o Qe@s@ddlmZddlmZgZGdddeZGdddeZdS))NormalInitializer)TruncatedNormalInitializerc"eZdZdZdfdd ZZS)NormalaThe Random Normal (Gaussian) distribution initializer. Args: mean (float, optional): mean of the normal distribution. The default value is 0.0. std (float, optional): standard deviation of the normal distribution. The default value is 1.0. 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 :ref:`api_guide_Name`. Returns: A parameter initialized by Random Normal (Gaussian) distribution. Examples: .. code-block:: python import paddle data = paddle.ones(shape=[3, 1, 2], dtype='float32') weight_attr = paddle.framework.ParamAttr( name="linear_weight", initializer=paddle.nn.initializer.Normal(mean=0.0, std=2.0)) bias_attr = paddle.framework.ParamAttr( name="linear_bias", initializer=paddle.nn.initializer.Normal(mean=0.0, std=2.0)) linear = paddle.nn.Linear(2, 2, weight_attr=weight_attr, bias_attr=bias_attr) # linear.weight: [[ 2.1973135 -2.2697184] # [-1.9104223 -1.0541488]] # linear.bias: [ 0.7885926 -0.74719954] res = linear(data) # res: [[[ 1.0754838 -4.071067 ]] # [[ 1.0754838 -4.071067 ]] # [[ 1.0754838 -4.071067 ]]] ?Nc:|dusJd|dusJdtt|j||dddSNzmean should not be Nonezstd should not be None)locscaleseed)superr__init__selfmeanZstdname __class__LD:\Projects\ConvertPro\env\Lib\site-packages\paddle/nn/initializer/normal.pyr8zNormal.__init__rrN__name__ __module__ __qualname____doc__r __classcell__rrrrrs"rcr)TruncatedNormalaThe truncated normal distribution (Gaussian distribution) initializer. Args: mean (float, optional): Mean of the normal distribution. The default value is :math:`0.0`. std (float, optional): Standard deviation of the normal distribution. The default value is :math:`1.0`. name (str, optional): For details, please refer to :ref:`api_guide_Name`. Generally, no setting is required. Default: None. Returns: A parameter initialized by truncated normal distribution (Gaussian distribution). Examples: .. code-block:: python import paddle data = paddle.ones(shape=[3, 1, 2], dtype='float32') weight_attr = paddle.framework.ParamAttr( name="linear_weight", initializer=paddle.nn.initializer.TruncatedNormal(mean=0.0, std=2.0)) bias_attr = paddle.framework.ParamAttr( name="linear_bias", initializer=paddle.nn.initializer.TruncatedNormal(mean=0.0, std=2.0)) linear = paddle.nn.Linear(2, 2, weight_attr=weight_attr, bias_attr=bias_attr) # linear.weight: [[-1.0981836 1.4140984] # [ 3.1390522 -2.8266568]] # linear.bias: [-2.1546738 -1.6570673] res = linear(data) # res: [[[-0.11380529 -3.0696259 ]] # [[-0.11380529 -3.0696259 ]] # [[-0.11380529 -3.0696259 ]] rrNcrr )rr rrrrrr`rzTruncatedNormal.__init__rrrrrrr >s!r N)Zfluid.initializerrr__all__rr rrrrs  )