dnn_backend_common.h File Reference

DNN common functions different backends. More...

#include "queue.h"
#include "safe_queue.h"
#include "../dnn_interface.h"
#include "libavutil/thread.h"

Go to the source code of this file.

Data Structures
struct	TaskItem
struct	LastLevelTaskItem
struct	DNNAsyncExecModule
	Common Async Execution Mechanism for the DNN Backends. More...

Macros
#define	DNN_DEFINE_CLASS_EXT(name, desc, options)
#define	DNN_DEFINE_CLASS(fname)

Functions
int	ff_check_exec_params (void *ctx, DNNBackendType backend, DNNFunctionType func_type, DNNExecBaseParams *exec_params)
int	ff_dnn_fill_task (TaskItem *task, DNNExecBaseParams *exec_params, void *backend_model, int async, int do_ioproc)
	Fill the Task for Backend Execution.
int	ff_dnn_async_module_cleanup (DNNAsyncExecModule *async_module)
	Join the Async Execution thread and set module pointers to NULL.
void	ff_dnn_wait_requests (SafeQueue *request_queue, int nireq)
	Wait for all inference requests to complete before teardown.
int	ff_dnn_start_inference_async (void *ctx, DNNAsyncExecModule *async_module)
	Start asynchronous inference routine for the TensorFlow model on a detached thread.
DNNAsyncStatusType	ff_dnn_get_result_common (Queue *task_queue, AVFrame **in, AVFrame **out)
	Extract input and output frame from the Task Queue after asynchronous inference.
int	ff_dnn_fill_gettingoutput_task (TaskItem *task, DNNExecBaseParams *exec_params, void *backend_model, int input_height, int input_width, void *ctx)
	Allocate input and output frames and fill the Task with execution parameters.

Detailed Description

DNN common functions different backends.

Definition in file dnn_backend_common.h.

Macro Definition Documentation

DNN_DEFINE_CLASS_EXT

#define DNN_DEFINE_CLASS_EXT	(		name,
			desc,
			options )

Value:

    {                                           \
        .class_name = desc,                     \
        .item_name  = av_default_item_name,     \
        .option     = options,                  \
        .version    = LIBAVUTIL_VERSION_INT,    \
        .category   = AV_CLASS_CATEGORY_FILTER, \
    }

Definition at line 32 of file dnn_backend_common.h.

DNN_DEFINE_CLASS

#define DNN_DEFINE_CLASS

(

fname

)

Value:

    DNN_DEFINE_CLASS_EXT(fname, #fname, fname##_options)

Definition at line 40 of file dnn_backend_common.h.

Function Documentation

ff_check_exec_params()

int ff_check_exec_params	(	void *	ctx,
		DNNBackendType	backend,
		DNNFunctionType	func_type,
		DNNExecBaseParams *	exec_params )

Definition at line 30 of file dnn_backend_common.c.

Referenced by dnn_execute_model_onnx(), dnn_execute_model_ov(), dnn_execute_model_tf(), and dnn_execute_model_th().

ff_dnn_fill_task()

int ff_dnn_fill_task	(	TaskItem *	task,
		DNNExecBaseParams *	exec_params,
		void *	backend_model,
		int	async,
		int	do_ioproc )

Fill the Task for Backend Execution.

It should be called after checking execution parameters using ff_check_exec_params.

Parameters

task	pointer to the allocated task
exec_param	pointer to execution parameters
backend_model	void pointer to the backend model
async	flag for async execution. Must be 0 or 1
do_ioproc	flag for IO processing. Must be 0 or 1

Returns

0 if successful or error code otherwise.

Definition at line 50 of file dnn_backend_common.c.

Referenced by dnn_execute_model_onnx(), dnn_execute_model_ov(), dnn_execute_model_tf(), dnn_execute_model_th(), and ff_dnn_fill_gettingoutput_task().

ff_dnn_async_module_cleanup()

int ff_dnn_async_module_cleanup

(

DNNAsyncExecModule *

async_module

)

Join the Async Execution thread and set module pointers to NULL.

Parameters

async_module

pointer to DNNAsyncExecModule module

Returns

0 if successful or error code otherwise.

Definition at line 86 of file dnn_backend_common.c.

Referenced by destroy_request_item(), destroy_request_item(), and destroy_request_item().

ff_dnn_wait_requests()

void ff_dnn_wait_requests	(	SafeQueue *	request_queue,
		int	nireq )

Wait for all inference requests to complete before teardown.

This blocks the calling thread until all request items have been returned to the request_queue by the async inference threads.

Parameters

request_queue	pointer to the SafeQueue holding request items
nireq	total number of allocated request items

Definition at line 106 of file dnn_backend_common.c.

Referenced by dnn_free_model_onnx(), dnn_free_model_ov(), dnn_free_model_tf(), and dnn_free_model_th().

ff_dnn_start_inference_async()

int ff_dnn_start_inference_async	(	void *	ctx,
		DNNAsyncExecModule *	async_module )

Start asynchronous inference routine for the TensorFlow model on a detached thread.

It calls the completion callback after the inference completes. Completion callback and inference function must be set before calling this function.

Parameters

ctx	pointer to the backend context
async_module	pointer to DNNAsyncExecModule module

Returns

0 on the start of async inference or error code otherwise.

Definition at line 114 of file dnn_backend_common.c.

Referenced by dnn_flush_tf(), execute_model_tf(), and execute_model_th().

ff_dnn_get_result_common()

DNNAsyncStatusType ff_dnn_get_result_common	(	Queue *	task_queue,
		AVFrame **	in,
		AVFrame **	out )

Extract input and output frame from the Task Queue after asynchronous inference.

Parameters

task_queue	pointer to the task queue of the backend
in	double pointer to the input frame
out	double pointer to the output frame

Return values

DAST_EMPTY_QUEUE	if task queue is empty
DAST_NOT_READY	if inference not completed yet.
DAST_SUCCESS	if result successfully extracted

Definition at line 142 of file dnn_backend_common.c.

Referenced by dnn_get_result_onnx(), dnn_get_result_ov(), dnn_get_result_tf(), and dnn_get_result_th().

ff_dnn_fill_gettingoutput_task()

int ff_dnn_fill_gettingoutput_task	(	TaskItem *	task,
		DNNExecBaseParams *	exec_params,
		void *	backend_model,
		int	input_height,
		int	input_width,
		void *	ctx )

Allocate input and output frames and fill the Task with execution parameters.

Parameters

task	pointer to the allocated task
exec_params	pointer to execution parameters
backend_model	void pointer to the backend model
input_height	height of input frame
input_width	width of input frame
ctx	pointer to the backend context

Returns

0 if successful or error code otherwise.

Definition at line 162 of file dnn_backend_common.c.

Referenced by get_output_onnx(), get_output_ov(), get_output_tf(), and get_output_th().