correspond to the case of m=1, m=2, etc. It is simply for the convenience of implementation.

from sphereface.

You did not get what I mean.

In sphereface, margin_inner_product_layer.cpp, line 277-278
you get gradient with respect to w using the same formula regardless of m: caffe_cpu_gemm(CblasTrans, CblasNoTrans, N_, K_, M_, (Dtype)1., top_diff, bottom_data, (Dtype)1., this->blobs_[0]->mutable_cpu_diff()); but

whereas in LargeMargin_softmax_loss, largemargin_inner_product_layer.cpp, line 263-356 you get gradient with respect to w according to m.

Can you tell me why?
Thanks.

from sphereface.