paddle. scale ( x, scale=1.0, bias=0.0, bias_after_scale=True, act=None, name=None ) [source]

Scale operator.

Putting scale and bias to the input Tensor as following:

bias_after_scale is True:


bias_after_scale is False:

  • x (Tensor) – Input N-D Tensor of scale operator. Data type can be float32, float64, int8, int16, int32, int64, uint8.

  • scale (float|Tensor) – The scale factor of the input, it should be a float number or a Tensor with shape [1] and data type as float32.

  • bias (float) – The bias to be put on the input.

  • bias_after_scale (bool) – Apply bias addition after or before scaling. It is useful for numeric stability in some circumstances.

  • act (str, optional) – Activation applied to the output such as tanh, softmax, sigmoid, relu.

  • 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


Output tensor of scale operator, with shape and data type same as input.

Return type



# scale as a float32 number
import paddle

data = paddle.randn(shape=[2,3], dtype='float32')
res = paddle.scale(data, scale=2.0, bias=1.0)
# scale with parameter scale as a Tensor
import paddle

data = paddle.randn(shape=[2, 3], dtype='float32')
factor = paddle.to_tensor([2], dtype='float32')
res = paddle.scale(data, scale=factor, bias=1.0)