When I run the following command with DS6.1 using file source, the FPS goes to 0 before all data is inferred, and only the actual inferred seconds are output to the video.
When using the nvstreammux property sync-inputs, it seems to only work for live sources, can it be used for file sources?
https://forums.developer.nvidia.com/t/deepstream-audio-with-sync-inputs/290725/3?u=y.majima
If it is possible to use it, please let me know how to set it up correctly.
command
USE_NEW_NVSTREAMMUX=yes gst-launch-1.0 -e uridecodebin uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.mp4 ! m.sink_0 nvstreammux name=m batch-size=1 sync-inputs=1 ! nvinfer config-file-path=/opt/nvidia/deepstream/deepstream/samples/configs/deeps
tream-app/config_infer_primary.txt ! nvdslogger ! nvvideoconvert ! nvdsosd ! nvstreamdemux name=demux demux.src_0 ! nvvideoconvert ! nvv4l2h264enc ! h264parse ! qtmux ! filesink location=out.mp4
max_fps_dur 8.33333e+06 min_fps_dur 2e+08
Setting pipeline to PAUSED ...
0:00:02.480207329 754 0x5558e68ccd30 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40
0:00:02.497471382 754 0x5558e68ccd30 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine
0:00:02.503941560 754 0x5558e68ccd30 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<nvinfer0> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/config_infer_primary.txt sucessfully
Pipeline is PREROLLING ...
max_fps_dur 8.33333e+06 min_fps_dur 2e+08
Redistribute latency...
Pipeline is PREROLLED ...
Setting pipeline to PLAYING ...
New clock: GstSystemClock
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
**PERF : FPS_0 (0.00)
Got EOS from element "pipeline0".
Execution ended after 0:00:48.240668324
Setting pipeline to PAUSED ...
Setting pipeline to READY ...
Setting pipeline to NULL ...
Freeing pipeline ...