Structs

  • | The LeakyRelu op takes one input tensor | $X$ and an argument $alpha$, and produces | one output tensor $Y$ of the same shape | as $X.$ The op performs the element wise | leaky relu operation, defined as | | $$y=LeakyRelu(x) =\begin{cases}\alpha | x & x < 0\x & otherwise\end{cases}$$ | | The default value of alpha is 0.01. | | Github Links: | | - https://github.com/pytorch/pytorch/blob/master/caffe2/operators/leaky_relu_op.h | | - https://github.com/pytorch/pytorch/blob/master/caffe2/operators/leaky_relu_op.cc |