Recherche avancée

Sur d’autres sites (4553)

• Low GPU Utilization NVIDIA / FFMPEG

  16 septembre 2023, par parakeetdev

  I'm trying to run a Docker container on runpod.io to offset media transcoding via serverless GPU's. I have the container image based off of "nvidia/cuda:12.1.0-cudnn8-devel-ubuntu22.04".

  


  Here's the configuration for FFMPEG in my Dockerfile :

  


  git clone https://github.com/FFmpeg/nv-codec-headers.git && \
    make install -C ./nv-codec-headers && \
    git clone https://git.ffmpeg.org/ffmpeg.git ffmpeg_source/ && \
    /ffmpeg_source/configure --prefix=/usr --ld="g++" --enable-nonfree --enable-gpl --enable-gnutls --enable-cuda-nvcc --enable-cuda --enable-cuda-llvm --enable-cuvid --enable-nvenc --enable-ffnvcodec --enable-libnpp --enable-libmp3lame --enable-libx264 --enable-libx265 --enable-libvpx --enable-libfreetype --enable-libvorbis --enable-libfdk-aac --enable-libopus --extra-cflags=-I/usr/local/cuda/include --extra-ldflags=-L/usr/local/cuda/lib64 --disable-static --enable-shared --disable-stripping


  


  I have the capability for GPU in my compose.yml :

  


      deploy:
      resources:
        reservations:
          devices:
          - driver: nvidia
            count: 1
            capabilities: [gpu]


  


  I receive the CUDA boot up screen when the container deploys. It's running on an RTX A6000, which is capable of hardware accelerated encoding and decoding via NVIDIA for ffmpeg.

  


  My FFMPEG command goes as follows :

  


  command = "ffmpeg -y -hwaccel cuda -hwaccel_output_format cuda -i - "

command += f"-vf scale_npp=1920:1080 -c:v h264_nvenc -b:v 5M -preset p2 -tune ll -f mp4 -bufsize 5M -maxrate 10M -qmin 0 -g 250 -bf 3 -b_ref_mode middle -temporal-aq 1 -rc-lookahead 20 -i_qfactor 0.75 -b_qfactor 1.1 {tempfile_1080.name} "

command += f"-vf scale_npp=1280:720 -c:v h264_nvenc -b:v 3M -preset p2 -tune ll -f mp4 -bufsize 3M -maxrate 6M -qmin 0 -g 250 -bf 3 -b_ref_mode middle -temporal-aq 1 -rc-lookahead 20 -i_qfactor 0.75 -b_qfactor 1.1 {tempfile_720.name} "

command += f"-vf scale_npp=640:480 -c:v h264_nvenc -b:v 1M -preset p2 -tune ll -f mp4 -bufsize 1M -maxrate 2M -qmin 0 -g 250 -bf 3 -b_ref_mode middle -temporal-aq 1 -rc-lookahead 20 -i_qfactor 0.75 -b_qfactor 1.1 {tempfile_480.name}"


  


  I'm using Python and piping to stdin with bytes.

  


  The CPU stays at 100%, while I'm lucky if the GPU ever leaves 0%. I think I've seen it hit at most about 4% utilization, while the CPU is completely maxed out.

  


  I've tried simpler commands. I thought maybe it was due to the audio, so I dropped the audio, but it didn't change anything.

  


  I've tried different images, 11.8 cuda, 12.0 cuda, 12.1 cuda, 12.2 cuda.

  


  I've tried the runtime and devel images for each of those versions.

  


  The drivers are up to date.

  


  It clearly taps into the GPU, because it will slightly bump up to a few percents before going back down to zero. On top of this, the output is also wrong/corrupted, as no video player will open the file, stating that it can't be played.

  


  I have also swapped "-hwaccel cuda" for "-hwaccel nvdec".

  


  No errors thrown and nothing changes. I have also tried with hevc_nvenc for the encoder in x265, also made no difference.

  


  Not sure what I'm doing wrong. Maybe this can't be done via piping ?

  


• Improving ffmpeg pixelation and delay when using four video sources with PiP and using NVIDIA GPU

  7 septembre 2023, par jpvans

  Trying to get the best quality/performance when putting four sources together with ffmpeg.

  


  My current ffmpeg command is :

  


  ffmpeg -input_format h264 -s 1920x1080 -i /dev/video0  -input_format h264 -s 1920x1080 -i /dev/video1 -input_format h264 -s 1920x1080 -i /dev/video2  -input_format h264 -s 1920x1080 -i /dev/video3 -filter_complex \
"[1:v]scale=iw/4:-1:flags=lanczos[pip1]; \
 [2:v]scale=iw/4:-1:flags=lanczos[pip2]; \
 [3:v]scale=iw/4:-1:flags=lanczos[pip3]; \
 [0:v][pip1]overlay=main_w-overlay_w-10:main_h-overlay_h-10[bg1]; \
 [bg1][pip2]overlay=(main_w-overlay_w)/2:main_h-overlay_h-10[bg2]; \
 [bg2][pip3]overlay=10:main_h-overlay_h-10,format=yuv420p[v]" \
-map "[v]" -tune zerolatency -vcodec h264_nvenc -gpu 0 -preset llhq -tune ull -rc:v cbr -b:v 2500K -rc cbr_ld_hq -profile:v baseline  -delay:v 0  -an \
        -f flv rtmp://ant-media-server.cloud.vtti.vt.edu/WebRTCAppEE/gst_test


  


  ffmpeg reports only 15 fps when the sources provide 30fps wondering what can be done to improve that

  


  

  


  Initial start-up messages from ffmpeg


  


• Decode frame sequence exception while NVIDIA GPU is used for H265 video decoding acceleration [closed]

  17 août 2023, par uproar

  We are using NVIDIA GPUs (model : GTX1050TI) to accelerate H.265 video decoding and rendering, and DXVA2 hardware acceleration is used. The version of FFmpeg is 4.2.2.
If the video is played for a long time, there will be frame skipping forward (that is, the video frame of the first few seconds will appear when it is played in normal order), and it will always exist after it appears, and it will not heal itself.
Has anyone been in the same situation or can anyone help ?

  


  We checked the rendering and playback timing of each frame and found that no forward jump occurred. Therefore, the data decoded by the GPU may be incorrect.
We also used AMD GPUs for comparison tests, but this is not the case with AMD GPUs.