mirror of https://git.ffmpeg.org/ffmpeg.git
104 lines
3.8 KiB
C
104 lines
3.8 KiB
C
/*
|
|
* 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
|
|
*/
|
|
|
|
/**
|
|
* @file
|
|
* DNN native backend implementation.
|
|
*/
|
|
|
|
#include "dnn_backend_native.h"
|
|
#include "libavutil/avassert.h"
|
|
#include "dnn_backend_native_layer_depth2space.h"
|
|
|
|
int dnn_load_layer_depth2space(Layer *layer, AVIOContext *model_file_context, int file_size, int operands_num)
|
|
{
|
|
DepthToSpaceParams *params;
|
|
int dnn_size = 0;
|
|
params = av_malloc(sizeof(*params));
|
|
if (!params)
|
|
return 0;
|
|
|
|
params->block_size = (int32_t)avio_rl32(model_file_context);
|
|
dnn_size += 4;
|
|
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;
|
|
layer->params = params;
|
|
|
|
if (layer->input_operand_indexes[0] >= operands_num || layer->output_operand_index >= operands_num) {
|
|
return 0;
|
|
}
|
|
|
|
return dnn_size;
|
|
}
|
|
|
|
int dnn_execute_layer_depth2space(DnnOperand *operands, const int32_t *input_operand_indexes,
|
|
int32_t output_operand_index, const void *parameters, NativeContext *ctx)
|
|
{
|
|
float *output;
|
|
const DepthToSpaceParams *params = (const DepthToSpaceParams *)parameters;
|
|
int block_size = params->block_size;
|
|
int32_t input_operand_index = input_operand_indexes[0];
|
|
int number = operands[input_operand_index].dims[0];
|
|
int height = operands[input_operand_index].dims[1];
|
|
int width = operands[input_operand_index].dims[2];
|
|
int channels = operands[input_operand_index].dims[3];
|
|
const float *input = operands[input_operand_index].data;
|
|
|
|
int y, x, by, bx, ch;
|
|
int new_channels = channels / (block_size * block_size);
|
|
int output_linesize = width * channels;
|
|
int by_linesize = output_linesize / block_size;
|
|
int x_linesize = new_channels * block_size;
|
|
|
|
DnnOperand *output_operand = &operands[output_operand_index];
|
|
output_operand->dims[0] = number;
|
|
output_operand->dims[1] = height * block_size;
|
|
output_operand->dims[2] = width * block_size;
|
|
output_operand->dims[3] = new_channels;
|
|
output_operand->data_type = operands[input_operand_index].data_type;
|
|
output_operand->length = 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;
|
|
}
|
|
output_operand->data = av_realloc(output_operand->data, output_operand->length);
|
|
if (!output_operand->data) {
|
|
av_log(ctx, AV_LOG_ERROR, "Failed to reallocate memory for output\n");
|
|
return DNN_ERROR;
|
|
}
|
|
output = output_operand->data;
|
|
|
|
for (y = 0; y < height; ++y){
|
|
for (x = 0; x < width; ++x){
|
|
for (by = 0; by < block_size; ++by){
|
|
for (bx = 0; bx < block_size; ++bx){
|
|
for (ch = 0; ch < new_channels; ++ch){
|
|
output[by * by_linesize + x * x_linesize + bx * new_channels + ch] = input[ch];
|
|
}
|
|
input += new_channels;
|
|
}
|
|
}
|
|
}
|
|
output += output_linesize;
|
|
}
|
|
return 0;
|
|
}
|