FFmpeg
dnn_io_proc.c
Go to the documentation of this file.
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 #include "dnn_io_proc.h"
22 #include "libavutil/imgutils.h"
23 #include "libswscale/swscale.h"
24 #include "libavutil/avassert.h"
26 
28 {
29  struct SwsContext *sws_ctx;
30  int bytewidth = av_image_get_linesize(frame->format, frame->width, 0);
31  if (bytewidth < 0) {
32  return AVERROR(EINVAL);
33  }
34  if (output->dt != DNN_FLOAT) {
35  avpriv_report_missing_feature(log_ctx, "data type rather than DNN_FLOAT");
36  return AVERROR(ENOSYS);
37  }
38 
39  switch (frame->format) {
40  case AV_PIX_FMT_RGB24:
41  case AV_PIX_FMT_BGR24:
42  sws_ctx = sws_getContext(frame->width * 3,
43  frame->height,
45  frame->width * 3,
46  frame->height,
48  0, NULL, NULL, NULL);
49  if (!sws_ctx) {
50  av_log(log_ctx, AV_LOG_ERROR, "Impossible to create scale context for the conversion "
51  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
52  av_get_pix_fmt_name(AV_PIX_FMT_GRAYF32), frame->width * 3, frame->height,
53  av_get_pix_fmt_name(AV_PIX_FMT_GRAY8), frame->width * 3, frame->height);
54  return AVERROR(EINVAL);
55  }
56  sws_scale(sws_ctx, (const uint8_t *[4]){(const uint8_t *)output->data, 0, 0, 0},
57  (const int[4]){frame->width * 3 * sizeof(float), 0, 0, 0}, 0, frame->height,
58  (uint8_t * const*)frame->data, frame->linesize);
59  sws_freeContext(sws_ctx);
60  return 0;
61  case AV_PIX_FMT_GRAYF32:
62  av_image_copy_plane(frame->data[0], frame->linesize[0],
63  output->data, bytewidth,
64  bytewidth, frame->height);
65  return 0;
66  case AV_PIX_FMT_YUV420P:
67  case AV_PIX_FMT_YUV422P:
68  case AV_PIX_FMT_YUV444P:
69  case AV_PIX_FMT_YUV410P:
70  case AV_PIX_FMT_YUV411P:
71  case AV_PIX_FMT_GRAY8:
72  case AV_PIX_FMT_NV12:
73  sws_ctx = sws_getContext(frame->width,
74  frame->height,
76  frame->width,
77  frame->height,
79  0, NULL, NULL, NULL);
80  if (!sws_ctx) {
81  av_log(log_ctx, AV_LOG_ERROR, "Impossible to create scale context for the conversion "
82  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
85  return AVERROR(EINVAL);
86  }
87  sws_scale(sws_ctx, (const uint8_t *[4]){(const uint8_t *)output->data, 0, 0, 0},
88  (const int[4]){frame->width * sizeof(float), 0, 0, 0}, 0, frame->height,
89  (uint8_t * const*)frame->data, frame->linesize);
90  sws_freeContext(sws_ctx);
91  return 0;
92  default:
94  return AVERROR(ENOSYS);
95  }
96 
97  return 0;
98 }
99 
101 {
102  struct SwsContext *sws_ctx;
103  int bytewidth = av_image_get_linesize(frame->format, frame->width, 0);
104  if (bytewidth < 0) {
105  return AVERROR(EINVAL);
106  }
107  if (input->dt != DNN_FLOAT) {
108  avpriv_report_missing_feature(log_ctx, "data type rather than DNN_FLOAT");
109  return AVERROR(ENOSYS);
110  }
111 
112  switch (frame->format) {
113  case AV_PIX_FMT_RGB24:
114  case AV_PIX_FMT_BGR24:
115  sws_ctx = sws_getContext(frame->width * 3,
116  frame->height,
118  frame->width * 3,
119  frame->height,
121  0, NULL, NULL, NULL);
122  if (!sws_ctx) {
123  av_log(log_ctx, AV_LOG_ERROR, "Impossible to create scale context for the conversion "
124  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
125  av_get_pix_fmt_name(AV_PIX_FMT_GRAY8), frame->width * 3, frame->height,
126  av_get_pix_fmt_name(AV_PIX_FMT_GRAYF32),frame->width * 3, frame->height);
127  return AVERROR(EINVAL);
128  }
129  sws_scale(sws_ctx, (const uint8_t **)frame->data,
130  frame->linesize, 0, frame->height,
131  (uint8_t * const [4]){input->data, 0, 0, 0},
132  (const int [4]){frame->width * 3 * sizeof(float), 0, 0, 0});
133  sws_freeContext(sws_ctx);
134  break;
135  case AV_PIX_FMT_GRAYF32:
136  av_image_copy_plane(input->data, bytewidth,
137  frame->data[0], frame->linesize[0],
138  bytewidth, frame->height);
139  break;
140  case AV_PIX_FMT_YUV420P:
141  case AV_PIX_FMT_YUV422P:
142  case AV_PIX_FMT_YUV444P:
143  case AV_PIX_FMT_YUV410P:
144  case AV_PIX_FMT_YUV411P:
145  case AV_PIX_FMT_GRAY8:
146  case AV_PIX_FMT_NV12:
147  sws_ctx = sws_getContext(frame->width,
148  frame->height,
150  frame->width,
151  frame->height,
153  0, NULL, NULL, NULL);
154  if (!sws_ctx) {
155  av_log(log_ctx, AV_LOG_ERROR, "Impossible to create scale context for the conversion "
156  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
159  return AVERROR(EINVAL);
160  }
161  sws_scale(sws_ctx, (const uint8_t **)frame->data,
162  frame->linesize, 0, frame->height,
163  (uint8_t * const [4]){input->data, 0, 0, 0},
164  (const int [4]){frame->width * sizeof(float), 0, 0, 0});
165  sws_freeContext(sws_ctx);
166  break;
167  default:
169  return AVERROR(ENOSYS);
170  }
171 
172  return 0;
173 }
174 
176 {
177  if (data->dt == DNN_UINT8) {
178  switch (data->order) {
179  case DCO_BGR:
180  return AV_PIX_FMT_BGR24;
181  case DCO_RGB:
182  return AV_PIX_FMT_RGB24;
183  default:
184  av_assert0(!"unsupported data pixel format.\n");
185  return AV_PIX_FMT_BGR24;
186  }
187  }
188 
189  av_assert0(!"unsupported data type.\n");
190  return AV_PIX_FMT_BGR24;
191 }
192 
193 int ff_frame_to_dnn_classify(AVFrame *frame, DNNData *input, uint32_t bbox_index, void *log_ctx)
194 {
195  const AVPixFmtDescriptor *desc;
196  int offsetx[4], offsety[4];
197  uint8_t *bbox_data[4];
198  struct SwsContext *sws_ctx;
199  int linesizes[4];
200  int ret = 0;
201  enum AVPixelFormat fmt;
202  int left, top, width, height;
204  const AVDetectionBBox *bbox;
206  av_assert0(sd);
207 
208  header = (const AVDetectionBBoxHeader *)sd->data;
209  bbox = av_get_detection_bbox(header, bbox_index);
210 
211  left = bbox->x;
212  width = bbox->w;
213  top = bbox->y;
214  height = bbox->h;
215 
216  fmt = get_pixel_format(input);
217  sws_ctx = sws_getContext(width, height, frame->format,
218  input->width, input->height, fmt,
220  if (!sws_ctx) {
221  av_log(log_ctx, AV_LOG_ERROR, "Failed to create scale context for the conversion "
222  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
225  return AVERROR(EINVAL);
226  }
227 
228  ret = av_image_fill_linesizes(linesizes, fmt, input->width);
229  if (ret < 0) {
230  av_log(log_ctx, AV_LOG_ERROR, "unable to get linesizes with av_image_fill_linesizes");
231  sws_freeContext(sws_ctx);
232  return ret;
233  }
234 
235  desc = av_pix_fmt_desc_get(frame->format);
236  offsetx[1] = offsetx[2] = AV_CEIL_RSHIFT(left, desc->log2_chroma_w);
237  offsetx[0] = offsetx[3] = left;
238 
239  offsety[1] = offsety[2] = AV_CEIL_RSHIFT(top, desc->log2_chroma_h);
240  offsety[0] = offsety[3] = top;
241 
242  for (int k = 0; frame->data[k]; k++)
243  bbox_data[k] = frame->data[k] + offsety[k] * frame->linesize[k] + offsetx[k];
244 
245  sws_scale(sws_ctx, (const uint8_t *const *)&bbox_data, frame->linesize,
246  0, height,
247  (uint8_t *const [4]){input->data, 0, 0, 0}, linesizes);
248 
249  sws_freeContext(sws_ctx);
250 
251  return ret;
252 }
253 
255 {
256  struct SwsContext *sws_ctx;
257  int linesizes[4];
258  int ret = 0;
260  sws_ctx = sws_getContext(frame->width, frame->height, frame->format,
261  input->width, input->height, fmt,
263  if (!sws_ctx) {
264  av_log(log_ctx, AV_LOG_ERROR, "Impossible to create scale context for the conversion "
265  "fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
266  av_get_pix_fmt_name(frame->format), frame->width, frame->height,
268  return AVERROR(EINVAL);
269  }
270 
271  ret = av_image_fill_linesizes(linesizes, fmt, input->width);
272  if (ret < 0) {
273  av_log(log_ctx, AV_LOG_ERROR, "unable to get linesizes with av_image_fill_linesizes");
274  sws_freeContext(sws_ctx);
275  return ret;
276  }
277 
278  sws_scale(sws_ctx, (const uint8_t *const *)frame->data, frame->linesize, 0, frame->height,
279  (uint8_t *const [4]){input->data, 0, 0, 0}, linesizes);
280 
281  sws_freeContext(sws_ctx);
282  return ret;
283 }
AVPixelFormat
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
av_frame_get_side_data
AVFrameSideData * av_frame_get_side_data(const AVFrame *frame, enum AVFrameSideDataType type)
Definition: frame.c:684
av_pix_fmt_desc_get
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
Definition: pixdesc.c:2662
output
filter_frame For filters that do not use the this method is called when a frame is pushed to the filter s input It can be called at any time except in a reentrant way If the input frame is enough to produce output
Definition: filter_design.txt:225
test::height
int height
Definition: vc1dsp.c:39
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:325
data
const char data[16]
Definition: mxf.c:143
AV_PIX_FMT_BGR24
@ AV_PIX_FMT_BGR24
packed RGB 8:8:8, 24bpp, BGRBGR...
Definition: pixfmt.h:69
sws_scale
int attribute_align_arg sws_scale(struct SwsContext *c, const uint8_t *const srcSlice[], const int srcStride[], int srcSliceY, int srcSliceH, uint8_t *const dst[], const int dstStride[])
swscale wrapper, so we don't need to export the SwsContext.
Definition: swscale.c:1201
dnn_io_proc.h
AVDetectionBBox::y
int y
Definition: detection_bbox.h:32
av_image_copy_plane
void av_image_copy_plane(uint8_t *dst, int dst_linesize, const uint8_t *src, int src_linesize, int bytewidth, int height)
Copy image plane from src to dst.
Definition: imgutils.c:374
SWS_FAST_BILINEAR
#define SWS_FAST_BILINEAR
Definition: swscale.h:65
get_pixel_format
static enum AVPixelFormat get_pixel_format(DNNData *data)
Definition: dnn_io_proc.c:175
av_get_detection_bbox
static av_always_inline AVDetectionBBox * av_get_detection_bbox(const AVDetectionBBoxHeader *header, unsigned int idx)
Definition: detection_bbox.h:84
avassert.h
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
float
float
Definition: af_crystalizer.c:122
width
#define width
av_image_fill_linesizes
int av_image_fill_linesizes(int linesizes[4], enum AVPixelFormat pix_fmt, int width)
Fill plane linesizes for an image with pixel format pix_fmt and width width.
Definition: imgutils.c:89
AV_CEIL_RSHIFT
#define AV_CEIL_RSHIFT(a, b)
Definition: common.h:50
av_assert0
#define av_assert0(cond)
assert() equivalent, that is always enabled.
Definition: avassert.h:37
DNNData
Definition: dnn_interface.h:59
AV_PIX_FMT_YUV420P
@ AV_PIX_FMT_YUV420P
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:66
AV_PIX_FMT_GRAYF32
#define AV_PIX_FMT_GRAYF32
Definition: pixfmt.h:438
ff_proc_from_frame_to_dnn
int ff_proc_from_frame_to_dnn(AVFrame *frame, DNNData *input, void *log_ctx)
Definition: dnn_io_proc.c:100
ff_frame_to_dnn_detect
int ff_frame_to_dnn_detect(AVFrame *frame, DNNData *input, void *log_ctx)
Definition: dnn_io_proc.c:254
NULL
#define NULL
Definition: coverity.c:32
AVDetectionBBoxHeader
Definition: detection_bbox.h:56
AV_PIX_FMT_GRAY8
@ AV_PIX_FMT_GRAY8
Y , 8bpp.
