torch.autograd Namespace Reference

Functions
def	backward (tensors, grad_tensors=None, retain_graph=None, create_graph=False, grad_variables=None)
def	grad (outputs, inputs, grad_outputs=None, retain_graph=None, create_graph=False, only_inputs=True, allow_unused=False)
def	variable (args, kwargs)

Detailed Description

``torch.autograd`` provides classes and functions implementing automatic
differentiation of arbitrary scalar valued functions. It requires minimal
changes to the existing code - you only need to declare :class:`Tensor` s
for which gradients should be computed with the ``requires_grad=True`` keyword.