FFmpeg coverage

GCC Code Coverage Report

Directory:	../../../ffmpeg/		Exec	Total	Coverage
File:	src/libavfilter/dnn/dnn_backend_native_layer_conv2d.c	Lines:	78	144	54.2 %
Date:	2021-04-14 23:45:22	Branches:	39	94	41.5 %


/*
 * Copyright (c) 2018 Sergey Lavrushkin
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "libavutil/avassert.h"
#include "libavutil/thread.h"
#include "libavutil/cpu.h"
#include "dnn_backend_native_layer_conv2d.h"

#define CLAMP_TO_EDGE(x, w) ((x) < 0 ? 0 : ((x) >= (w) ? (w - 1) : (x)))

//struct to pass parameters
typedef struct ThreadCommonParam{
    DnnOperand *operands;
    const int32_t *input_operand_indexes;
    int32_t output_operand_index;
    const void *parameters;
    NativeContext *ctx;
    float *output_data;
} ThreadCommonParam;

typedef struct ThreadParam{
    ThreadCommonParam *thread_common_param;
    int thread_start, thread_end;
#if HAVE_PTHREAD_CANCEL
    pthread_t thread;
#endif
} ThreadParam;

int ff_dnn_load_layer_conv2d(Layer *layer, AVIOContext *model_file_context, int file_size, int operands_num)
{
    ConvolutionalParams *conv_params;
    int kernel_size;
    int dnn_size = 0;
    conv_params = av_malloc(sizeof(*conv_params));
    if (!conv_params)
        return 0;

    conv_params->dilation = (int32_t)avio_rl32(model_file_context);
    conv_params->padding_method = (int32_t)avio_rl32(model_file_context);
    conv_params->activation = (int32_t)avio_rl32(model_file_context);
    conv_params->input_num = (int32_t)avio_rl32(model_file_context);
    conv_params->output_num = (int32_t)avio_rl32(model_file_context);
    conv_params->kernel_size = (int32_t)avio_rl32(model_file_context);
    conv_params->has_bias = (int32_t)avio_rl32(model_file_context);
    dnn_size += 28;

    kernel_size = conv_params->input_num * conv_params->output_num *
                      conv_params->kernel_size * conv_params->kernel_size;
    dnn_size += kernel_size * 4;
    if (conv_params->has_bias)
        dnn_size += conv_params->output_num * 4;

    if (dnn_size > file_size || conv_params->input_num <= 0 ||
        conv_params->output_num <= 0 || conv_params->kernel_size <= 0){
        av_freep(&conv_params);
        return 0;
    }

    conv_params->kernel = av_malloc_array(kernel_size, sizeof(*conv_params->kernel));
    if (!conv_params->kernel) {
        av_freep(&conv_params);
        return 0;
    }
    for (int i = 0; i < kernel_size; ++i) {
        conv_params->kernel[i] = av_int2float(avio_rl32(model_file_context));
    }

    conv_params->biases = NULL;
    if (conv_params->has_bias) {
        conv_params->biases = av_malloc_array(conv_params->output_num, sizeof(*conv_params->biases));
        if (!conv_params->biases){
            av_freep(&conv_params->kernel);
            av_freep(&conv_params);
            return 0;
        }
        for (int i = 0; i < conv_params->output_num; ++i){
            conv_params->biases[i] = av_int2float(avio_rl32(model_file_context));
        }
    }

    layer->params = conv_params;

    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
    dnn_size += 8;

    if (layer->input_operand_indexes[0] >= operands_num || layer->output_operand_index >= operands_num) {
        return 0;
    }

    return dnn_size;
}

static void * dnn_execute_layer_conv2d_thread(void *threadarg)
{
    //pass parameters
    ThreadParam *thread_param = threadarg;
    ThreadCommonParam *thread_common_param = thread_param->thread_common_param;
    DnnOperand *operands = thread_common_param->operands;
    int32_t input_operand_index = thread_common_param->input_operand_indexes[0];
    int height = operands[input_operand_index].dims[1];
    int width = operands[input_operand_index].dims[2];
    int channel = operands[input_operand_index].dims[3];
    const float *input = operands[input_operand_index].data;
    const ConvolutionalParams *conv_params = thread_common_param->parameters;

    int radius = conv_params->kernel_size >> 1;
    int src_linesize = width * conv_params->input_num;
    int filter_linesize = conv_params->kernel_size * conv_params->input_num;
    int filter_size = conv_params->kernel_size * filter_linesize;
    int pad_size = (conv_params->padding_method == VALID) ? (conv_params->kernel_size - 1) / 2 * conv_params->dilation : 0;

