pub fn binary_cross_entropy_with_logits_loss<S: Shape, E: Dtype, D: Device<E>, T: Tape<E, D>>(
    logits: Tensor<S, E, D, T>,
    target_probs: Tensor<S, E, D>
) -> Tensor<Rank0, E, D, T>
Expand description

Binary Cross Entropy With Logits in numerically stable way.

See bce_with_logits.

Inputs

  • logits - unnormalized inputs. NOT output of sigmoid
  • target_probs - target values between 0 and 1.