Dragon API Dragon v0.3.0 Python RandomNormal¶ class dragon.vm.tensorlayer.initializers.RandomNormal( mean=0.0, stddev=0.05)[source]¶ Fill tensor from a normal distribution. __init__¶ RandomNormal.__init__( mean=0.0, stddev=0.05)[source]¶ Create a RandomNormal initializer. Parameters: mean (number, optional, default=0.) – The value to \(\mu\). stddev (number, optional, default=0.05) – The value to \(\sigma\). Methods¶ __call__¶ Initializer.__call__( shape, dtype='float32', **kwargs)[source] Return a tensor initialized as specified initializer. Parameters: shape (Sequence[int]) – The shape of the tensor. dtype (str, optional, default='float32') – The optional data type. Returns:dragon.Tensor – The output tensor.