torch.nn.functional.selu¶ torch.nn.functional.selu(input, inplace=False) → 张量[源码]¶ 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。 有关更多详细信息，请参阅 SELU。 Return type 张量
