Uniform

class paddle.nn.initializer. Uniform ( low=- 1.0, high=1.0, name=None ) [source]

The uniform distribution initializer.

Parameters
  • low (float, optional) – Lower boundary of the uniform distribution. The default value is \(-1.0\).

  • high (float, optional) – Upper boundary of the uniform distribution. The default value is \(1.0\).

  • name (str, optional) – For details, please refer to Name. Generally, no setting is required. Default: None.

Returns

A parameter initialized by uniform distribution.

Examples

import paddle

data = paddle.ones(shape=[3, 1, 2], dtype='float32')
weight_attr = paddle.framework.ParamAttr(
    name="linear_weight",
    initializer=paddle.nn.initializer.Uniform(low=-0.5, high=0.5))
bias_attr = paddle.framework.ParamAttr(
    name="linear_bias",
    initializer=paddle.nn.initializer.Uniform(low=-0.5, high=0.5))
linear = paddle.nn.Linear(2, 2, weight_attr=weight_attr, bias_attr=bias_attr)
# linear.weight:  [[-0.46245047  0.05260676]
#                  [ 0.38054508  0.29169726]]
# linear.bias:  [-0.2734719   0.23939109]

res = linear(data)
# res:  [[[-0.3553773  0.5836951]]
#        [[-0.3553773  0.5836951]]
#        [[-0.3553773  0.5836951]]]