    float *output = thread_common_param->output_data;
    output += (conv_params->output_num) * (width - 2 * pad_size) * (thread_param->thread_start - pad_size);

    av_assert0(channel == conv_params->input_num);

    for (int y = thread_param->thread_start; y < thread_param->thread_end; ++y) {
        for (int x = pad_size; x < width - pad_size; ++x) {
            for (int n_filter = 0; n_filter < conv_params->output_num; ++n_filter) {
                if (conv_params->has_bias)
                    output[n_filter] = conv_params->biases[n_filter];
                else
                    output[n_filter] = 0.f;

                for (int ch = 0; ch < conv_params->input_num; ++ch) {
                    for (int kernel_y = 0; kernel_y < conv_params->kernel_size; ++kernel_y) {
                        for (int kernel_x = 0; kernel_x < conv_params->kernel_size; ++kernel_x) {
                            float input_pel;
                            if (conv_params->padding_method == SAME_CLAMP_TO_EDGE) {
                                int y_pos = CLAMP_TO_EDGE(y + (kernel_y - radius) * conv_params->dilation, height);
                                int x_pos = CLAMP_TO_EDGE(x + (kernel_x - radius) * conv_params->dilation, width);
                                input_pel = input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
                            } else {
                                int y_pos = y + (kernel_y - radius) * conv_params->dilation;
                                int x_pos = x + (kernel_x - radius) * conv_params->dilation;
                                input_pel = (x_pos < 0 || x_pos >= width || y_pos < 0 || y_pos >= height) ? 0.0 :
                                                   input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
                            }


                            output[n_filter] += input_pel * conv_params->kernel[n_filter * filter_size + kernel_y * filter_linesize +
                                                                                kernel_x * conv_params->input_num + ch];
                        }
                    }
                }
                switch (conv_params->activation){
                case RELU:
                    output[n_filter] = FFMAX(output[n_filter], 0.0);
                    break;
                case TANH:
                    output[n_filter] = 2.0f  / (1.0f + exp(-2.0f * output[n_filter])) - 1.0f;
                    break;
                case SIGMOID:
                    output[n_filter] = 1.0f / (1.0f + exp(-output[n_filter]));
                    break;
                case NONE:
                    break;
                case LEAKY_RELU:
                    output[n_filter] = FFMAX(output[n_filter], 0.0) + 0.2 * FFMIN(output[n_filter], 0.0);
                }
            }
            output += conv_params->output_num;
        }
    }
    return NULL;
}


int ff_dnn_execute_layer_conv2d(DnnOperand *operands, const int32_t *input_operand_indexes,
                                int32_t output_operand_index, const void *parameters, NativeContext *ctx)
{
#if HAVE_PTHREAD_CANCEL
    int thread_num = (ctx->options.conv2d_threads <= 0 || ctx->options.conv2d_threads > av_cpu_count())
        ? (av_cpu_count() + 1) : (ctx->options.conv2d_threads);
    int ret = DNN_SUCCESS, thread_stride;
    ThreadParam *thread_param;
#else
    ThreadParam thread_param = { 0 };
#endif
    ThreadCommonParam thread_common_param;
    const ConvolutionalParams *conv_params = parameters;
    int height = operands[input_operand_indexes[0]].dims[1];
    int width = operands[input_operand_indexes[0]].dims[2];
    int pad_size = (conv_params->padding_method == VALID) ? (conv_params->kernel_size - 1) / 2 * conv_params->dilation : 0;
    DnnOperand *output_operand = &operands[output_operand_index];
    void *tmp;

    output_operand->dims[0] = operands[input_operand_indexes[0]].dims[0];
    output_operand->dims[1] = height - pad_size * 2;
    output_operand->dims[2] = width - pad_size * 2;
    output_operand->dims[3] = conv_params->output_num;
    output_operand->data_type = operands[input_operand_indexes[0]].data_type;
    output_operand->length = ff_calculate_operand_data_length(output_operand);
    if (output_operand->length <= 0) {
        av_log(ctx, AV_LOG_ERROR, "The output data length overflow\n");
        return DNN_ERROR;
    }
    tmp = av_realloc(output_operand->data, output_operand->length);
    if (!tmp) {
        av_log(ctx, AV_LOG_ERROR, "Failed to reallocate memory for output\n");
        return DNN_ERROR;
    }
    output_operand->data = tmp;
    thread_common_param.output_data = output_operand->data;
    thread_common_param.operands = operands;
    thread_common_param.input_operand_indexes = input_operand_indexes;
    thread_common_param.output_operand_index = output_operand_index;
    thread_common_param.parameters = parameters;
    thread_common_param.ctx = ctx;

