Normal

class deeplay.initializers.normal.Normal(targets: ~typing.Tuple[~typing.Type[~torch.nn.modules.module.Module], ...] = (<class 'torch.nn.modules.linear.Linear'>, <class 'torch.nn.modules.conv.Conv1d'>, <class 'torch.nn.modules.conv.Conv2d'>, <class 'torch.nn.modules.conv.Conv3d'>, <class 'torch.nn.modules.conv.ConvTranspose1d'>, <class 'torch.nn.modules.conv.ConvTranspose2d'>, <class 'torch.nn.modules.conv.ConvTranspose3d'>, <class 'torch.nn.modules.batchnorm.BatchNorm1d'>, <class 'torch.nn.modules.batchnorm.BatchNorm2d'>, <class 'torch.nn.modules.batchnorm.BatchNorm3d'>), mean: float = 0.0, std: float = 1.0)

Bases: Initializer

Methods Summary

initialize_tensor(tensor, name)

Methods Documentation

initialize_tensor(tensor, name)