mindspore.ops.CumProd

class mindspore.ops.CumProd(exclusive=False, reverse=False)[source]

Computes the cumulative product of the tensor x along axis. For example, if input is a vector of size N, the result will also be a vector of size N, with elements.

\[y_i = x_1 * x_2 * x_3 * ... * x_i\]

Parameters

exclusive (bool) – If True , perform exclusive cumulative product. Default: False .
reverse (bool) – If True , reverse the result along axis. Default: False .

Inputs:

x (Tensor[Number]) - The input tensor.
axis (int) - The dimensions to compute the cumulative product. Only constant value is allowed.

Outputs:

Tensor, has the same shape and dtype as the x.

Raises

TypeError – If exclusive or reverse is not a bool.
TypeError – If axis is not an int.
ValueError – If axis is None.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> a, b, c, = 1, 2, 3
>>> x = Tensor(np.array([a, b, c]).astype(np.float32))
>>> op0 = ops.CumProd()
>>> output0 = op0(x, 0) # output=[a, a * b, a * b * c]
>>> op1 = ops.CumProd(exclusive=True)
>>> output1 = op1(x, 0) # output=[1, a, a * b]
>>> op2 = ops.CumProd(reverse=True)
>>> output2 = op2(x, 0) # output=[a * b * c, b * c, c]
>>> op3 = ops.CumProd(exclusive=True, reverse=True)
>>> output3 = op3(x, 0) # output=[b * c, c, 1]
>>> print(output0)
[1. 2. 6.]
>>> print(output1)
[1. 1. 2.]
>>> print(output2)
[6. 6. 3.]
>>> print(output3)
[6. 3. 1.]
>>> x = Tensor(np.array([[1, 2, 3], [4, 5, 6], [5, 3, 5]]).astype(np.float32))
>>> output4 = op0(x, 0)
>>> output5 = op0(x, 1)
>>> print(output4)
[[ 1.  2.  3.]
 [ 4. 10. 18.]
 [20. 30. 90.]]
>>> print(output5)
[[  1.   2.   6.]
 [  4.  20. 120.]
 [  5.  15.  75.]]