Kaiming normal initialization — nn_init_kaiming_normal

Fills the input Tensor with values according to the method described in Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification - He, K. et al. (2015), using a normal distribution.

Usage

nn_init_kaiming_normal_(
  tensor,
  a = 0,
  mode = "fan_in",
  nonlinearity = "leaky_relu"
)

Arguments

tensor: an n-dimensional torch.Tensor
a: the negative slope of the rectifier used after this layer (only used with 'leaky_relu')
mode: either 'fan_in' (default) or 'fan_out'. Choosing 'fan_in' preserves the magnitude of the variance of the weights in the forward pass. Choosing 'fan_out' preserves the magnitudes in the backwards pass.
nonlinearity: the non-linear function. recommended to use only with 'relu' or 'leaky_relu' (default).

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_kaiming_normal_(w, mode = "fan_in", nonlinearity = "leaky_relu")
}
#> torch_tensor
#> -0.1326 -0.0364 -0.6945  0.1553  0.5481
#>  0.9961  0.0728 -0.0166  0.6824 -0.8009
#>  0.1405  0.2096  0.5808  0.1475 -0.4082
#> [ CPUFloatType{3,5} ]