- class torch.nn.LazyBatchNorm2d(eps=1e-05, momentum=0.1, affine=True, track_running_stats=True, device=None, dtype=None)[source]¶
torch.nn.BatchNorm2dmodule with lazy initialization of the
num_featuresargument of the
BatchNorm2dthat is inferred from the
input.size(1). The attributes that will be lazily initialized are weight, bias, running_mean and running_var.
torch.nn.modules.lazy.LazyModuleMixinfor further documentation on lazy modules and their limitations.
eps (float) – a value added to the denominator for numerical stability. Default: 1e-5
momentum (float) – the value used for the running_mean and running_var computation. Can be set to
Nonefor cumulative moving average (i.e. simple average). Default: 0.1
affine (bool) – a boolean value that when set to
True, this module has learnable affine parameters. Default:
track_running_stats (bool) – a boolean value that when set to
True, this module tracks the running mean and variance, and when set to
False, this module does not track such statistics, and initializes statistics buffers
None. When these buffers are
None, this module always uses batch statistics. in both training and eval modes. Default: