normalize¶

dragon.vm.torch.nn.functional.normalize(
  input,
  p=2,
  dim=1,
  end_dim=None,
  eps=1e-12,
  out=None
)[source]¶

Apply the \(L_{p}\) normalization to the input.

The \(L_{p}\) normalization is defined as:

\[v = \frac{v}{\left\|v\right\|_{p} + \epsilon} \]

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• p (int, optional, default=2) – The exponent of norm.
• dim (int, optional, default=1) – The first dimension to reduce.
• end_dim (int, optional) – The last dimension to reduce.
• eps (float, optional, default=1e-12) – The value to \(\epsilon\).
• out (dragon.vm.torch.Tensor, optional) – The output tensor.

Returns:

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