Internal layer activation data policy. More...

Inheritance diagram for dcnnsol::image_data_policy< SP, PP >:

Public Types
using	values_t = tagged::permute_tensor_class< typename PP::data, float, height_tag, width_tag, channel_tag, batch_tag>
	4-dimensional tensor type carrying activations

using	co_values_t = tagged::permute_tensor_class< tagged::co_list< typename PP::data>, float, tagged::co<height_tag>, tagged::co<width_tag>, tagged::co<channel_tag>, tagged::co<batch_tag>>
	4-dimensional tensor type carrying loss derivatives wrt. activations

Static Public Attributes
static constexpr auto	hr = SP::hr
	Image height range, statically sized.

static constexpr auto	wr = SP::wr
	Image width range, statically sized.

static constexpr auto	cr = SP::cr
	Channel index range, statically sized.

Detailed Description

template<typename SP, is_policy PP>
struct dcnnsol::image_data_policy< SP, PP >

Internal layer activation data policy.

Template Parameters

SP	Sizing policy
PP	Permutation policy

Member Typedef Documentation

template<typename SP, is_policy PP>

4-dimensional tensor type carrying loss derivatives wrt. activations

Same as values_t but indexes co-tagged according to tensor theory.

Layout: Indexes nested according to permutation policy (dcnnsol::permutation_policy::data)

template<typename SP, is_policy PP>

using dcnnasgn::image_data_policy< SP, PP >::values_t = tagged::permute_tensor_class< typename PP::data, float, height_tag, width_tag, channel_tag, batch_tag>

4-dimensional tensor type carrying activations

Layout: Indexes nested according to permutation policy (dcnnsol::permutation_policy::data)

The documentation for this struct was generated from the following file: