jeffqjiangNew
3230cca447
* * rocDecode: Initial check in for decode buffer pool.
* * rocDecode: All 135 streams pass.
* * rocDecode: Fixed a build error in debug mode.
* * rocDecode/HEVC: Removed two workaround in HEVC DPB management, after decode buffer pool implementa
tion.
- WR 1: Conditional bumping (when max_num_reorder_pics > 0) to avoid synchronous job submission in
C.5.2.3.
- WR 2: Add two more buffers in DPB to avoid buffer over-writing.
* * rocDecode/HEVC: Added display delay feature.
* * rocDecode/HEVC: Fixed the -z option issue within the context of the new decode buffer pool implementation.
* * rocDecode/HEVC: Removed redundent code.
* * rocDecode/AVC: Added decode buffer pool implementation for AVC.
* * rocDecode: Added a few changes.
- Added display delay feature to AVC.
- Removed a workaround for AVC: AVC_MAX_DPB_FRAMES was increased to 18. Now it is back to 16.
- Removed a workaround for AVC: increased DPB buffer size by 2. Now it is back to normal.
- Code format changes for HEVC.
* * rocDecode/AVC: Fixed the -z option issue within the context of the new decode buffer pool implementation.
* * rocDecode: Merged OutputDecodedPictures() method to upper class RocVideoParser.
* * rocDecode: Code cleanup. No functional changes.
* * rocDecode: Made decode buffer pool size adaptive.
- Removed the hard coded decode buffer pool size set in the decoder.
- Exposed the display delay parameter from RocVideoDecoder class to the user.
- Now the decoder buffer pool size is determined from the DPB buffer size and display delay parameter.
* * rocDecode: Several changes based on code review.
- Merged decode and display use status into one parameter.
- Removed the surface index from DecodeFrameBuffer, which is now implicitly referred by the array index.
- Changed a function name for better clarity.
* * rocDecode: Added a comment.
[ROCm/rocdecode commit: 61c8661b9c]
Video decode sample
The video decode sample illustrates decoding a single packetized video stream using FFMPEG demuxer, video parser, and rocDecoder to get the individual decoded frames in YUV format. This sample can be configured with a device ID and optionally able to dump the output to a file. This sample uses the high-level RocVideoDecoder class which connects both the video parser and Rocdecoder. This process repeats in a loop until all frames have been decoded.
Prerequisites:
-
Install rocDecode
-
- On
Ubuntu
sudo apt install ffmpeg libavcodec-dev libavformat-dev libavutil-dev- On
RHEL/SLES- install ffmpeg development packages manually or use rocDecode-setup.py script
- On
Build
mkdir video_decode_sample && cd video_decode_sample
cmake ../
make -j
Run
./videodecode -i <input video file [required]>
-o <output path to save decoded YUV frames [optional]>
-d <GPU device ID - 0:device 0 / 1:device 1/ ... [optional - default:0]>
-f <Number of decoded frames - specify the number of pictures to be decoded [optional]>
-z <force_zero_latency - Decoded frames will be flushed out for display immediately [optional]>
-disp_delay <display delay - specify the number of frames to be delayed for display [optional]>
-sei <extract SEI messages [optional]>
-md5 <generate MD5 message digest on the decoded YUV image sequence [optional]>
-md5_check MD5_File_Path <generate MD5 message digest on the decoded YUV image sequence and compare to the reference MD5 string in a file [optional]>
-crop <crop rectangle for output (not used when using interopped decoded frame) [optional - default: 0,0,0,0]>
-m <output_surface_memory_type - decoded surface memory [optional - default: 0][0 : OUT_SURFACE_MEM_DEV_INTERNAL/ 1 : OUT_SURFACE_MEM_DEV_COPIED/ 2 : OUT_SURFACE_MEM_HOST_COPIED/3 : OUT_SURFACE_MEM_NOT_MAPPED]>