LazyInstanceNorm3d#

classtorch.nn.LazyInstanceNorm3d(eps=1e-05,momentum=0.1,affine=True,track_running_stats=True,device=None,dtype=None)[source]#

Atorch.nn.InstanceNorm3d module with lazy initialization of thenum_features argument.

Thenum_features argument of theInstanceNorm3d is inferred from theinput.size(1).The attributes that will be lazily initialized areweight,bias,running_mean andrunning_var.

Check thetorch.nn.modules.lazy.LazyModuleMixin for further documentationon lazy modules and their limitations.

Parameters

• num_features –$C$C from an expected input of size$(N,C,D,H,W)$(N,C,D,H,W) or$(C,D,H,W)$(C,D,H,W)

• eps (float) – a value added to the denominator for numerical stability. Default: 1e-5

• momentum (Optional[float]) – the value used for the running_mean and running_var computation. Default: 0.1

• affine (bool) – a boolean value that when set toTrue, this module haslearnable affine parameters, initialized the same way as done for batch normalization.Default:False.

• track_running_stats (bool) – a boolean value that when set toTrue, thismodule tracks the running mean and variance, and when set toFalse,this module does not track such statistics and always uses batchstatistics in both training and eval modes. Default:False

Shape:

• Input:$(N,C,D,H,W)$(N,C,D,H,W) or$(C,D,H,W)$(C,D,H,W)

• Output:$(N,C,D,H,W)$(N,C,D,H,W) or$(C,D,H,W)$(C,D,H,W) (same shape as input)

cls_to_become[source]#

alias ofInstanceNorm3d