trunc_normal_¶

dragon.vm.torch.nn.init.trunc_normal_(
  tensor,
  mean=0,
  std=1,
  a=- 2,
  b=2
)[source]¶

Fill tensor from a truncated normal distribution.

\[\text{tensor} \sim \mathcal{TN}(\mu, \sigma^{2}, a, b) \]

Parameters:

• tensor (dragon.vm.torch.Tensor) – The input tensor.
• mean (number, optional, default=0) – The value to \(\mu\).
• std (number, optional, default=1) – The value to \(\sigma\).
• a (number, optional, default=-2) – The value to \(a\).
• b (number, optional, default=2) – The value to \(b\).

Returns:

dragon.vm.torch.Tensor – The output tensor.