Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU): GPU
• DeepStream Version: 6.0
• TensorRT Version: 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only): 495.44
When running the config file with two or more live input streams, quite a number of errors appear. And these error change with the streams (i.e., different combination of streams give different errors.).
Even one single stream, when given as input twice, also gives an error, as given below:
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:1484 Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error 0:00:01.277340488 4200 0x55cc25e6e490 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1889> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed 0:00:01.285283588 4200 0x55cc25e6e490 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1996> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild 0:00:01.285315498 4200 0x55cc25e6e490 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1210 INT8 not supported by platform. Trying FP16 mode. WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.3.0 WARNING: [TRT]: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.5 WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.3.0 WARNING: [TRT]: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.5 0:00:22.442300326 4200 0x55cc25e6e490 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1947> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b2_gpu0_fp16.engine successfully WARNING: [TRT]: TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.3.0 WARNING: [TRT]: TensorRT was linked against cuDNN 8.2.1 but loaded cuDNN 8.0.5 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 0:00:22.457908401 4200 0x55cc25e6e490 INFO nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/content/drive/MyDrive/config_infer_primary.txt sucessfully Runtime commands: h: Print this help q: Quit p: Pause r: Resume NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source. To go back to the tiled display, right-click anywhere on the window. **PERF: FPS 0 (Avg) FPS 1 (Avg) **PERF: 0.00 (0.00) 0.00 (0.00) ** INFO: <bus_callback:194>: Pipeline ready (deepstream-app:4200): GLib-GObject-WARNING **: 15:34:21.554: g_object_set_is_valid_property: object class 'GstNvJpegDec' has no property named 'DeepStream' Using GPU 0 (Tesla P100-PCIE-16GB, 56 SMs, 2048 th/SM max, CC 6.0, ECC on) (deepstream-app:4200): GLib-GObject-WARNING **: 15:34:22.048: g_object_set_is_valid_property: object class 'GstNvJpegDec' has no property named 'DeepStream' Using GPU 0 (Tesla P100-PCIE-16GB, 56 SMs, 2048 th/SM max, CC 6.0, ECC on) **PERF: 0.00 (0.00) 0.00 (0.00) **PERF: 25.33 (3.02) 0.00 (0.00) **PERF: 0.00 (1.05) 0.00 (0.00) ** INFO: <bus_callback:180>: Pipeline running ERROR from sink_sub_bin_mux1: Could not multiplex stream. Debug info: gstqtmux.c(4561): gst_qt_mux_add_buffer (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstQTMux:sink_sub_bin_mux1: Buffer has no PTS. ERROR from src_bin_muxer: memory type configured and i/p buffer mismatch ip_surf 3 muxer 2 Debug info: gstnvstreammux.c(609): gst_nvstreammux_chain (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer Quitting ERROR from sink_bin_queue: Internal data stream error. Debug info: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstQueue:sink_bin_queue: streaming stopped, reason error (-5) 0:00:41.840546862 4200 0x55cc25c610f0 WARN nvinfer gstnvinfer.cpp:2288:gst_nvinfer_output_loop:<primary_gie> error: Internal data stream error. 0:00:41.840564581 4200 0x55cc25c610f0 WARN nvinfer gstnvinfer.cpp:2288:gst_nvinfer_output_loop:<primary_gie> error: streaming stopped, reason error (-5) Cuda failure: status=1 nvbufsurface: Error(-1) in releasing cuda memory App run failed
Here’s the config file:
[application] enable-perf-measurement=1 perf-measurement-interval-sec=5 #gie-kitti-output-dir=streamscl [tiled-display] enable=1 rows=1 columns=2 width=1280 height=720 [source0] enable=1 type=2 uri=http://honjin1.miemasu.net/nphMotionJpeg?Resolution=640x480&Quality=Standard gpu-id=0 cudadec-memtype=0 [source1] enable=1 type=2 uri=http://honjin1.miemasu.net/nphMotionJpeg?Resolution=640x480&Quality=Standard gpu-id=0 cudadec-memtype=0 [sink0] enable=1 type=3 container=1 codec=1 enc-type=0 sync=0 bitrate=20000000 profile=0 output-file=/content/out.mp4 source-id=0 [sink1] enable=0 type=4 codec=1 enc-type=0 sync=0 bitrate=4000000 profile=0 rtsp-port=8554 udp-port=5400 [osd] enable=1 border-width=2 text-size=15 text-color=1;1;1;1; text-bg-color=0;0;0;1 font=Serif show-clock=1 clock-x-offset=0 clock-y-offset=0 clock-text-size=20 clock-color=1;0;0;1 display-mask=1 [primary-gie] enable=1 model-engine-file=/../../models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine batch-size=2 bbox-border-color0=1;0;0;1 bbox-border-color1=0;1;1;1 bbox-border-color2=0;0;1;1 bbox-border-color3=0;1;0;1 interval=0 gie-unique-id=1 config-file=config_infer_primary.txt [streammux] live-source=1 batch-size=2 batched-push-timeout=40000 width=1280 height=720 [tests] file-loop=0