ailayer_reshape.h File Reference

Base layer implementation of the Reshape layer. More...

Go to the source code of this file.

Data Structures
struct	ailayer_reshape
	General layer structure. More...
struct	ailayer_flatten
	Structure of the Flatten layer, based on the reshape layer . More...

Typedefs
typedef struct ailayer_reshape	ailayer_reshape_t
typedef struct ailayer_flatten	ailayer_flatten_t

Functions
ailayer_t *	ailayer_reshape (ailayer_reshape_t *layer, ailayer_t *input_layer)
	Initialize and connect the given Reshape layer. More...
void	ailayer_reshape_forward (ailayer_t *self)
	Calculate the forward pass for given Reshape layer. More...
void	ailayer_reshape_backward (ailayer_t *self)
	Calculate the backward pass for given Reshape layer. More...
void	ailayer_reshape_calc_result_shape (ailayer_t *self)
	Calculate the shape of the result tensor (ailayer.result) More...
void	ailayer_reshape_print_specs (const ailayer_t *self)
	Print the layer specification. More...

Variables
const aicore_layertype_t *	ailayer_reshape_type
	Reshape layer type. More...

Detailed Description

Base layer implementation of the Reshape 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_reshape_default.h) or set the required math functions on your own.

The Reshape layer (also used as Flatten layer) is used to reshape a tensor during the forward pass without changing any data. This can be useful for example to connect a Dense layer to a convolutional layer by using the Flatten layer.

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

Function Documentation

ailayer_reshape()

ailayer_t* ailayer_reshape	(	ailayer_reshape_t *	layer,
		ailayer_t *	input_layer
	)

Initialize and connect the given Reshape layer.

This function represents the "constructor" of the abstract Reshape 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_reshape_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_reshape.base)

ailayer_reshape_backward()

void ailayer_reshape_backward

(

ailayer_t *

self

)

Calculate the backward pass for given Reshape 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.

When no reshape function is given (ailayer_reshape.reshape = 0), this function does nothing (as the target shape is already defined).

Used math functions (optional; if set to zero, only the shape is changed):

• ailayer_reshape.reshape

Parameters

*self

Layer to calculate the backward path for.

ailayer_reshape_calc_result_shape()

void ailayer_reshape_calc_result_shape

(

ailayer_t *

self

)

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

Implementation of ailayer.calc_result_shape.

Resulting shape is given by ailayer_reshape.output_shape and optionally the inferred axis ailayer_reshape.infer_axis.

Parameters

*self

Layer to calculate the resulting shape for.

ailayer_reshape_forward()

void ailayer_reshape_forward

(

ailayer_t *

self

)

Calculate the forward pass for given Reshape 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.

When no reshape function is given (ailayer_reshape.reshape = 0), this function does nothing (as the target shape is already defined).

Used math functions (optional; if set to zero, only the shape is changed):

• ailayer_reshape.reshape

Parameters

*self

Layer to calculate the forward path for.

ailayer_reshape_print_specs()

void ailayer_reshape_print_specs

(

const ailayer_t *

self

)

Print the layer specification.

Parameters

*self

The layer to print the specification for

Variable Documentation

ailayer_reshape_type

const aicore_layertype_t* ailayer_reshape_type

extern

Reshape 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.