torch.nn.functional.selu# torch.nn.functional.selu(input, inplace=False) → Tensor[source]# 逐元素应用SELU(x)=scale∗(max(0,x)+min(0,α∗(exp(x)−1)))\text{SELU}(x) = scale * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))SELU(x)=scale∗(max(0,x)+min(0,α∗(exp(x)−1)))，其中 α=1.6732632423543772848170429916717\alpha=1.6732632423543772848170429916717α=1.6732632423543772848170429916717 和 scale=1.0507009873554804934193349852946scale=1.0507009873554804934193349852946scale=1.0507009873554804934193349852946。 更多详情请参见 SELU。 返回类型 张量
torch.nn.functional.selu# torch.nn.functional.selu(input, inplace=False) → Tensor[source]# 逐元素应用SELU(x)=scale∗(max(0,x)+min(0,α∗(exp(x)−1)))\text{SELU}(x) = scale * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))SELU(x)=scale∗(max(0,x)+min(0,α∗(exp(x)−1)))，其中 α=1.6732632423543772848170429916717\alpha=1.6732632423543772848170429916717α=1.6732632423543772848170429916717 和 scale=1.0507009873554804934193349852946scale=1.0507009873554804934193349852946scale=1.0507009873554804934193349852946。 更多详情请参见 SELU。 返回类型 张量