paddle. empty_like ( x, dtype=None, name=None ) [source]

This Op returns a Tensor with uninitialized data which has identical shape of x and dtype. If the dtype is None, the data type of Tensor is same with x.

  • x (Tensor) – The input tensor which specifies shape and data type. The data type can be bool, float16, float32, float64, int32, int64.

  • dtype (np.dtype|str, optional) – The data type of output. The data type can be one of bool, float16, float32, float64, int32, int64. The default value is None, which means the output data type is the same as input.

  • name (str, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to Name.


Tensor which is created according to x and dtype, and is uninitialized.

Return type



import paddle
import numpy as np

paddle.set_device("cpu")  # and use cpu device

x = paddle.randn([2, 3], 'float32')
output = paddle.empty_like(x)
#[[1.8491974e+20 1.8037303e+28 1.7443726e+28]     # uninitialized
# [4.9640171e+28 3.0186127e+32 5.6715899e-11]]    # uninitialized