XavierInit — mmengine 0.10.7 documentation (original) (raw)

class mmengine.model.XavierInit(gain=1, distribution='normal', **kwargs)[source]¶

Initialize module parameters with values according to the method described in the paper below.

Understanding the difficulty of training deep feedforward neural networks - Glorot, X. & Bengio, Y. (2010).

Parameters:

• gain (int | float) – an optional scaling factor. Defaults to 1.
• bias (int | float) – the value to fill the bias. Defaults to 0.
• bias_prob (float, optional) – the probability for bias initialization. Defaults to None.
• distribution (str) – distribution either be 'normal'or 'uniform'. Defaults to 'normal'.
• layer (str | list_[_str] , optional) – the layer will be initialized. Defaults to None.