mindspore.ops.bias_add

mindspore.ops.bias_add(input_x, bias)[source]

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

Parameters

  • input_x (Tensor) – The input tensor. The shape can be 2-5 dimensions. The data type should be float16 or float32.

  • bias (Tensor) – The bias tensor, with shape \((C)\). C must be the same as channel dimension C of input_x. The data type should be float16 or float32.

Returns

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

Raises

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

  • TypeError – If dtype of input_x or bias is neither float16 nor float32.

  • 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

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