TruncNormalInit — mmengine 0.10.7 documentation (original) (raw)

class mmengine.model.TruncNormalInit(mean=0, std=1, a=-2, b=2, **kwargs)[source]¶

Initialize module parameters with the values drawn from the normal distribution \(\mathcal{N}(\text{mean}, \text{std}^2)\) with values outside \([a, b]\).

Parameters:

• mean (float) – the mean of the normal distribution. Defaults to 0.
• std (float) – the standard deviation of the normal distribution. Defaults to 1.
• a (float) – The minimum cutoff value.
• b (float) – The maximum cutoff value.
• bias (float) – the value to fill the bias. Defaults to 0.
• bias_prob (float, optional) – the probability for bias initialization. Defaults to None.
• layer (str | list_[_str] , optional) – the layer will be initialized. Defaults to None.