Mish: A Self Regularized Non-Monotonic Neural Activation Function.
Usage
activation_mish(x)
Arguments
x
A `Tensor`. Must be one of the following types: `float16`, `float32`, `float64`.
Returns: A `Tensor`. Has the same type as `x`.
Value
A `Tensor`. Has the same type as `x`.
Details
Computes mish activation: x * tanh(softplus(x))
See [Mish: A Self Regularized Non-Monotonic Neural Activation Function](https://arxiv.org/abs/1908.08681).