2 * Copyright (c) 2018 Sergey Lavrushkin
4 * This file is part of FFmpeg.
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
23 * DNN inference engine interface.
26 #ifndef AVFILTER_DNN_INTERFACE_H
27 #define AVFILTER_DNN_INTERFACE_H
30 #include "libavutil/frame.h"
33 #define DNN_GENERIC_ERROR FFERRTAG('D','N','N','!')
35 typedef enum {DNN_NATIVE, DNN_TF, DNN_OV} DNNBackendType;
37 typedef enum {DNN_FLOAT = 1, DNN_UINT8 = 4} DNNDataType;
46 DAST_FAIL, // something wrong
47 DAST_EMPTY_QUEUE, // no more inference result to get
48 DAST_NOT_READY, // all queued inferences are not finished
49 DAST_SUCCESS // got a result frame successfully
54 DFT_PROCESS_FRAME, // process the whole frame
55 DFT_ANALYTICS_DETECT, // detect from the whole frame
56 DFT_ANALYTICS_CLASSIFY, // classify for each bounding box
59 typedef struct DNNData{
61 int width, height, channels;
62 // dt and order together decide the color format
67 typedef struct DNNExecBaseParams {
68 const char *input_name;
69 const char **output_names;
75 typedef struct DNNExecClassificationParams {
76 DNNExecBaseParams base;
78 } DNNExecClassificationParams;
80 typedef int (*FramePrePostProc)(AVFrame *frame, DNNData *model, AVFilterContext *filter_ctx);
81 typedef int (*DetectPostProc)(AVFrame *frame, DNNData *output, uint32_t nb, AVFilterContext *filter_ctx);
82 typedef int (*ClassifyPostProc)(AVFrame *frame, DNNData *output, uint32_t bbox_index, AVFilterContext *filter_ctx);
84 typedef struct DNNModel{
85 // Stores model that can be different for different backends.
87 // Stores options when the model is executed by the backend
89 // Stores FilterContext used for the interaction between AVFrame and DNNData
90 AVFilterContext *filter_ctx;
91 // Stores function type of the model
92 DNNFunctionType func_type;
93 // Gets model input information
94 // Just reuse struct DNNData here, actually the DNNData.data field is not needed.
95 int (*get_input)(void *model, DNNData *input, const char *input_name);
96 // Gets model output width/height with given input w/h
97 int (*get_output)(void *model, const char *input_name, int input_width, int input_height,
98 const char *output_name, int *output_width, int *output_height);
99 // set the pre process to transfer data from AVFrame to DNNData
100 // the default implementation within DNN is used if it is not provided by the filter
101 FramePrePostProc frame_pre_proc;
102 // set the post process to transfer data from DNNData to AVFrame
103 // the default implementation within DNN is used if it is not provided by the filter
104 FramePrePostProc frame_post_proc;
105 // set the post process to interpret detect result from DNNData
106 DetectPostProc detect_post_proc;
107 // set the post process to interpret classify result from DNNData
108 ClassifyPostProc classify_post_proc;
111 // Stores pointers to functions for loading, executing, freeing DNN models for one of the backends.
112 typedef struct DNNModule{
113 // Loads model and parameters from given file. Returns NULL if it is not possible.
114 DNNModel *(*load_model)(const char *model_filename, DNNFunctionType func_type, const char *options, AVFilterContext *filter_ctx);
115 // Executes model with specified input and output. Returns the error code otherwise.
116 int (*execute_model)(const DNNModel *model, DNNExecBaseParams *exec_params);
117 // Retrieve inference result.
118 DNNAsyncStatusType (*get_result)(const DNNModel *model, AVFrame **in, AVFrame **out);
119 // Flush all the pending tasks.
120 int (*flush)(const DNNModel *model);
121 // Frees memory allocated for model.
122 void (*free_model)(DNNModel **model);
125 // Initializes DNNModule depending on chosen backend.
126 DNNModule *ff_get_dnn_module(DNNBackendType backend_type);