- deepstream-app version 6.1.0
- DeepStreamSDK 6.1.0
- CUDA Driver Version: 11.4
- CUDA Runtime Version: 11.0
- TensorRT Version: 8.2
- cuDNN Version: 8.4
- libNVWarp360 Version: 2.0.1d3
- Question: When I was using deepstream-test3 for multiple video detection, I found that there was no way to output the correct results of each video channel at the same time.
- The problem: The results of the four channels are jumping from channel 1 to channel 2. Normally, all four channels should have test results at the same time, but it is not the case.
- Test: I did not modify the code of deepstream-test3. I have observed the needle feeding the nfinfer and it is feeding all four frames at the same time.
[property] gpu-id=0 net-scale-factor=0.0039215697906911373 model-color-format=0 custom-network-config=yolov5s.cfg model-file=yolov5s.wts model-engine-file=model_b4_gpu0_fp32.engine #int8-calib-file=calib.table labelfile-path=labels.txt batch-size=4 network-mode=0 num-detected-classes=80 interval=0 gie-unique-id=1 process-mode=1 network-type=0 cluster-mode=4 maintain-aspect-ratio=0 parse-bbox-func-name=NvDsInferParseYolo custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so engine-create-func-name=NvDsInferYoloCudaEngineGet [class-attrs-all] pre-cluster-threshold=0