Closed elvindp closed 2 years ago
circle softmax 和 pair-wise circle 可以具体看看 circle loss 那篇 paper,主要就是分类 loss 和度量学习 loss 的区别
circle softmax 和 pair-wise circle 可以具体看看 circle loss 那篇 paper,主要就是分类 loss 和度量学习 loss 的区别
明白了,所以, 一个输入时,是一组logits,和softmax里存放的矩阵乘 另一个是embeding pair。
@elvindp @L1aoXingyu 请问以下,pair-wise circle的输入,embedding是Batch*Embedding Dim的Tensor。Target是对应什么呢?对应这个Batch个的ID号么?
This issue is stale because it has been open for 30 days with no activity.
This issue was closed because it has been inactive for 14 days since being marked as stale.
circle softmax就是circle loss……是我傻逼了…… 但circle loss里的pairwise loss和circle softmax的区别是什么?什么时候用?
谢谢