Open mzprose opened 3 years ago
Hello, is your code suitable for calculating the nuclear norm loss between tensor (batch, channel, height, width)?
是的,核范数交叉熵损失输入与交叉熵损失shape与type相同。另外,训练时你需要仔细调节学习率。
Hello, is your code suitable for calculating the nuclear norm loss between tensor (batch, channel, height, width)?