Масштабный фильтр вылетает с ошибкой при использовании из примера транскодирования

Я немного изменил (просто для компиляции в c ++) этот пример кода:
https://github.com/FFmpeg/FFmpeg/blob/master/doc/examples/transcoding.c.

Что работает: как есть (нулевой фильтр), ряд других фильтров, таких как частота кадров, DrawText, …

Что не работает: масштабный фильтр при уменьшении.

Я использую следующий синтаксис для масштаба (я пробовал и многие другие, тот же эффект):
«Масштаб = ш = IW / 2: -1»

Ошибка: «Ширина входного изображения (240) больше шага (128)», где значения ширины и шага зависят от ввода.

Информация о разной среде: windows, VS 2017, пример ввода: rtsp: //wowzaec2demo.streamlock.net/vod/mp4: BigBuckBunny_115k.mov

Любой ключ к тому, что я делаю неправильно?

Спасибо !

РЕДАКТИРОВАТЬ, чтобы добавить пример рабочего кода

#pragma comment(lib, "avcodec.lib")
#pragma comment(lib, "avutil.lib")
#pragma comment(lib, "avformat.lib")
#pragma comment(lib, "avfilter.lib")

/*
* Copyright (c) 2010 Nicolas George
* Copyright (c) 2011 Stefano Sabatini
* Copyright (c) 2014 Andrey Utkin
*
**** EDITED 2017 for testing (see original here: https://github.com/FFmpeg/FFmpeg/blob/master/doc/examples/transcoding.c)
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/

/**
* @file
* API example for demuxing, decoding, filtering, encoding and muxing
* @example transcoding.c
*/

extern "C"{
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>
}static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;

typedef struct StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_ctx;

static int open_input_file(const char *filename, int& videoStreamIndex)
{
int ret;
unsigned int i;

ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}

if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}

// Just need video
videoStreamIndex = -1;
for (unsigned int i = 0; i < ifmt_ctx->nb_streams; i++)
{
if (ifmt_ctx->streams[i]->codecpar->codec_type != AVMEDIA_TYPE_VIDEO)
continue;
videoStreamIndex = i;
break;
}
if (videoStreamIndex < 0)
{
av_log(NULL, AV_LOG_ERROR, "Cannot find video stream\n");
return videoStreamIndex;
}stream_ctx = (StreamContext*)av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);

for (i = 0; i < ifmt_ctx->nb_streams; i++) {

// Just need video
if (i != videoStreamIndex)
continue;AVStream *stream = ifmt_ctx->streams[i];
AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
return AVERROR(ENOMEM);
}
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context ""for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
stream_ctx[i].dec_ctx = codec_ctx;
}

av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}

static int open_output_file(const char *filename, const int videoStreamIndex)
{
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;

ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}for (i = 0; i < ifmt_ctx->nb_streams; i++) {
// Just need video
if (i != videoStreamIndex)
continue;

out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}

in_stream = ifmt_ctx->streams[i];
dec_ctx = stream_ctx[i].dec_ctx;

if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
/* in this example, we choose transcoding to same codec */
encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}

/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;

/* video time_base can be set to whatever is handy and supported by encoder */
//enc_ctx->time_base = av_inv_q(dec_ctx->framerate);
enc_ctx->time_base = dec_ctx->time_base;/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;

out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
}
else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
}
else {
/* if this stream must be remuxed */
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}

}
av_dump_format(ofmt_ctx, 0, filename, 1);

if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}

/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}

return 0;
}

static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec)
{
char args[512];
int ret = 0;
AVFilter *buffersrc = NULL;
AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();

if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}

if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}

snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);

ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}

ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}

ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
}
else {
ret = AVERROR_UNKNOWN;
goto end;
}

/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;

inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;

if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}

if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;

if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;

/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;

end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);

return ret;
}

static int init_filters(const int videoStreamIndex)
{
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = (FilteringContext*)av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);

for (i = 0; i < ifmt_ctx->nb_streams; i++) {

// Just video
if (i != videoStreamIndex)
continue;

filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
continue;

filter_spec = "null"; /* passthrough (dummy) filter for video */
//filter_spec = "scale=w=iw/2:-1";
// filter_spec = "drawtext=fontfile=FreeSerif.ttf: text='%{localtime}': x=w-text_w: y=0: fontsize=24: [email protected]: box=1: [email protected]";
// filter_spec = "drawtext=fontfile=FreeSerif.ttf :text='test': x=w-text_w: y=text_h: fontsize=24: [email protected]: box=1: [email protected]";

ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
stream_ctx[i].enc_ctx, filter_spec);
if (ret)
return ret;
}
return 0;
}

static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame, const int videoStreamIndex) {

// Just video
if (stream_index != videoStreamIndex)
return 0;

int ret;
int got_frame_local;
AVPacket enc_pkt;
int(*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codecpar->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;

if (!got_frame)
got_frame = &got_frame_local;

// av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);

ret = enc_func(stream_ctx[stream_index].enc_ctx, &enc_pkt,
filt_frame, got_frame);

av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;

/* prepare packet for muxing */
/*enc_pkt.stream_index = stream_index;
av_packet_rescale_ts(&enc_pkt, stream_ctx[stream_index].enc_ctx->time_base, ofmt_ctx->streams[stream_index]->time_base);*/
enc_pkt.stream_index = 0;
av_packet_rescale_ts(&enc_pkt, stream_ctx[stream_index].enc_ctx->time_base, ofmt_ctx->streams[0]->time_base);

av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}

static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index, const int videoStreamIndex)
{
// Just video, all else crashes
if (stream_index != videoStreamIndex)
return 0;

int ret;
AVFrame *filt_frame;

// av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}

/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
// av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}

filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL, videoStreamIndex);
if (ret < 0)
break;
}

return ret;
}

static int flush_encoder(unsigned int stream_index, const int videoStreamIndex)
{
int ret;
int got_frame;

// Just video
if (stream_index != videoStreamIndex)
return 0;

if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;

while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame, videoStreamIndex);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}#include <vector>

int main(int argc, char **argv)
{
int ret;

AVPacket packet;
packet.data = NULL;
packet.size = 0;

AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int(*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);#ifdef _DEBUG
// Hardcoded arguments
std::vector<char*> varguments;
{
varguments.push_back(argv[0]);

// Source
varguments.push_back("./big_buck_bunny_short.mp4 ");

// Destination
varguments.push_back("./big_buck_bunny_short-processed.mp4");
}

char** arguments = new char*[varguments.size()];
for (unsigned int i = 0; i < varguments.size(); i++)
{
arguments[i] = varguments[i];
}
argc = varguments.size();
argv = arguments;
#endif // _DEBUGif (argc != 3) {
av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]);
return 1;
}

av_register_all();
avfilter_register_all();

int videoStreamIndex = -1;
if ((ret = open_input_file(argv[1], videoStreamIndex)) < 0)
goto end;
if ((ret = open_output_file(argv[2], videoStreamIndex)) < 0)
goto end;
if ((ret = init_filters(videoStreamIndex)) < 0)
goto end;

// Stop after a couple of frames
int framesToGet = 100;

/* read all packets */
//while (framesToGet--)
while(1)
{
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;

// I just need video
if (stream_index != videoStreamIndex) {
av_packet_unref(&packet);
continue;
}

type = ifmt_ctx->streams[packet.stream_index]->codecpar->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);

if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
stream_ctx[stream_index].dec_ctx->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(stream_ctx[stream_index].dec_ctx, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}

if (got_frame) {
frame->pts = frame->best_effort_timestamp;
ret = filter_encode_write_frame(frame, stream_index, videoStreamIndex);
av_frame_free(&frame);
if (ret < 0)
goto end;
}
else {
av_frame_free(&frame);
}
}
else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);

ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_packet_unref(&packet);
}

/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i, videoStreamIndex);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}

/* flush encoder */
ret = flush_encoder(i, videoStreamIndex);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}

av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
// Just video
if (i != videoStreamIndex)
continue;
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
if (filter_ctx && filter_ctx[i].filter_graph)
avfilter_graph_free(&filter_ctx[i].filter_graph);
}
av_free(filter_ctx);
av_free(stream_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);

/*if (ret < 0)
av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));*/

return ret ? 1 : 0;
}