Rate this Page

Template Class ConvNdImpl#

Inheritance Relationships#

Base Type#

Derived Types#

Class Documentation#

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

Base class for all (dimension-specialized) convolution modules.

Subclassed by torch::nn::ConvTransposeNdImpl< 1, ConvTranspose1dImpl >, torch::nn::ConvTransposeNdImpl< 3, ConvTranspose3dImpl >, torch::nn::ConvTransposeNdImpl< 2, ConvTranspose2dImpl >, torch::nn::ConvTransposeNdImpl< D, Derived >

Public Functions

inline explicit ConvNdImpl(detail::ConvNdOptions<D> 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_parameters()#
inline virtual void pretty_print(std::ostream &stream) const override#

Pretty prints the Conv{1,2,3}d module into the given stream.

Public Members

detail::ConvNdOptions<D> options#

The options with which this Module was constructed.

Tensor weight#

The learned kernel (or “weight”).

Tensor bias#

The learned bias. Only defined if the bias option was true.

Protected Attributes

std::vector<int64_t> _reversed_padding_repeated_twice#