#if HAVE_PTHREAD_CANCEL
    thread_param = av_malloc_array(thread_num, sizeof(*thread_param));
    if (!thread_param)
        return DNN_ERROR;
    thread_stride = (height - pad_size * 2) / thread_num;
    //create threads
    for (int i = 0; i < thread_num; i++){
        thread_param[i].thread_common_param = &thread_common_param;
        thread_param[i].thread_start = thread_stride * i + pad_size;
        thread_param[i].thread_end = (i == thread_num - 1) ? (height - pad_size) : (thread_param[i].thread_start + thread_stride);
        if (pthread_create(&thread_param[i].thread, NULL,
                           dnn_execute_layer_conv2d_thread, &thread_param[i])) {
            thread_num = i;
            ret = DNN_ERROR;
            break;
        }
    }

    for (int i = 0; i < thread_num; i++){
        pthread_join(thread_param[i].thread, NULL);
    }

    //release memory
    av_freep(&thread_param);

    return ret;
#else
    thread_param.thread_common_param = &thread_common_param;
    thread_param.thread_start = pad_size;
    thread_param.thread_end = height - pad_size;
    dnn_execute_layer_conv2d_thread(&thread_param);

    return DNN_SUCCESS;
#endif
}


Generated by: GCOVR (Version 4.2)

