mindspore.ops.derivative

mindspore.ops.derivative(fn, primals, order)[source]

This function is designed to calculate the higher order differentiation of given composite function. To figure out order-th order differentiations, original inputs and order must be provided together. In particular, the value of input first order derivative is set to 1, while the other to 0.

Note

If primals is Tensor of int type, it will be converted to Tensor of float type.

Parameters

fn (Union[Cell, function]) – Function to do TaylorOperation.
primals (Union[Tensor, tuple[Tensor]]) – The inputs to fn.
order (int) – For each Tensor, the order-th order of derivative of output with respect to the inputs will be figured out.

Returns

Tuple, tuple of out_primals and out_series.

out_primals (Union[Tensor, list[Tensor]]) - The output of fn(primals).
out_series (Union[Tensor, list[Tensor]]) - The order-th order of derivative of output with respect to the inputs.

Raises

TypeError – If primals is not a tensor or tuple of tensors.
TypeError – If order is not int.
ValueError – If order is less than 1.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import numpy as np
>>> import mindspore as ms
>>> import mindspore.nn as nn
>>> import mindspore.ops as ops
>>> from mindspore import Tensor
>>> ms.set_context(mode=ms.GRAPH_MODE)
>>> class Net(nn.Cell):
...     def __init__(self):
...         super().__init__()
...         self.sin = ops.Sin()
...         self.exp = ops.Exp()
...     def construct(self, x):
...         out1 = self.sin(x)
...         out2 = self.exp(out1)
...         return out2
>>> primals = Tensor(np.array([[1, 2], [3, 4]]).astype(np.float32))
>>> order = 3
>>> net = Net()
>>> out_primals, out_series = ops.derivative(net, primals, order)
>>> print(out_primals, out_series)
[[2.319777  2.4825778]
 [1.1515628 0.4691642]] [[-4.0515366   3.6724353 ]
 [ 0.5053504  -0.52061415]]