erkuoge6464的博客

一维卷积三种类型：full卷积、same卷积和valid卷积

标签平滑损失函数： class LabelSmoothingCrossEntropy(nn.Module): def __init__(self, epsilon: float = 0.1, reduction='mean'): super().__init__() self.epsilon, self.reduction = epsilon, reduction def forward(self, output, target):