Dragon API Dragon v0.3.0 Python GlorotNormal¶ class dragon.vm.tensorlayer.initializers.GlorotNormal( mode='fan_avg', scale=2.0)[source]¶ Fill tensor from a glorot normal distribution. __init__¶ GlorotNormal.__init__( mode='fan_avg', scale=2.0)[source]¶ Create a GlorotNormal initializer. Parameters: mode ({'fan_in', 'fan_out', 'fan_avg'}, optional) – The mode to compute the fans. scale (float, optional, default=2.0) – The scale factor to distribution. 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.