GCC Code Coverage Report
Directory: ../../../ffmpeg/ Exec Total Coverage
File: src/libavfilter/dnn/dnn_backend_native_layer_avgpool.c Lines: 54 77 70.1 %
Date: 2020-09-25 14:59:26 Branches: 23 42 54.8 %

Line Branch Exec Source
1
/*
2
 * Copyright (c) 2020
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
/**
22
 * @file
23
 * DNN native backend implementation.
24
 */
25
26
#include "libavutil/avassert.h"
27
#include "dnn_backend_native_layer_avgpool.h"
28
29
int dnn_load_layer_avg_pool(Layer *layer, AVIOContext *model_file_context, int file_size, int operands_num)
30
{
31
    AvgPoolParams *avgpool_params;
32
    int dnn_size = 0;
33
    avgpool_params = av_malloc(sizeof(*avgpool_params));
34
    if(!avgpool_params)
35
        return 0;
36
37
    avgpool_params->strides = (int32_t)avio_rl32(model_file_context);
38
    avgpool_params->padding_method = (int32_t)avio_rl32(model_file_context);
39
    avgpool_params->kernel_size = (int32_t)avio_rl32(model_file_context);
40
    dnn_size += 12;
41
42
    if (dnn_size > file_size || avgpool_params->kernel_size <= 0 || avgpool_params->strides <=0){
43
        av_freep(&avgpool_params);
44
        return 0;
45
    }
46
47
    layer->params = avgpool_params;
48
    layer->input_operand_indexes[0] = (int32_t)avio_rl32(model_file_context);
49
    layer->output_operand_index = (int32_t)avio_rl32(model_file_context);
50
    dnn_size += 8;
51
52
    if (layer->input_operand_indexes[0] >= operands_num || layer->output_operand_index >= operands_num) {
53
        return 0;
54
    }
55
    return dnn_size;
56
}
57
58
2
int dnn_execute_layer_avg_pool(DnnOperand *operands, const int32_t *input_operand_indexes,
59
                             int32_t output_operand_index, const void *parameters, NativeContext *ctx)
60
{
61
    float *output;
62
    int height_end, width_end, height_radius, width_radius, output_height, output_width, kernel_area;
63
2
    int32_t input_operand_index = input_operand_indexes[0];
64
2
    int number = operands[input_operand_index].dims[0];
65
2
    int height = operands[input_operand_index].dims[1];
66
2
    int width = operands[input_operand_index].dims[2];
67
2
    int channel = operands[input_operand_index].dims[3];
68
2
    const float *input = operands[input_operand_index].data;
69
2
    const AvgPoolParams *avgpool_params = (const AvgPoolParams *)parameters;
70
71
2
    int kernel_strides = avgpool_params->strides;
72
2
    int src_linesize = width * channel;
73
2
    DnnOperand *output_operand = &operands[output_operand_index];
74
75
    /**
76
     * When padding_method = SAME, the tensorflow will only padding the hald number of 0 pxiels
77
     * except the remainders.
78
     * Eg: assuming the input height = 1080, the strides = 11, so the remainders = 1080 % 11 = 2
79
     *     and if ksize = 5: it will fill (5 - 2) >> 1 = 1 line before the first line of input image,
80
     *                       and 5 - 2 - 1 = 2 lines after the last line of input image.
81
     *     and if ksize = 7: it will fill (7 - 2) >> 1 = 2 lines before the first line of input image,
82
     *                       and 7 - 2 - 2 = 3 lines after the last line of input image.
83
     */
84
2
    if (avgpool_params->padding_method == SAME) {
85
1
        height_end = height;
86
1
        width_end = width;
87
1
        height_radius = avgpool_params->kernel_size - ((height - 1) % kernel_strides + 1);
88
1
        width_radius = avgpool_params->kernel_size - ((width - 1) % kernel_strides + 1);
89
1
        height_radius = height_radius < 0 ? 0 : height_radius >> 1;
90
1
        width_radius = width_radius < 0 ? 0 : width_radius >> 1;
91
1
        output_height = ceil(height / (kernel_strides * 1.0));
92
1
        output_width = ceil(width / (kernel_strides * 1.0));
93
    } else {
94
1
        av_assert0(avgpool_params->padding_method == VALID);
95
1
        height_end = height - avgpool_params->kernel_size + 1;
96
1
        width_end = width - avgpool_params->kernel_size + 1;
97
1
        height_radius = 0;
98
1
        width_radius = 0;
99
1
        output_height = ceil((height - avgpool_params->kernel_size + 1) / (kernel_strides * 1.0));
100
1
        output_width = ceil((width - avgpool_params->kernel_size + 1) / (kernel_strides * 1.0));
101
    }
102
103
2
    output_operand->dims[0] = number;
104
2
    output_operand->dims[1] = output_height;
105
2
    output_operand->dims[2] = output_width;
106
    // not support pooling in channel dimension now
107
2
    output_operand->dims[3] = channel;
108
2
    output_operand->data_type = operands[input_operand_index].data_type;
109
2
    output_operand->length = calculate_operand_data_length(output_operand);
110
2
    if (output_operand->length <= 0) {
111
        av_log(ctx, AV_LOG_ERROR, "The output data length overflow\n");
112
        return DNN_ERROR;
113
    }
114
2
    output_operand->data = av_realloc(output_operand->data, output_operand->length);
115
2
    if (!output_operand->data) {
116
        av_log(ctx, AV_LOG_ERROR, "Failed to reallocate memory for output\n");
117
        return DNN_ERROR;
118
    }
119
2
    output = output_operand->data;
120
121
11
    for (int y = 0; y < height_end; y += kernel_strides) {
122
59
        for (int x = 0; x < width_end; x += kernel_strides) {
123
200
            for (int n_channel = 0; n_channel < channel; ++n_channel) {
124
150
                output[n_channel] = 0.0;
125
150
                kernel_area = 0;
126
450
                for (int kernel_y = 0; kernel_y < avgpool_params->kernel_size; ++kernel_y) {
127
900
                    for (int kernel_x = 0; kernel_x < avgpool_params->kernel_size; ++kernel_x) {
128
                        float input_pel;
129
600
                        int y_pos = y + (kernel_y - height_radius);
130
600
                        int x_pos = x + (kernel_x - width_radius);
131


600
                        if (x_pos < 0 || x_pos >= width || y_pos < 0 || y_pos >= height) {
132
63
                            input_pel = 0.0;
133
                        } else {
134
537
                            kernel_area++;
135
537
                            input_pel = input[y_pos * src_linesize + x_pos * channel + n_channel];
136
                        }
137
600
                        output[n_channel] += input_pel;
138
                    }
139
                }
140
150
                output[n_channel] /= kernel_area;
141
            }
142
50
            output += channel;
143
        }
144
    }
145
146
2
    return 0;
147
}