torch.nn.functional.huber_loss¶
- torch.nn.functional.huber_loss(input, target, reduction='mean', delta=1.0)[source]¶
Compute the Huber loss.
Function uses a squared term if the absolute element-wise error falls below delta and a delta-scaled L1 term otherwise.
When delta equals 1, this loss is equivalent to SmoothL1Loss. In general, Huber loss differs from SmoothL1Loss by a factor of delta (AKA beta in Smooth L1).
See
HuberLossfor details.- Return type
