mindspore.nn.Jvp

class mindspore.nn.Jvp(fn)[source]

Compute the jacobian-vector-product of the given network. Jvp is equivalent to forward mode autodiff.

Parameters: network (Cell) – The network that takes Tensor inputs and returns a tuple of Tensors or a Tensor.

Inputs:

inputs (Tensors) - The inputs to net.
v (Tensors or Tuple of Tensors) - The vector for which the Jacobian vector product is computed. Must have the same size as the input of network.

Outputs:

A tuple with 2 Tensors or Tuple of Tensors: - net_output (Tensors or Tuple of Tensors) - The output of network(inputs). - jvp (Tensors or Tuple of Tensors) - The result of the jacobian vector product.

Examples

>>> from mindspore.nn import Jvp
>>> class Net(nn.Cell):
...     def construct(self, x, y):
...         return x**3 + y
>>> x = Tensor(np.array([[1, 2], [3, 4]]).astype(np.float32))
>>> y = Tensor(np.array([[1, 2], [3, 4]]).astype(np.float32))
>>> v = Tensor(np.array([[1, 1], [1, 1]]).astype(np.float32))
>>> output = Jvp(Net())(x, y, (v, v))