uniform_like

dragon.random.uniform_like(
  inputs,
  low=- 1,
  high=1,
  dtype='float32',
  **kwargs
)[source]

Return a tensor initialized from the uniform distribution with shape as the other.

\[\text{out} \sim \mathcal{U}(\alpha, \beta) \]
Parameters:
  • inputs (dragon.Tensor) The tensor to hint the shape.
  • low (number, optional, default=-1) The value to \(\alpha\).
  • high (number, optional, default=1) The value to \(\beta\).
  • dtype (str, optional, default='float32') The optional data type.
Returns:

dragon.Tensor The output tensor.