mshadow::expr::UnPoolingExp< Reducer, Device > Struct Template Reference

unpooling expr reverse operation of pooling, used to pass gradient back More...

#include <tensor_expr_ext.h>

Inheritance diagram for mshadow::expr::UnPoolingExp< Reducer, Device >:

Public Member Functions
	UnPoolingExp (const Tensor< Device, 4 > &data_src, const Tensor< Device, 4 > &data_pooled, const Tensor< Device, 4 > &grad_pooled, index_t ksize, index_t kstride)
	constructor
Public Member Functions inherited from mshadow::expr::MakeTensorExp< UnPoolingExp< Reducer, Device >, Tensor< Device, 4 >, 4 >
const UnPoolingExp< Reducer, Device > &	real_self (void) const
	true self of subtype
Public Member Functions inherited from mshadow::expr::Exp< MakeTensorExp< UnPoolingExp< Reducer, Device >, Tensor< Device, 4 >, dim >, type::kMapper >
const MakeTensorExp < UnPoolingExp< Reducer, Device >, Tensor< Device, 4 > , dim > &	self (void) const
MakeTensorExp< UnPoolingExp < Reducer, Device >, Tensor < Device, 4 >, dim > &	refself (void)

Public Attributes
const Tensor< Device, 4 > &	data_src_
	source input, corresponds to src in pooling
const Tensor< Device, 4 > &	data_pooled_
	result of pooled data, corresponds to result of pooling
const Tensor< Device, 4 > &	grad_pooled_
	gradient data of pooled part, to be propgate down
index_t	ksize_
	kernel size
index_t	kstride_
	kernel stride
Public Attributes inherited from mshadow::expr::MakeTensorExp< UnPoolingExp< Reducer, Device >, Tensor< Device, 4 >, 4 >
Shape< dim >	shape_
	the shape of this expression

Detailed Description

template<typename Reducer, typename Device>
struct mshadow::expr::UnPoolingExp< Reducer, Device >

unpooling expr reverse operation of pooling, used to pass gradient back

Template Parameters

Reducer	specifies reduction operation during pooling
Device	which device it lies

---

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

• /home/wangwei/program/asf/release-0.1/apache-singa-incubating-0.1.0-RC1/include/mshadow/tensor_expr_ext.h