Line	Branch	Exec	Source
1			/*
2			* Copyright (c) 2018 Sergey Lavrushkin
3			*
4			* This file is part of FFmpeg.
5			*
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.
10			*
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.
15			*
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
19			*/
20
21			#include "libavutil/avassert.h"
22			#include "libavutil/thread.h"
23			#include "libavutil/cpu.h"
24			#include "dnn_backend_native_layer_conv2d.h"
25
26			#define CLAMP_TO_EDGE(x, w) ((x) < 0 ? 0 : ((x) >= (w) ? (w - 1) : (x)))
27
28			//struct to pass parameters
29			typedef struct ThreadCommonParam{
30			DnnOperand *operands;
31			const int32_t *input_operand_indexes;
32			int32_t output_operand_index;
33			const void *parameters;
34			NativeContext *ctx;
35			float *output_data;
36			} ThreadCommonParam;
37
38			typedef struct ThreadParam{
39			ThreadCommonParam *thread_common_param;
40			int thread_start, thread_end;
41			#if HAVE_PTHREAD_CANCEL
42			pthread_t thread;
43			#endif
44			} ThreadParam;
45
46			int ff_dnn_load_layer_conv2d(Layer layer, AVIOContext model_file_context, int file_size, int operands_num)
47			{
48			ConvolutionalParams *conv_params;
49			int kernel_size;
50			int dnn_size = 0;
51			conv_params = av_malloc(sizeof(*conv_params));
52			if (!conv_params)
53			return 0;
54
55			conv_params->dilation = (int32_t)avio_rl32(model_file_context);
56			conv_params->padding_method = (int32_t)avio_rl32(model_file_context);
57			conv_params->activation = (int32_t)avio_rl32(model_file_context);
58			conv_params->input_num = (int32_t)avio_rl32(model_file_context);
59			conv_params->output_num = (int32_t)avio_rl32(model_file_context);
60			conv_params->kernel_size = (int32_t)avio_rl32(model_file_context);
61			conv_params->has_bias = (int32_t)avio_rl32(model_file_context);
62			dnn_size += 28;
63
64			kernel_size = conv_params->input_num * conv_params->output_num *
65			conv_params->kernel_size * conv_params->kernel_size;
66			dnn_size += kernel_size * 4;
67			if (conv_params->has_bias)
68			dnn_size += conv_params->output_num * 4;
69
70			if (dnn_size > file_size \|\| conv_params->input_num <= 0 \|\|
71			conv_params->output_num <= 0 \|\| conv_params->kernel_size <= 0){
72			av_freep(&conv_params);
73			return 0;
74			}
75
76			conv_params->kernel = av_malloc_array(kernel_size, sizeof(*conv_params->kernel));
77			if (!conv_params->kernel) {
78			av_freep(&conv_params);
79			return 0;
80			}
81			for (int i = 0; i < kernel_size; ++i) {
82			conv_params->kernel[i] = av_int2float(avio_rl32(model_file_context));
83			}
84
85			conv_params->biases = NULL;
86			if (conv_params->has_bias) {
87			conv_params->biases = av_malloc_array(conv_params->output_num, sizeof(*conv_params->biases));
88			if (!conv_params->biases){
89			av_freep(&conv_params->kernel);
90			av_freep(&conv_params);
91			return 0;
92			}
93			for (int i = 0; i < conv_params->output_num; ++i){
94			conv_params->biases[i] = av_int2float(avio_rl32(model_file_context));
95			}
96			}
97
98			layer->params = conv_params;
99
100			layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
101			layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
102			dnn_size += 8;
103
104			if (layer->input_operand_indexes[0] >= operands_num \|\| layer->output_operand_index >= operands_num) {
105			return 0;
106			}
107
108			return dnn_size;
109			}
110
111		2	static void * dnn_execute_layer_conv2d_thread(void *threadarg)
112			{
113			//pass parameters
114		2	ThreadParam *thread_param = threadarg;
115		2	ThreadCommonParam *thread_common_param = thread_param->thread_common_param;
116		2	DnnOperand *operands = thread_common_param->operands;
117		2	int32_t input_operand_index = thread_common_param->input_operand_indexes[0];
118		2	int height = operands[input_operand_index].dims[1];
119		2	int width = operands[input_operand_index].dims[2];
120		2	int channel = operands[input_operand_index].dims[3];
121		2	const float *input = operands[input_operand_index].data;
122		2	const ConvolutionalParams *conv_params = thread_common_param->parameters;
123
124		2	int radius = conv_params->kernel_size >> 1;
125		2	int src_linesize = width * conv_params->input_num;
126		2	int filter_linesize = conv_params->kernel_size * conv_params->input_num;
127		2	int filter_size = conv_params->kernel_size * filter_linesize;
128	✓✓	2	int pad_size = (conv_params->padding_method == VALID) ? (conv_params->kernel_size - 1) / 2 * conv_params->dilation : 0;
129
130		2	float *output = thread_common_param->output_data;
131		2	output += (conv_params->output_num) * (width - 2 * pad_size) * (thread_param->thread_start - pad_size);
132
133	✗✓	2	av_assert0(channel == conv_params->input_num);
134
135	✓✓	10	for (int y = thread_param->thread_start; y < thread_param->thread_end; ++y) {
136	✓✓	50	for (int x = pad_size; x < width - pad_size; ++x) {
137	✓✓	126	for (int n_filter = 0; n_filter < conv_params->output_num; ++n_filter) {
138	✓✗	84	if (conv_params->has_bias)
139		84	output[n_filter] = conv_params->biases[n_filter];
140			else
141			output[n_filter] = 0.f;
