Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
multimedia/ffmpeg: backport SVTAV1 fixes after d187ef9
- Loading branch information
Showing
2 changed files
with
272 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,271 @@ | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/04b89e8ae33b | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/64e2fb3f9d89 | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/0463f5d6d56d | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/c5f314309067 | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/c33b4048859a | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/a2b090da7932 | ||
https://git.ffmpeg.org/gitweb/ffmpeg.git/commitdiff/1dddb930aaf0 | ||
|
||
--- configure.orig 2021-10-24 20:47:11 UTC | ||
+++ configure | ||
@@ -6430,7 +6430,7 @@ enabled libsoxr && require libsoxr soxr.h so | ||
enabled libssh && require_pkg_config libssh libssh libssh/sftp.h sftp_init | ||
enabled libspeex && require_pkg_config libspeex speex speex/speex.h speex_decoder_init | ||
enabled libsrt && require_pkg_config libsrt "srt >= 1.3.0" srt/srt.h srt_socket | ||
-enabled libsvtav1 && require_pkg_config libsvtav1 "SvtAv1Enc >= 0.8.4" EbSvtAv1Enc.h svt_av1_enc_init_handle | ||
+enabled libsvtav1 && require_pkg_config libsvtav1 "SvtAv1Enc >= 0.9.0" EbSvtAv1Enc.h svt_av1_enc_init_handle | ||
enabled libtensorflow && require libtensorflow tensorflow/c/c_api.h TF_Version -ltensorflow | ||
enabled libtesseract && require_pkg_config libtesseract tesseract tesseract/capi.h TessBaseAPICreate | ||
enabled libtheora && require libtheora theora/theoraenc.h th_info_init -ltheoraenc -ltheoradec -logg | ||
--- doc/encoders.texi.orig 2021-10-24 20:47:07 UTC | ||
+++ doc/encoders.texi | ||
@@ -1754,28 +1754,15 @@ Set the operating point level. | ||
@item tier | ||
Set the operating point tier. | ||
|
||
-@item rc | ||
-Set the rate control mode to use. | ||
- | ||
-Possible modes: | ||
-@table @option | ||
-@item cqp | ||
-Constant quantizer: use fixed values of qindex (dependent on the frame type) | ||
-throughout the stream. This mode is the default. | ||
- | ||
-@item vbr | ||
-Variable bitrate: use a target bitrate for the whole stream. | ||
- | ||
-@item cvbr | ||
-Constrained variable bitrate: use a target bitrate for each GOP. | ||
-@end table | ||
- | ||
@item qmax | ||
Set the maximum quantizer to use when using a bitrate mode. | ||
|
||
@item qmin | ||
Set the minimum quantizer to use when using a bitrate mode. | ||
|
||
+@item crf | ||
+Constant rate factor value used in crf rate control mode (0-63). | ||
+ | ||
@item qp | ||
Set the quantizer used in cqp rate control mode (0-63). | ||
|
||
@@ -1786,14 +1773,18 @@ Enable scene change detection. | ||
Set number of frames to look ahead (0-120). | ||
|
||
@item preset | ||
-Set the quality-speed tradeoff, in the range 0 to 8. Higher values are | ||
-faster but lower quality. Defaults to 8 (highest speed). | ||
+Set the quality-speed tradeoff, in the range 0 to 13. Higher values are | ||
+faster but lower quality. | ||
|
||
@item tile_rows | ||
Set log2 of the number of rows of tiles to use (0-6). | ||
|
||
@item tile_columns | ||
Set log2 of the number of columns of tiles to use (0-4). | ||
+ | ||
+@item svtav1-params | ||
+Set SVT-AV1 options using a list of @var{key}=@var{value} pairs separated | ||
+by ":". See the SVT-AV1 encoder user guide for a list of accepted parameters. | ||
|
||
@end table | ||
|
||
--- libavcodec/libsvtav1.c.orig 2021-10-24 20:47:07 UTC | ||
+++ libavcodec/libsvtav1.c | ||
@@ -37,6 +37,10 @@ | ||
#include "avcodec.h" | ||
#include "profiles.h" | ||
|
||
+#ifndef SVT_AV1_CHECK_VERSION | ||
