- class paddle. ParamAttr ( name=None, initializer=None, learning_rate=1.0, regularizer=None, trainable=True, do_model_average=True, need_clip=True )
ParamAttrHAS BEEN DEPRECATED since 2.0. Please use
ParamAttrto speficiy the clip scope. There are three clipping strategies: ClipGradByGlobalNorm , ClipGradByNorm , ClipGradByValue .
Create a object to represent the attribute of parameter. The attributes are: name, initializer, learning rate, regularizer, trainable, gradient clip, and model average.
name (str, optional) – The parameter’s name. Default None, meaning that the name would be created automatically.
initializer (Initializer, optional) – The method to initial this parameter. Default None, meaning that the weight parameter is initialized by Xavier initializer, and the bias parameter is initialized by 0.
learning_rate (float, optional) – The parameter’s learning rate. The learning rate when optimize is the global learning rates times the parameter’s learning rate times the factor of learning rate scheduler. Default 1.0.
regularizer (WeightDecayRegularizer, optional) – Regularization strategy. There are two method: L1Decay , L2Decay . If regularizer is also set in
optimizer(such as SGD ), that regularizer setting in optimizer will be ignored. Default None, meaning there is no regularization.
trainable (bool, optional) – Whether this parameter is trainable. Default True.
do_model_average (bool, optional) – Whether this parameter should do model average when model average is enabled. Only used in ExponentialMovingAverage. Default True.
need_clip (bool, optional) – Whether the parameter gradient need to be cliped in optimizer. Default is True.
import paddle weight_attr = paddle.ParamAttr(name="weight", learning_rate=0.5, regularizer=paddle.regularizer.L2Decay(1.0), trainable=True) print(weight_attr.name) # "weight" paddle.nn.Linear(3, 4, weight_attr=weight_attr)