Template Class NormImplBase#

Inheritance Relationships#

Class Documentation#

template<size_t D, typename Derived, typename DerivedOptions>
class NormImplBase : public torch::nn::Cloneable<Derived>#

Base class for all (dimension-specialized) batchnorm and instancenorm modules.

Subclassed by torch::nn::BatchNormImplBase< 1, BatchNorm1dImpl >, torch::nn::BatchNormImplBase< 3, BatchNorm3dImpl >, torch::nn::BatchNormImplBase< 2, BatchNorm2dImpl >, torch::nn::InstanceNormImpl< 1, InstanceNorm1dImpl >, torch::nn::InstanceNormImpl< 2, InstanceNorm2dImpl >, torch::nn::InstanceNormImpl< 3, InstanceNorm3dImpl >

Public Functions

inline NormImplBase(const DerivedOptions &options_)#

inline virtual void reset() override#

reset() must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.

inline void reset_running_stats()#

inline void reset_parameters()#

Public Members

DerivedOptions options#

The options with which this module was constructed.

Tensor weight#

The learned weight.

Only defined if the affine option was true upon construction.

Tensor bias#

The learned bias.

Only defined if the affine option was true upon construction.

Tensor running_mean#

The running mean.

Only defined if the track_running_stats option was true upon construction.

Tensor running_var#

The running variance.

Only defined if the track_running_stats option was true upon construction.

Tensor num_batches_tracked#

The number of the forward call.

Only defined if the track_running_stats option was true upon construction.

Protected Functions

virtual void _check_input_dim(const Tensor &input) = 0#