yolo_layer.cpp File Reference

Include dependency graph for yolo_layer.cpp:

Functions
void	backward_yolo_layer (Darknet::Layer &l, Darknet::NetworkState state)
void	correct_yolo_boxes (Darknet::Detection *dets, int n, int w, int h, int netw, int neth, int relative, int letter)
void	forward_yolo_layer (Darknet::Layer &l, Darknet::NetworkState state)
int	get_yolo_detections (const Darknet::Layer &l, int w, int h, int netw, int neth, float thresh, int *map, int relative, Darknet::Detection *dets, int letter)
int	get_yolo_detections_batch (const Darknet::Layer &l, int w, int h, int netw, int neth, float thresh, int *map, int relative, Darknet::Detection *dets, int letter, int batch)
int	get_yolo_detections_v3 (Darknet::Network *net, int w, int h, int netw, int neth, float thresh, int *map, int relative, Darknet::Detection *dets, int letter, Darknet::Output_Object_Cache &cache)
	Convert everything we've detected into bounding boxes and confidence scores for each class.
Darknet::Layer	make_yolo_layer (int batch, int w, int h, int n, int total, int *mask, int classes, int max_boxes)
void	process_batch (void *ptr)
void	resize_yolo_layer (Darknet::Layer *l, int w, int h)
int	yolo_num_detections (const Darknet::Layer &l, float thresh)
int	yolo_num_detections_batch (const Darknet::Layer &l, float thresh, int batch)
int	yolo_num_detections_v3 (Darknet::Network *net, const int index, const float thresh, Darknet::Output_Object_Cache &cache)
	Count the number of objects found in the current image.

Function Documentation

backward_yolo_layer()

void backward_yolo_layer	(	Darknet::Layer &	l,
		Darknet::NetworkState	state
	)

Here is the call graph for this function:

Here is the caller graph for this function:

correct_yolo_boxes()

void correct_yolo_boxes	(	Darknet::Detection *	dets,
		int	n,
		int	w,
		int	h,
		int	netw,
		int	neth,
		int	relative,
		int	letter
	)

Here is the caller graph for this function:

forward_yolo_layer()

void forward_yolo_layer	(	Darknet::Layer &	l,
		Darknet::NetworkState	state
	)

Here is the call graph for this function:

Here is the caller graph for this function:

get_yolo_detections()

int get_yolo_detections	(	const Darknet::Layer &	l,
		int	w,
		int	h,
		int	netw,
		int	neth,
		float	thresh,
		int *	map,
		int	relative,
		Darknet::Detection *	dets,
		int	letter
	)

Here is the call graph for this function:

Here is the caller graph for this function:

get_yolo_detections_batch()

int get_yolo_detections_batch	(	const Darknet::Layer &	l,
		int	w,
		int	h,
		int	netw,
		int	neth,
		float	thresh,
		int *	map,
		int	relative,
		Darknet::Detection *	dets,
		int	letter,
		int	batch
	)

Here is the call graph for this function:

Here is the caller graph for this function:

get_yolo_detections_v3()

int get_yolo_detections_v3	(	Darknet::Network *	net,
		int	w,
		int	h,
		int	netw,
		int	neth,
		float	thresh,
		int *	map,
		int	relative,
		Darknet::Detection *	dets,
		int	letter,
		Darknet::Output_Object_Cache &	cache
	)

Convert everything we've detected into bounding boxes and confidence scores for each class.

Todo:

V3 what is this and where does it get used?

Here is the call graph for this function:

Here is the caller graph for this function:

make_yolo_layer()

Darknet::Layer make_yolo_layer	(	int	batch,
		int	w,
		int	h,
		int	n,
		int	total,
		int *	mask,
		int	classes,
		int	max_boxes
	)

Here is the call graph for this function:

Here is the caller graph for this function:

process_batch()

void process_batch

(

void *

ptr

)

Here is the call graph for this function:

Here is the caller graph for this function:

resize_yolo_layer()

void resize_yolo_layer	(	Darknet::Layer *	l,
		int	w,
		int	h
	)

Here is the caller graph for this function:

yolo_num_detections()

int yolo_num_detections	(	const Darknet::Layer &	l,
		float	thresh
	)

Todo:

V3 JAZZ 2024-06-02: Why does "omp parallel" not work like I expect?

Here is the caller graph for this function:

yolo_num_detections_batch()

int yolo_num_detections_batch	(	const Darknet::Layer &	l,
		float	thresh,
		int	batch
	)

Here is the caller graph for this function:

yolo_num_detections_v3()

int yolo_num_detections_v3	(	Darknet::Network *	net,
		const int	index,
		const float	thresh,
		Darknet::Output_Object_Cache &	cache
	)

Count the number of objects found in the current image.

Only looks at the YOLO layer at index within the network. Starting with V3 JAZZ, this will also populate (appends, does not clear!) the object cache with the location of all objects found so we don't have to look through the entire YOLO output again when creating the boxes.

Here is the caller graph for this function: