如何在 pytorch 中制作截断的正态分布?
How to make a Truncated normal distribution in pytorch?
我想在 PyTorch 中创建一个截断正态分布(即具有范围的高斯分布)。
我希望能够更改均值、标准差和范围。
有 PyTorch 方法吗?
使用torch.nn.init.trunc_normal_
.
给定的描述 Here:
Fills the input Tensor with values drawn from a truncated
normal distribution. The values are effectively drawn from the
normal distribution :math:\mathcal{N}(\text{mean}, \text{std}^2)
with values outside :math:[a, b]
redrawn until they are within
the bounds. The method used for generating the random values works
best when :math:a \leq \text{mean} \leq b
.
我想在 PyTorch 中创建一个截断正态分布(即具有范围的高斯分布)。
我希望能够更改均值、标准差和范围。
有 PyTorch 方法吗?
使用torch.nn.init.trunc_normal_
.
给定的描述 Here:
Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distribution :math:
\mathcal{N}(\text{mean}, \text{std}^2)
with values outside :math:[a, b]
redrawn until they are within the bounds. The method used for generating the random values works best when :math:a \leq \text{mean} \leq b
.