why does the way of calculating l1_loss depend on target.requires_grad?
def l1_loss(input, target, size_average=None, reduce=None, reduction='mean'):
# type: (Tensor, Tensor, Optional[bool], Optional[bool], str) -> Tensor
r"""l1_loss(input, target, size_average=None, reduce=None, reduction='mean') -> Tensor
Function that takes the mean element-wise absolute value difference.
See :class:`~torch.nn.L1Loss` for details.
"""
if not (target.size() == input.size()):
warnings.warn("Using a target size ({}) that is different to the input size ({}). "
"This will likely lead to incorrect results due to broadcasting. "
"Please ensure they have the same size.".format(target.size(), input.size()),
stacklevel=2)
if size_average is not None or reduce is not None:
reduction = _Reduction.legacy_get_string(size_average, reduce)
if target.requires_grad:
ret = torch.abs(input - target)
if reduction != 'none':
ret = torch.mean(ret) if reduction == 'mean' else torch.sum(ret)
else:
expanded_input, expanded_target = torch.broadcast_tensors(input, target)
ret = torch._C._nn.l1_loss(expanded_input, expanded_target, _Reduction.get_enum(reduction))
return ret