Shortcuts

Template Struct MaxPoolOptions

Page Contents

Struct Documentation

template<size_t D>
struct torch::nn::MaxPoolOptions

Options for a D-dimensional maxpool module.

Public Functions

MaxPoolOptions(ExpandingArray<D> kernel_size)
auto kernel_size(const ExpandingArray<D> &new_kernel_size) -> decltype(*this)

the size of the window to take a max over

auto kernel_size(ExpandingArray<D> &&new_kernel_size) -> decltype(*this)
const ExpandingArray<D> &kernel_size() const noexcept
ExpandingArray<D> &kernel_size() noexcept
auto stride(const ExpandingArray<D> &new_stride) -> decltype(*this)

the stride of the window. Default value is `kernel_size

auto stride(ExpandingArray<D> &&new_stride) -> decltype(*this)
const ExpandingArray<D> &stride() const noexcept
ExpandingArray<D> &stride() noexcept
auto padding(const ExpandingArray<D> &new_padding) -> decltype(*this)

implicit zero padding to be added on both sides

auto padding(ExpandingArray<D> &&new_padding) -> decltype(*this)
const ExpandingArray<D> &padding() const noexcept
ExpandingArray<D> &padding() noexcept
auto dilation(const ExpandingArray<D> &new_dilation) -> decltype(*this)

a parameter that controls the stride of elements in the window

auto dilation(ExpandingArray<D> &&new_dilation) -> decltype(*this)
const ExpandingArray<D> &dilation() const noexcept
ExpandingArray<D> &dilation() noexcept
auto ceil_mode(const bool &new_ceil_mode) -> decltype(*this)

when True, will use ceil instead of floor to compute the output shape

auto ceil_mode(bool &&new_ceil_mode) -> decltype(*this)
const bool &ceil_mode() const noexcept
bool &ceil_mode() noexcept

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources