ailayer_template.h File Reference

[DEPRECATED] This file acts as a reference for new layer structures. Some of the shown functions are mandatory, some are optional. More...

Go to the source code of this file.

Data Structures
struct	ailayer_template
	Template for general AIfES layers. More...

Typedefs
typedef struct ailayer_template	ailayer_template_t

Functions
ailayer_t *	ailayer_template (ailayer_template_t *layer, ailayer_t *input_layer)
	Initialize the given layer struct - mandatory More...
void	ailayer_template_forward (ailayer_t *self)
	Calculate the forward path for given layer - mandatory More...
void	ailayer_template_backward (ailayer_t *self)
	Calculate the backward (training) path for the given layer - depends on usability in training More...
void	ailayer_template_calc_result_shape (ailayer_t *self)
	Calculate the shape of the result tensor. More...
uint32_t	ailayer_template_sizeof_paramem (const ailayer_t *self)
	Calculate and return the parameter memory size needed for this layer - mandatory for hidden layers More...
void	ailayer_template_set_paramem (ailayer_t *self, void *memory_ptr)
	Distribute provided memory to the parameter pointers - mandatory for hidden layers More...
uint32_t	ailayer_template_sizeof_trainmem (const ailayer_t *self)
	Calculate and return the necessary memory size needed by this layer for training - mandatory for hidden layers More...
void	ailayer_template_set_trainmem (ailayer_t *self, void *memory_ptr)
	Distribute provided memory to the training gradients pointers - mandatory for hidden layers More...
void	ailayer_template_print_specs (const ailayer_t *self)
	Print the layer specification. More...

Variables
const aicore_layertype_t *	ailayer_template_type

Detailed Description

[DEPRECATED] This file acts as a reference for new layer structures. Some of the shown functions are mandatory, some are optional.

Version

2.2.0

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/.

Function Documentation

ailayer_template()

ailayer_t* ailayer_template	(	ailayer_template_t *	layer,
		ailayer_t *	input_layer
	)

Initialize the given layer struct - mandatory

Initializes and sets all parameters needed by the layer structure.

Parameters

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

Returns

Pointer to the (successfully) initialized layer structure.

ailayer_template_backward()

void ailayer_template_backward

(

ailayer_t *

self

)

Calculate the backward (training) path for the given layer - depends on usability in training

Parameters

*self

Layer to calculate the backward path for.

ailayer_template_calc_result_shape()

void ailayer_template_calc_result_shape

(

ailayer_t *

self

)

Calculate the shape of the result tensor.

Parameters

*self

Layer to calculate the resulting shape for.

ailayer_template_forward()

void ailayer_template_forward

(

ailayer_t *

self

)

Calculate the forward path for given layer - mandatory

Parameters

*self

Layer to calculate the forward path for.

ailayer_template_print_specs()

void ailayer_template_print_specs

(

const ailayer_t *

self

)

Print the layer specification.

Parameters

*self

The layer to print the specification for

ailayer_template_set_paramem()

void ailayer_template_set_paramem	(	ailayer_t *	self,
		void *	memory_ptr
	)

Distribute provided memory to the parameter pointers - mandatory for hidden layers

Parameters

*self	The layer to set the memory fields for.
*memory_ptr	Pointer to the buffer provided for the layer parameters.

ailayer_template_set_trainmem()

void ailayer_template_set_trainmem	(	ailayer_t *	self,
		void *	memory_ptr
	)

Distribute provided memory to the training gradients pointers - mandatory for hidden layers

Parameters

*self	The layer to set the memory fields for.
*memory_ptr	Pointer to the buffer provided for the layer gradients.

ailayer_template_sizeof_paramem()

uint32_t ailayer_template_sizeof_paramem

(

const ailayer_t *

self

)

Calculate and return the parameter memory size needed for this layer - mandatory for hidden layers

Parameters

*self

The layer to calculate the parameter memory size for

Returns

Calculated parameter memory size in bytes.

ailayer_template_sizeof_trainmem()

uint32_t ailayer_template_sizeof_trainmem

(

const ailayer_t *

self

)

Calculate and return the necessary memory size needed by this layer for training - mandatory for hidden layers

Parameters

*self

The layer to calculate the gradient memory size for.

Returns

Calculated gradient memory size in bytes.