Struct auto_diff::op::loss::BCEWithLogitsLoss

[+] Show declaration

pub struct BCEWithLogitsLoss {}

[−] Expand description

This loss combines a Sigmoid layer and the BCELoss in one single class. This version is more numerically stable than using a plain Sigmoid followed by a BCELoss as, by combining the operations into one layer, we take advantage of the log-sum-exp trick for numerical stability.

-y log (1/(1 + exp(-x))) - (1-y) log(1 - 1/(1 + exp(-x)))

Prediction comes first, label comes second.

Implementations

impl BCEWithLogitsLoss[−]

pub fn new() -> BCEWithLogitsLoss

Trait Implementations

impl OpTrait for BCEWithLogitsLoss[+]

[+] Show hidden undocumented items

fn get_name(&self) -> String

fn get_input_size(&self) -> usize

fn get_output_size(&self) -> usize

fn apply(&mut self, input: &[&Tensor], output: &[&Tensor])[−]

The first is the prediction, the second input is the label ORDER IS IMPORTANT, SECOND ARGUMENT WON'T GET GRADEINT.

fn grad(
    &self,
    input: &[&Tensor],
    output_grad: &[&Tensor],
    input_grad: &[&Tensor]
)[−]

Given the forward input value and backward output_grad, Update weight gradient. return backward input gradeint.

fn get_values(&self) -> Vec<&Tensor>[−]

access weight values

fn set_values(&self, _v: &[Tensor])

fn get_grads(&self) -> Vec<&Tensor>[−]

access gradient values

fn call(&mut self, input: &[&Tensor]) -> Vec<Tensor>