set_global_initializer

paddle.nn.initializer. set_global_initializer ( weight_init, bias_init=None ) [source]

This API is used to set up global model parameter initializer in framework.

After this API is invoked, the global initializer will takes effect in subsequent code.

The model parameters include weight and bias . In the framework, they correspond to paddle.ParamAttr , which is inherited from paddle.Tensor , and is a persistable Variable. This API only takes effect for model parameters, not for variables created through apis such as create_global_var , create_tensor.

If the initializer is also set up by param_attr or bias_attr when creating a network layer, the global initializer setting here will not take effect because it has a lower priority.

If you want to cancel the global initializer in framework, please set global initializer to None .

Parameters
  • weight_init (Initializer) – set the global initializer for weight of model parameters.

  • bias_init (Initializer, optional) – set the global initializer for bias of model parameters. Default: None.

Returns

None

Examples

>>> import paddle
>>> import paddle.nn as nn

>>> nn.initializer.set_global_initializer(nn.initializer.Uniform(), nn.initializer.Constant())
>>> x_var = paddle.uniform((2, 4, 8, 8), dtype='float32', min=-1., max=1.)

>>> # The weight of conv1 is initialized by Uniform
>>> # The bias of conv1 is initialized by Constant
>>> conv1 = nn.Conv2D(4, 6, (3, 3))
>>> y_var1 = conv1(x_var)

>>> # If set param_attr/bias_attr too, global initializer will not take effect
>>> # The weight of conv2 is initialized by Xavier
>>> # The bias of conv2 is initialized by Normal
>>> conv2 = nn.Conv2D(4, 6, (3, 3),
...     weight_attr=nn.initializer.XavierUniform(),
...     bias_attr=nn.initializer.Normal())
>>> y_var2 = conv2(x_var)

>>> # Cancel the global initializer in framework, it will takes effect in subsequent code
>>> nn.initializer.set_global_initializer(None)