142
143	✓✓	336	for (int ch = 0; ch < conv_params->input_num; ++ch) {
144	✓✓	1008	for (int kernel_y = 0; kernel_y < conv_params->kernel_size; ++kernel_y) {
145	✓✓	3024	for (int kernel_x = 0; kernel_x < conv_params->kernel_size; ++kernel_x) {
146			float input_pel;
147	✗✓	2268	if (conv_params->padding_method == SAME_CLAMP_TO_EDGE) {
148			int y_pos = CLAMP_TO_EDGE(y + (kernel_y - radius) * conv_params->dilation, height);
149			int x_pos = CLAMP_TO_EDGE(x + (kernel_x - radius) * conv_params->dilation, width);
150			input_pel = input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
151			} else {
152		2268	int y_pos = y + (kernel_y - radius) * conv_params->dilation;
153		2268	int x_pos = x + (kernel_x - radius) * conv_params->dilation;
154	✓✓✓✓ ✓✓✓✓	3840	input_pel = (x_pos < 0 \|\| x_pos >= width \|\| y_pos < 0 \|\| y_pos >= height) ? 0.0 :
155		1572	input[y_pos * src_linesize + x_pos * conv_params->input_num + ch];
156			}
157
158
159		2268	output[n_filter] += input_pel * conv_params->kernel[n_filter * filter_size + kernel_y * filter_linesize +
160		2268	kernel_x * conv_params->input_num + ch];
161			}
162			}
163			}
164	✗✓✗✗ ✗✗	84	switch (conv_params->activation){
165			case RELU:
166			output[n_filter] = FFMAX(output[n_filter], 0.0);
167			break;
168		84	case TANH:
169		84	output[n_filter] = 2.0f / (1.0f + exp(-2.0f * output[n_filter])) - 1.0f;
170		84	break;
171			case SIGMOID:
172			output[n_filter] = 1.0f / (1.0f + exp(-output[n_filter]));
173			break;
174			case NONE:
175			break;
176			case LEAKY_RELU:
177			output[n_filter] = FFMAX(output[n_filter], 0.0) + 0.2 * FFMIN(output[n_filter], 0.0);
178			}
179		84	}
180		42	output += conv_params->output_num;
181			}
182			}
183		2	return NULL;
184			}
185
186
187		2	int ff_dnn_execute_layer_conv2d(DnnOperand operands, const int32_t input_operand_indexes,
188			int32_t output_operand_index, const void parameters, NativeContext ctx)
189			{
190			#if HAVE_PTHREAD_CANCEL
191	✗✓	2	int thread_num = (ctx->options.conv2d_threads <= 0 \|\| ctx->options.conv2d_threads > av_cpu_count())
192	✓✗	4	? (av_cpu_count() + 1) : (ctx->options.conv2d_threads);
193		2	int ret = DNN_SUCCESS, thread_stride;
194			ThreadParam *thread_param;
195			#else
196			ThreadParam thread_param = { 0 };
197			#endif
198			ThreadCommonParam thread_common_param;
199		2	const ConvolutionalParams *conv_params = parameters;
200		2	int height = operands[input_operand_indexes[0]].dims[1];
201		2	int width = operands[input_operand_indexes[0]].dims[2];
202	✓✓	2	int pad_size = (conv_params->padding_method == VALID) ? (conv_params->kernel_size - 1) / 2 * conv_params->dilation : 0;
203		2	DnnOperand *output_operand = &operands[output_operand_index];
204			void *tmp;
205
206		2	output_operand->dims[0] = operands[input_operand_indexes[0]].dims[0];
207		2	output_operand->dims[1] = height - pad_size * 2;
208		2	output_operand->dims[2] = width - pad_size * 2;
209		2	output_operand->dims[3] = conv_params->output_num;
210		2	output_operand->data_type = operands[input_operand_indexes[0]].data_type;
211		2	output_operand->length = ff_calculate_operand_data_length(output_operand);
212	✗✓	2	if (output_operand->length <= 0) {
213			av_log(ctx, AV_LOG_ERROR, "The output data length overflow\n");
214			return DNN_ERROR;
215			}
216		2	tmp = av_realloc(output_operand->data, output_operand->length);
217	✗✓	2	if (!tmp) {
218			av_log(ctx, AV_LOG_ERROR, "Failed to reallocate memory for output\n");
219			return DNN_ERROR;
220			}
221		2	output_operand->data = tmp;
222		2	thread_common_param.output_data = output_operand->data;
223		2	thread_common_param.operands = operands;
224		2	thread_common_param.input_operand_indexes = input_operand_indexes;
225		2	thread_common_param.output_operand_index = output_operand_index;
226		2	thread_common_param.parameters = parameters;
227		2	thread_common_param.ctx = ctx;
228
229			#if HAVE_PTHREAD_CANCEL
230		2	thread_param = av_malloc_array(thread_num, sizeof(*thread_param));
231	✗✓	2	if (!thread_param)
232			return DNN_ERROR;
233		2	thread_stride = (height - pad_size * 2) / thread_num;
234			//create threads
235	✓✓	4	for (int i = 0; i < thread_num; i++){
236		2	thread_param[i].thread_common_param = &thread_common_param;
237		2	thread_param[i].thread_start = thread_stride * i + pad_size;
238	✓✗	2	thread_param[i].thread_end = (i == thread_num - 1) ? (height - pad_size) : (thread_param[i].thread_start + thread_stride);
239	✗✓	2	if (pthread_create(&thread_param[i].thread, NULL,
240		2	dnn_execute_layer_conv2d_thread, &thread_param[i])) {
241			thread_num = i;
242			ret = DNN_ERROR;
243			break;
244			}
245			}
246
247	✓✓	4	for (int i = 0; i < thread_num; i++){
248		2	pthread_join(thread_param[i].thread, NULL);
249			}
250
251			//release memory
252		2	av_freep(&thread_param);
253
254		2	return ret;
255			#else
256			thread_param.thread_common_param = &thread_common_param;
257			thread_param.thread_start = pad_size;
258			thread_param.thread_end = height - pad_size;
259			dnn_execute_layer_conv2d_thread(&thread_param);
260
261			return DNN_SUCCESS;
262			#endif
263			}