Any idea of using circle loss in a generative model?
Closed this issue · 2 comments
parap1uie-s commented
Hi, thanks for the awesome implementation of Circle Loss.
We know that metric learning methods can essentially create a generative model, like main_emmbed.py
, we could acquire emmbeding
layer's output with 3D-vector to print a spherical map.
However, I noticed that the output of the complete model was generated by a 10-dimensional fully connected layer, which means that the model is a discriminant model.
Is there any way to directly use the output of the embedding layer as a generative model to achieve classification? Like np.argmin(distance)
(prototypical network)?
zhen8838 commented
不好意思,我对于prototypical network
不太了解。如果想使用向量距离进行分类首先需要确定分类阈值。
parap1uie-s commented
我明白了。最后一个全连接层里权值矩阵,本身就是类似于anchor一样的聚类中心。多谢