mindspore.ops.BiasAdd

class mindspore.ops.BiasAdd(data_format='NCHW')[source]

Returns the sum of the input Tensor and the bias Tensor. Before adding, the bias Tensor will be broadcasted to be consistent with the shape of the input Tensor.

Parameters

data_format (str, optional) – The format of input and output data. It should be "NHWC" , "NCHW" or "NCDHW" . Default is "NCHW" .

Inputs:

  • input_x (Tensor) - The input tensor. The shape can be 2-5 dimensions. Supported dtypes:

    • Ascend/CPU: all Number type.

    • GPU: float16, float32, int8.

  • bias (Tensor) - The bias tensor, with shape \((C)\). C must be the same as channel dimension C of input_x. It has the same type as input_x.

Outputs:

Tensor, with the same shape and data type as input_x.

Raises

  • TypeError – If data_format is not a str.

  • ValueError – If value of data_format is not in the range of ['NHWC','NCHW','NCDHW'].

  • TypeError – If input_x or bias is not a Tensor.

  • TypeError – If dtype of input_x or bias is inconsistent.

  • TypeError – If dimension of input_x is not in the range [2, 5].

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input_x = Tensor(np.arange(6).reshape((2, 3)), mindspore.float32)
>>> bias = Tensor(np.random.random(3).reshape((3,)), mindspore.float32)
>>> bias_add = ops.BiasAdd()
>>> output = bias_add(input_x, bias)
>>> print(output.shape)
(2, 3)