+#define SVT_AV1_CHECK_VERSION(major, minor, patch) 0 | ||
+#endif | ||
+ | ||
typedef enum eos_status { | ||
EOS_NOT_REACHED = 0, | ||
EOS_SENT, | ||
@@ -60,10 +64,11 @@ typedef struct SvtContext { | ||
EOS_STATUS eos_flag; | ||
|
||
// User options. | ||
+ AVDictionary *svtav1_opts; | ||
int hierarchical_level; | ||
int la_depth; | ||
int enc_mode; | ||
- int rc_mode; | ||
+ int crf; | ||
int scd; | ||
int qp; | ||
|
||
@@ -151,7 +156,63 @@ static int config_enc_params(EbSvtAv1EncConfiguration | ||
{ | ||
SvtContext *svt_enc = avctx->priv_data; | ||
const AVPixFmtDescriptor *desc; | ||
+ AVDictionaryEntry *en = NULL; | ||
|
||
+ // Update param from options | ||
+ param->hierarchical_levels = svt_enc->hierarchical_level; | ||
+ | ||
+ if (svt_enc->enc_mode >= 0) | ||
+ param->enc_mode = svt_enc->enc_mode; | ||
+ | ||
+ param->tier = svt_enc->tier; | ||
+ | ||
+ if (avctx->bit_rate) { | ||
+ param->target_bit_rate = avctx->bit_rate; | ||
+ if (avctx->rc_max_rate != avctx->bit_rate) | ||
+ param->rate_control_mode = 1; | ||
+ else | ||
+ param->rate_control_mode = 2; | ||
+ } | ||
+ param->max_bit_rate = avctx->rc_max_rate; | ||
+ param->vbv_bufsize = avctx->rc_buffer_size; | ||
+ | ||
+ if (svt_enc->crf > 0) { | ||
+ param->qp = svt_enc->crf; | ||
+ param->rate_control_mode = 0; | ||
+ param->enable_tpl_la = 1; | ||
+ } else if (svt_enc->qp > 0) { | ||
+ param->qp = svt_enc->qp; | ||
+ param->rate_control_mode = 0; | ||
+ param->enable_tpl_la = 0; | ||
+ } | ||
+ param->scene_change_detection = svt_enc->scd; | ||
+ | ||
+ if (svt_enc->la_depth >= 0) | ||
+ param->look_ahead_distance = svt_enc->la_depth; | ||
+ | ||
+ param->tile_columns = svt_enc->tile_columns; | ||
+ param->tile_rows = svt_enc->tile_rows; | ||
+ | ||
+#if SVT_AV1_CHECK_VERSION(0, 9, 1) | ||
+ while ((en = av_dict_get(svt_enc->svtav1_opts, "", en, AV_DICT_IGNORE_SUFFIX))) { | ||
+ EbErrorType ret = svt_av1_enc_parse_parameter(param, en->key, en->value); | ||
+ if (ret != EB_ErrorNone) { | ||
+ int level = (avctx->err_recognition & AV_EF_EXPLODE) ? AV_LOG_ERROR : AV_LOG_WARNING; | ||
+ av_log(avctx, level, "Error parsing option %s: %s.\n", en->key, en->value); | ||
+ if (avctx->err_recognition & AV_EF_EXPLODE) | ||
+ return AVERROR(EINVAL); | ||
+ } | ||
+ } | ||
+#else | ||
+ if ((en = av_dict_get(svt_enc->svtav1_opts, "", NULL, AV_DICT_IGNORE_SUFFIX))) { | ||
+ int level = (avctx->err_recognition & AV_EF_EXPLODE) ? AV_LOG_ERROR : AV_LOG_WARNING; | ||
+ av_log(avctx, level, "svt-params needs libavcodec to be compiled with SVT-AV1 " | ||
+ "headers >= 0.9.1.\n"); | ||
+ if (avctx->err_recognition & AV_EF_EXPLODE) | ||
+ return AVERROR(ENOSYS); | ||
+ } | ||
+#endif | ||
+ | ||
param->source_width = avctx->width; | ||
param->source_height = avctx->height; | ||
|
||
@@ -184,16 +245,6 @@ static int config_enc_params(EbSvtAv1EncConfiguration | ||
param->profile = FF_PROFILE_AV1_HIGH; | ||
} | ||
|
||
- // Update param from options | ||
- param->hierarchical_levels = svt_enc->hierarchical_level; | ||
- param->enc_mode = svt_enc->enc_mode; | ||
- param->tier = svt_enc->tier; | ||
- param->rate_control_mode = svt_enc->rc_mode; | ||
- param->scene_change_detection = svt_enc->scd; | ||
- param->qp = svt_enc->qp; | ||
- | ||
- param->target_bit_rate = avctx->bit_rate; | ||
- | ||
if (avctx->gop_size > 0) | ||
param->intra_period_length = avctx->gop_size - 1; | ||
|
||
@@ -205,19 +256,15 @@ static int config_enc_params(EbSvtAv1EncConfiguration | ||
param->frame_rate_denominator = avctx->time_base.num * avctx->ticks_per_frame; | ||
} | ||
|
||
- if (param->rate_control_mode) { | ||
+ avctx->bit_rate = param->target_bit_rate; | ||
+ if (avctx->bit_rate) { | ||
param->max_qp_allowed = avctx->qmax; | ||
param->min_qp_allowed = avctx->qmin; | ||
} | ||
|
||
- param->intra_refresh_type = 2; /* Real keyframes only */ | ||
+ /* 2 = IDR, closed GOP, 1 = CRA, open GOP */ | ||
+ param->intra_refresh_type = avctx->flags & AV_CODEC_FLAG_CLOSED_GOP ? 2 : 1; | ||
|
||
- if (svt_enc->la_depth >= 0) | ||
- param->look_ahead_distance = svt_enc->la_depth; | ||
- | ||
- param->tile_columns = svt_enc->tile_columns; | ||
- param->tile_rows = svt_enc->tile_rows; | ||
- | ||
return 0; | ||
} | ||
|
||
@@ -480,8 +527,8 @@ static const AVOption options[] = { | ||
{ "la_depth", "Look ahead distance [0, 120]", OFFSET(la_depth), | ||
AV_OPT_TYPE_INT, { .i64 = -1 }, -1, 120, VE }, | ||
|
||
- { "preset", "Encoding preset [0, 8]", | ||
- OFFSET(enc_mode), AV_OPT_TYPE_INT, { .i64 = MAX_ENC_PRESET }, 0, MAX_ENC_PRESET, VE }, | ||
+ { "preset", "Encoding preset", | ||
+ OFFSET(enc_mode), AV_OPT_TYPE_INT, { .i64 = -1 }, -1, MAX_ENC_PRESET, VE }, | ||
|
||
{ "tier", "Set operating point tier", OFFSET(tier), | ||
AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, VE, "tier" }, | ||
@@ -518,21 +565,19 @@ static const AVOption options[] = { | ||
{ LEVEL("7.3", 73) }, | ||
#undef LEVEL | ||
|
||
- { "rc", "Bit rate control mode", OFFSET(rc_mode), | ||
- AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 3, VE , "rc"}, | ||
- { "cqp", "Constant quantizer", 0, AV_OPT_TYPE_CONST, { .i64 = 0 }, INT_MIN, INT_MAX, VE, "rc" }, | ||
- { "vbr", "Variable Bit Rate, use a target bitrate for the entire stream", 0, AV_OPT_TYPE_CONST, { .i64 = 1 }, INT_MIN, INT_MAX, VE, "rc" }, | ||
- { "cvbr", "Constrained Variable Bit Rate, use a target bitrate for each GOP", 0, AV_OPT_TYPE_CONST,{ .i64 = 2 }, INT_MIN, INT_MAX, VE, "rc" }, | ||
+ { "crf", "Constant Rate Factor value", OFFSET(crf), | ||
+ AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 63, VE }, | ||
+ { "qp", "Initial Quantizer level value", OFFSET(qp), | ||
+ AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 63, VE }, | ||
|
||
- { "qp", "Quantizer to use with cqp rate control mode", OFFSET(qp), | ||
- AV_OPT_TYPE_INT, { .i64 = 50 }, 0, 63, VE }, | ||
- | ||
{ "sc_detection", "Scene change detection", OFFSET(scd), | ||
AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, VE }, | ||
|
||
{ "tile_columns", "Log2 of number of tile columns to use", OFFSET(tile_columns), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 4, VE}, | ||
{ "tile_rows", "Log2 of number of tile rows to use", OFFSET(tile_rows), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 6, VE}, | ||
|
||
+ { "svtav1-params", "Set the SVT-AV1 configuration using a :-separated list of key=value parameters", OFFSET(svtav1_opts), AV_OPT_TYPE_DICT, { 0 }, 0, 0, VE }, | ||
+ | ||
{NULL}, | ||
}; | ||
|
||
@@ -544,9 +589,10 @@ static const AVClass class = { | ||
}; | ||
|
||
static const AVCodecDefault eb_enc_defaults[] = { | ||
- { "b", "7M" }, | ||
+ { "b", "0" }, | ||
+ { "flags", "+cgop" }, | ||
{ "g", "-1" }, | ||
- { "qmin", "0" }, | ||
+ { "qmin", "1" }, | ||
{ "qmax", "63" }, | ||
{ NULL }, | ||
}; | ||
@@ -561,12 +607,11 @@ AVCodec ff_libsvtav1_encoder = { | ||
.receive_packet = eb_receive_packet, | ||
.close = eb_enc_close, | ||
.capabilities = AV_CODEC_CAP_DELAY | AV_CODEC_CAP_OTHER_THREADS, | ||
- .caps_internal = FF_CODEC_CAP_AUTO_THREADS, | ||
+ .caps_internal = FF_CODEC_CAP_AUTO_THREADS | FF_CODEC_CAP_INIT_CLEANUP, | ||
.pix_fmts = (const enum AVPixelFormat[]){ AV_PIX_FMT_YUV420P, | ||
AV_PIX_FMT_YUV420P10, | ||
AV_PIX_FMT_NONE }, | ||
.priv_class = &class, | ||
.defaults = eb_enc_defaults, | ||
- .caps_internal = FF_CODEC_CAP_INIT_CLEANUP, | ||
.wrapper_name = "libsvtav1", | ||
}; |