Definition: pixfmt.h:74
test::width
int width
Definition: vc1dsp.c:38
AV_PIX_FMT_RGB24
@ AV_PIX_FMT_RGB24
packed RGB 8:8:8, 24bpp, RGBRGB...
Definition: pixfmt.h:68
AVDetectionBBox::w
int w
Definition: detection_bbox.h:33
sws_getContext
struct SwsContext * sws_getContext(int srcW, int srcH, enum AVPixelFormat srcFormat, int dstW, int dstH, enum AVPixelFormat dstFormat, int flags, SwsFilter *srcFilter, SwsFilter *dstFilter, const double *param)
Allocate and return an SwsContext.
Definition: utils.c:2050
avpriv_report_missing_feature
void avpriv_report_missing_feature(void *avc, const char *msg,...) av_printf_format(2
Log a generic warning message about a missing feature.
AVFrameSideData::data
uint8_t * data
Definition: frame.h:233
header
static const uint8_t header[24]
Definition: sdr2.c:67
height
#define height
DNN_FLOAT
@ DNN_FLOAT
Definition: dnn_interface.h:37
input
and forward the test the status of outputs and forward it to the corresponding return FFERROR_NOT_READY If the filters stores internally one or a few frame for some input
Definition: filter_design.txt:172
av_image_get_linesize
int av_image_get_linesize(enum AVPixelFormat pix_fmt, int width, int plane)
Compute the size of an image line with format pix_fmt and width width for the plane plane.
Definition: imgutils.c:76
ret
ret
Definition: filter_design.txt:187
AV_PIX_FMT_NV12
@ AV_PIX_FMT_NV12
planar YUV 4:2:0, 12bpp, 1 plane for Y and 1 plane for the UV components, which are interleaved (firs...
Definition: pixfmt.h:89
frame
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a frame
Definition: filter_design.txt:264
AVDetectionBBox::h
int h
Definition: detection_bbox.h:34
DNN_UINT8
@ DNN_UINT8
Definition: dnn_interface.h:37
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
sws_freeContext
void sws_freeContext(struct SwsContext *swsContext)
Free the swscaler context swsContext.
Definition: utils.c:2381
AVDetectionBBox::x
int x
Distance in pixels from the left/top edge of the frame, together with width and height,...
Definition: detection_bbox.h:31
DCO_RGB
@ DCO_RGB
Definition: dnn_interface.h:42
AV_PIX_FMT_YUV444P
@ AV_PIX_FMT_YUV444P
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
desc
const char * desc
Definition: libsvtav1.c:83
AV_PIX_FMT_YUV422P
@ AV_PIX_FMT_YUV422P
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
AVFrameSideData
Structure to hold side data for an AVFrame.
Definition: frame.h:231
AVPixFmtDescriptor
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
Definition: pixdesc.h:69
ff_frame_to_dnn_classify
int ff_frame_to_dnn_classify(AVFrame *frame, DNNData *input, uint32_t bbox_index, void *log_ctx)
Definition: dnn_io_proc.c:193
AV_PIX_FMT_YUV411P
@ AV_PIX_FMT_YUV411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
imgutils.h
AV_PIX_FMT_YUV410P
@ AV_PIX_FMT_YUV410P
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Definition: pixfmt.h:72
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
AVDetectionBBox
Definition: detection_bbox.h:26
DCO_BGR
@ DCO_BGR
Definition: dnn_interface.h:41
SwsContext
Definition: swscale_internal.h:298
detection_bbox.h
swscale.h
AV_FRAME_DATA_DETECTION_BBOXES
@ AV_FRAME_DATA_DETECTION_BBOXES
Bounding boxes for object detection and classification, as described by AVDetectionBBoxHeader.
Definition: frame.h:190
av_get_pix_fmt_name
const char * av_get_pix_fmt_name(enum AVPixelFormat pix_fmt)
Return the short name for a pixel format, NULL in case pix_fmt is unknown.
Definition: pixdesc.c:2582
ff_proc_from_dnn_to_frame
int ff_proc_from_dnn_to_frame(AVFrame *frame, DNNData *output, void *log_ctx)
Definition: dnn_io_proc.c:27