kaiming_uniform_¶

dragon.vm.torch.nn.init.kaiming_uniform_(
  tensor,
  a=0,
  mode='fan_in',
  nonlinearity='leaky_relu'
)[source]¶

Fill tensor from a kaiming uniform distribution.

\[\text{tensor} \sim \mathcal{U}(-\alpha, \alpha) \\ \, \\ \, \text{where} \quad \alpha = \text{gain} \times \sqrt{\frac{3}{\text{fan}}} \]

Parameters:

• tensor (dragon.vm.torch.Tensor) – The input tensor.
• a (number, optional, default=0) – The negative slope to compute gain value.
• mode ({'fan_in', 'fan_out'}, optional) – The mode to compute fans.
• nonlinearity (str, optional, default='leaky_relu') – The nonlinearity to compute gain value.

Returns:

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