Recherche avancée

Sur d’autres sites (7842)

• x86/tx_float : remove vgatherdpd usage

  20 mai 2022, par Lynne

  x86/tx_float : remove vgatherdpd usage
  Its performance loss ranges from either being just as fast as individual loads
  
  (Skylake), a few percent slower (Alderlake), 8% slower (Zen 3), to completely
  
  disasterous (older/other CPUs).
  Sadly, gathers never panned out fast on x86, even with the benefit of time and
  
  implementation experience.
  This also saves a register, as there's no need to fill out an additional
  
  register mask.
  Zen 3 (16384-point transform) :
  
  Before : 1561050 decicycles in           av_tx (fft),  131072 runs,      0 skips
  
  After :  1449621 decicycles in           av_tx (fft),  131072 runs,      0 skips
  Alderlake :
  
  2% slower on big transforms (65536), to 1% (131072), to a few percent for smaller
  
  sizes.
  

  • [DH] libavutil/x86/tx_float.asm
  • [DH] libavutil/x86/tx_float_init.c

• RGB-frame encoding - FFmpeg/libav

  4 février 2014, par learner

  I am learning video encoding & decoding in FFmpeg. I tried the code sample on this page (only the video encoding & decoding part). Here the dummy image being created is in YCbCr format. How do I achieve similar encoding by creating RGB frames ? I am stuck at :

  Firstly, how to create this RGB dummy frame ?

  Secondly, how to encode it ? Which codec to use ? Most of them work with YUV420p only...

  EDIT : I have a YCbCr encoder and decoder as given on the this page. The thing is, I have RGB frame-sequence in my database and I need to encode it. But the encoder is for YCbCr. So, I am wondering to convert RGB frames to YCbCr (or YUV420P) somehow and then encode them.
  At decoding end, I get decoded YCbCr frames and I convert them back to RGB. How to go ahead with it ?

  I did try the swscontext thing, but the converted frames lose color information and also scaling errors. I thought of doing it manually using two for loops and colorspace conversion formulae
  but I am not able to access individual pixel of a frame using FFmpeg/libav library ! Like in OpenCV we can easily access it with something like : Mat img(x,y) but no such thing here ! I am totally a newcomer to this area...

  Someone can help me ?

  Many Thanks !

• Convert sequence of h264 frames into video with ffmpeg

  12 août 2022, par utnd03

  I'm testing a hardware video encoder module, and for each input frame (raw YUV in NV12 format) the encoder generates an h264 output frame. How can I "concatenate" these individual h264 output frames into a video (e.g. mp4) with ffmpeg ?

  


  $ ls
dst0000.h264  dst0002.h264  dst0004.h264  dst0006.h264  dst0008.h264 
dst0001.h264  dst0003.h264  dst0005.h264  dst0007.h264

$ file dst0000.h264
dst0000.h264: JVT NAL sequence, H.264 video, main @ L 31


  


  I tried ffmpeg -i dst0001.h264 -c:v copy output.mp4, which allows me to view a single h264 frame (and they look normal, so the encoder is working properly).

  


  I also tried ffmpeg -f image2 -s 640x480 -r 30 -i dst%04d.h264 -c:v copy out.mp4, but this gave the following error, which I had no idea how to fix :

  


  [image2 @ 0x55bf32735780] Could not find codec parameters for stream 0 (Video: none, none, 640x480): unknown codec
Consider increasing the value for the 'analyzeduration' (0) and 'probesize' (5000000) options
Input #0, image2, from 'dst%04d.h264':
  Duration: 00:00:00.30, start: 0.000000, bitrate: N/A
  Stream #0:0: Video: none, none, 640x480, 30 fps, 30 tbr, 30 tbn
[mp4 @ 0x55bf3273fc80] Could not find tag for codec none in stream #0, codec not currently supported in container
Could not write header for output file #0 (incorrect codec parameters ?): Invalid argument
Error initializing output stream 0:0 -- 
Stream mapping:
  Stream #0:0 -> #0:0 (copy)
    Last message repeated 1 times