vjp

paddle.incubate.autograd. vjp ( func, xs, v=None ) [source]

Computes the Vector-Jacobian product, a functional form of reverse mode automatic differentiation.

Warning

This API is in beta, the signatures could be changed in future version.

Parameters

  • func (Callable) – A function that takes xs as inputs parameter and returns a sequence of Tensors or a Tensor.

  • xs (Tensor|Sequence[Tensor]) – Used as positional arguments to evaluate func. xs is accepted as one Tensor or a sequence of Tensors.

  • v (Tensor|Sequence[Tensor]|None, optional) – The cotangent vector invovled in the VJP computation. v matches the size and shape of func ‘s output. Defaults to None, which is equivalent to all ones the same size of func ‘s output.

Returns

  • func_out(Tensor|tuple[Tensor]): The output of func(xs) .

  • vjp(Tensor|tuple[Tensor]): The vjp result.

Return type

output(tuple)

Examples

import paddle

def func(x):
    return paddle.matmul(x, x)

x = paddle.ones(shape=[2, 2], dtype='float32')
_, vjp_result = paddle.incubate.autograd.vjp(func, x)
print(vjp_result)
# Tensor(shape=[2, 2], dtype=float32, place=Place(gpu:0), stop_gradient=False,
#        [[4., 4.],
#         [4., 4.]])

v = paddle.to_tensor([[1.0, 0.0], [0.0, 0.0]])
_, vjp_result = paddle.incubate.autograd.vjp(func, x, v)
print(vjp_result)
# Tensor(shape=[2, 2], dtype=float32, place=Place(gpu:0), stop_gradient=False,
#        [[2., 1.],
#         [1., 0.]])