ailayer_maxpool2d.h File Reference

Base layer implementation of the MaxPool2D layer. More...

Go to the source code of this file.

Data Structures
struct	ailayer_maxpool2d
	General layer structure. More...

Typedefs
typedef struct ailayer_maxpool2d	ailayer_maxpool2d_t

Functions
ailayer_t *	ailayer_maxpool2d (ailayer_maxpool2d_t *layer, ailayer_t *input_layer)
	Initialize and connect the given MaxPool2D layer. More...
void	ailayer_maxpool2d_forward (ailayer_t *self)
	Calculate the forward pass for given MaxPool2D layer. More...
void	ailayer_maxpool2d_backward (ailayer_t *self)
	Calculate the backward pass for given MaxPool2D layer. More...
void	ailayer_maxpool2d_calc_result_shape (ailayer_t *self)
	Calculate the shape of the result tensor (ailayer.result) More...
uint32_t	ailayer_maxpool2d_sizeof_trainmem (const ailayer_t *self)
	Calculate and return the memory size needed by this layer for training. More...
void	ailayer_maxpool2d_set_trainmem (ailayer_t *self, void *memory_ptr)
	Distribute provided memory to the gradients pointers. More...
void	ailayer_maxpool2d_print_specs (const ailayer_t *self)
	Print the layer specification. More...

Variables
const aicore_layertype_t *	ailayer_maxpool2d_type
	MaxPool2D layer type. More...

Detailed Description

Base layer implementation of the MaxPool2D layer.

Version

2.2.0

Date

20.10.2020

Copyright

Copyright (C) 2020-2023 Fraunhofer Institute for Microelectronic Circuits and Systems. All rights reserved.

AIfES is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License along with this program. If not, see https://www.gnu.org/licenses/.

This is an "abstract" data-type independent implementation. To use the layer use one of the provided implementations for a specific hardware and data-type (for example from ailayer_maxpool2d_default.h) or set the required math functions on your own.

The MaxPool2D layer (or 2D Max-Pooling layer) is used to compress the size of activations, by only taking the maximum activation values within a small window (pooling kernel).

When the channel axis equals 1 (channels first), the shapes of input and output are \( [N,C,H_{in},W_{in}] \) and \( [N,C,H_{out},W_{out}] \), respectively.

When the channel axis equals -1 or 3 (channels last), the shapes of input and output are \( [N,H_{in},W_{in},C] \) and \( [N,H_{out},W_{out},C] \), respectively.

N is the batch size.

The results of the forward pass of this layer are written to the result tensor of the base ailayer_t struct.

Function Documentation

ailayer_maxpool2d()

ailayer_t* ailayer_maxpool2d	(	ailayer_maxpool2d_t *	layer,
		ailayer_t *	input_layer
	)

Initialize and connect the given MaxPool2D layer.

This function represents the "constructor" of the abstract MaxPool2D layer. It initializes the layer structure and connects it to the previous layer.
This function is not intended to call it directly. Instead use one of the data type specific implementations (like for example ailayer_maxpool2d_f32_default()).

Parameters

*layer	The layer to initialize.
*input_layer	The previous layer that provides the inputs to the layer.

Returns

Pointer to the (successfully) initialized general layer structure (ailayer_maxpool2d.base)

ailayer_maxpool2d_backward()

void ailayer_maxpool2d_backward

(

ailayer_t *

self

)

Calculate the backward pass for given MaxPool2D layer.

Implementation of ailayer.backward.

It uses the deltas tensor of the next layer as input and writes the result of the backward pass to the deltas tensor (ailayer.deltas) of the given layer.

Used math functions:

• ailayer_maxpool2d.maxpool2d_bwd

Parameters

*self

Layer to calculate the backward path for.

ailayer_maxpool2d_calc_result_shape()

void ailayer_maxpool2d_calc_result_shape

(

ailayer_t *

self

)

Calculate the shape of the result tensor (ailayer.result)

Implementation of ailayer.calc_result_shape.

Resulting shape is \( [N,C,H_{out},W_{out}] \) (channels first) or \( [N,H_{out},W_{out},C] \) (channels last) with

\[ H_{out} = floor \left( \frac{H_{in} + 2 * P_h - H_{pool}}{S_h} \right) + 1 \]

\[ W_{out} = floor \left( \frac{W_{in} + 2 * P_w - W_{pool}}{S_w} \right) + 1 \]

Parameters

*self

Layer to calculate the resulting shape for.

ailayer_maxpool2d_forward()

void ailayer_maxpool2d_forward

(

ailayer_t *

self

)

Calculate the forward pass for given MaxPool2D layer.

Implementation of ailayer.forward.

It uses the result tensor of the previous layer as input and writes the result of the forward pass to the result tensor (ailayer.result) of the given layer.

Used math functions:

• ailayer_maxpool2d.maxpool2d_fwd

Parameters

*self

Layer to calculate the forward path for.

ailayer_maxpool2d_print_specs()

void ailayer_maxpool2d_print_specs

(

const ailayer_t *

self

)

Print the layer specification.

Parameters

*self

The layer to print the specification for

ailayer_maxpool2d_set_trainmem()

void ailayer_maxpool2d_set_trainmem	(	ailayer_t *	self,
		void *	memory_ptr
	)

Distribute provided memory to the gradients pointers.

Implementation of ailayer.set_trainmem.

The required memory size can be calculated with ailayer_maxpool2d_sizeof_trainmem().

Parameters

*self	The layer to set the memory fields for.
*memory_ptr	The memory that can be used for the gradients

ailayer_maxpool2d_sizeof_trainmem()

uint32_t ailayer_maxpool2d_sizeof_trainmem

(

const ailayer_t *

self

)

Calculate and return the memory size needed by this layer for training.

Implementation of ailayer.sizeof_trainmem.

The memory size is calculated for storage of the max_locations.

Parameters

*self

The layer to calculate the gradient memory size for.

Returns

Calculated gradient memory size in bytes.

Variable Documentation

ailayer_maxpool2d_type

const aicore_layertype_t* ailayer_maxpool2d_type

extern

MaxPool2D layer type.

Defines the type of the layer (for example for type checks and debug prints). See aicore_layertype for more information about the layer type.