Module dfdx::losses

Standard loss functions such as mse_loss(), cross_entropy_with_logits_loss(), and more.

Functions

• binary_cross_entropy_with_logits_loss
  Binary Cross Entropy With Logits in numerically stable way.
• cross_entropy_with_logits_loss
  Cross entropy loss. This computes: -(logits.log_softmax() * target_probs).sum(-1).mean()
• huber_loss
  Huber Loss uses absolute error when the error is higher than beta, and squared error when the error is lower than beta.
• kl_div_with_logits_loss
  KL Divergence loss. This computes (target_probs * (target_probs.log() - logits.log_softmax())).sum(-1).mean()
• mae_loss
  Mean absolute error. This computes (pred - targ).abs().mean()
• mse_loss
  Mean Squared Error. This computes (pred - targ).square().mean().
• rmse_loss
  Root Mean square error. This computes (pred - targ).square().mean().sqrt()
• smooth_l1_loss
  Smooth l1 loss (closely related to Huber Loss) uses absolute error when the error is higher than beta, and squared error when the error is lower than beta.