Closed SNEAndy closed 7 months ago
Hi,I'm using the mAUCMLoss to finish my multi-label classification. I realized that if the batch size of my dataloader is 1,the mAUCMLoss will always be 0,otherwise,it will not. So the batch size must greater than 1 to fit this loss function ?
Do you still have this issue?
Hi,I'm using the mAUCMLoss to finish my multi-label classification. I realized that if the batch size of my dataloader is 1,the mAUCMLoss will always be 0,otherwise,it will not. So the batch size must greater than 1 to fit this loss function ?