mindspore.numpy.exp(x, dtype=None)[source]

Calculates the exponential of all elements in the input array.


Numpy arguments casting, order, subok, signature, and extobj are not supported. When where is provided, out must have a tensor value. out is not supported for storing the result, however it can be used in combination with where to set the value at indices for which where is set to False. On GPU, the supported dtypes are np.float16, and np.float32. On CPU, the supported dtypes are np.float16, np.float32, np.float64.

  • x (Tensor) – input data.

  • dtype (mindspore.dtype, optional) – defaults to None. Overrides the dtype of the output Tensor.


Tensor or scalar, element-wise exponential of x. This is a scalar if both x1 and x2 are scalars.

Supported Platforms:

Ascend GPU CPU


>>> import mindspore.numpy as np
>>> output = np.exp(np.arange(5).astype(np.float32))
>>> print(output)
[ 1.         2.718282   7.3890557 20.085537  54.598145 ]