randn

dragon.vm.torch.randn(
  *size,
  out=None,
  dtype='float32',
  device=None,
  requires_grad=False
)[source]

Return a tensor from the normal distribution of N(0, 1).

Parameters:
  • size (int...) – The output tensor shape.
  • out (dragon.vm.torch.Tensor, optional) – The output tensor.
  • dtype (str, optional, default='float32') – The data type of output tensor.
  • device (dragon.vm.torch.device, optional) – The device of output tensor.
  • requires_grad (bool, optional, default=False) – Record gradient for output tensor or not.
Returns:

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