Trait collenchyma_nn::Tanh [−] [src]

pub trait Tanh<F>: NN<F> {
    fn tanh(&self, x: &mut SharedTensor<F>, result: &mut SharedTensor<F>) -> Result<(), Error>;
    fn tanh_plain(&self, x: &SharedTensor<F>, result: &mut SharedTensor<F>) -> Result<(), Error>;
    fn tanh_grad(&self, x: &mut SharedTensor<F>, x_diff: &mut SharedTensor<F>, result: &mut SharedTensor<F>, result_diff: &mut SharedTensor<F>) -> Result<(), Error>;
    fn tanh_grad_plain(&self, x: &SharedTensor<F>, x_diff: &SharedTensor<F>, result: &SharedTensor<F>, result_diff: &mut SharedTensor<F>) -> Result<(), Error>;
}

Provides the functionality for a Backend to support TanH operations.

Required Methods

fn tanh(&self, x: &mut SharedTensor<F>, result: &mut SharedTensor<F>) -> Result<(), Error>

Computes the hyperbolic Tangent over the input Tensor x with complete memory management.

Saves the result to result.

For a no-memory managed version see tanh_plain.

fn tanh_plain(&self, x: &SharedTensor<F>, result: &mut SharedTensor<F>) -> Result<(), Error>

Computes the tanh over the input Tensor x without any memory management.

Saves the result to result.

Attention:
For a correct computation result, you need to manage the memory allocation and synchronization yourself.
For a memory managed version see tanh.

fn tanh_grad(&self, x: &mut SharedTensor<F>, x_diff: &mut SharedTensor<F>, result: &mut SharedTensor<F>, result_diff: &mut SharedTensor<F>) -> Result<(), Error>

Computes the gradient of tanh over the input Tensor x with complete memory management.

Saves the result to result_diff.

For a no-memory managed version see tanh_grad_plain.

fn tanh_grad_plain(&self, x: &SharedTensor<F>, x_diff: &SharedTensor<F>, result: &SharedTensor<F>, result_diff: &mut SharedTensor<F>) -> Result<(), Error>

Computes the gradient of tanh over the input Tensor x without any memory management.

Saves the result to result_diff.

Attention:
For a correct computation result, you need to manage the memory allocation and synchronization yourself.
For a memory managed version see tanh_grad.

Implementors