# Deepstream implementation **URL:** \ **Category:** DeepStream SDK\ **Created:** [May 21, 2022, 7:36am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142 "2022-05-21T07:36:53Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![user53799](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user53799](https://forums.developer.nvidia.com/u/user53799)\ **Post date:** [May 21, 2022, 7:36am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/1 "2022-05-21T07:36:53Z")
P configuration as below: **• Hardware Platform (Jetson / GPU)** jetson NX **• DeepStream Version** 6.0.1 **• JetPack Version (valid for Jetson only)** 4.6.2 **• TensorRT Version** 8.2.1.8 sudo /usr/src/tensorrt/bin/trtexec --refit --sparsity=enable --ifp16 --best --saveEngine=yolov5s\_custom\_fp16.engine --onnx=best.onnx --device=0 --plugins I already got a engine file, how can i put into the deepstream pipline? (py3) shisun@nx:~/DeepStream-Yolo$ deepstream-app -c deepstream\_app\_config.txt Using winsys: x11 0:00:05.416749790 27837 0x2f8a8670 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/home/shisun/DeepStream-Yolo/yolov5s\_fp16.engine INFO: [Implicit Engine Info]: layers num: 5 0 INPUT kHALF images 3x640x640 1 OUTPUT kHALF 490 3x80x80x6 2 OUTPUT kHALF 558 3x40x40x6 3 OUTPUT kHALF 626 3x20x20x6 4 OUTPUT kFLOAT output 25200x6 0:00:05.444020002 27837 0x2f8a8670 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /home/shisun/DeepStream-Yolo/yolov5s\_fp16.engine 0:00:05.462007896 27837 0x2f8a8670 INFO nvinfer gstnvinfer\_impl.cpp:313:notifyLoadModelStatus:\ [UID 1]: Load new model:/home/shisun/DeepStream-Yolo/config\_infer\_primary\_yoloV5.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) \*\*PERF: 0.00 (0.00) \*\* INFO: \: Pipeline ready Opening in BLOCKING MODE NvMMLiteOpen : Block : BlockType = 260 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NvMMLiteBlockCreate : Block : BlockType = 260 \*\* INFO: \: Pipeline running 0:00:05.946443823 27837 0x2f19fe80 ERROR nvinfer gstnvinfer.cpp:1150:get\_converted\_buffer:\ cudaMemset2DAsync failed with error cudaErrorIllegalAddress while converting buffer 0:00:05.947321591 27837 0x2f19fe80 WARN nvinfer gstnvinfer.cpp:1472:gst\_nvinfer\_process\_full\_frame:\ error: Buffer conversion failed ERROR from primary\_gie: Buffer conversion failed Debug info: /dvs/git/dirty/git-master\_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1472): gst\_nvinfer\_process\_full\_frame (): /GstPipeline:pipeline/GstBin:primary\_gie\_bin/GstNvInfer:primary\_gie Quitting ERROR: Failed to add cudaStream callback for returning input buffers, cuda err\_no:77, err\_str:cudaErrorIllegalAddress ERROR: Preprocessor transform input data failed., nvinfer error:NVDSINFER\_CUDA\_ERROR 0:00:05.981711511 27837 0x2f280450 WARN nvinfer gstnvinfer.cpp:1324:gst\_nvinfer\_input\_queue\_loop:\ error: Failed to queue input batch for inferencing Segmentation fault (core dumped) ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [May 23, 2022, 7:26am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/3 "2022-05-23T07:26:34Z")
> **• JetPack Version (valid for Jetson only)** > 4.6.2 > **• TensorRT Version** > 8.2.1.8 Jetpack 4.6.2 includes TensorRT 8.0.1, please use the compatible version. ---
**Author:** ![user53799](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user53799](https://forums.developer.nvidia.com/u/user53799)\ **Post date:** [May 23, 2022, 8:18am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/4 "2022-05-23T08:18:34Z")
Thank you for reply. and do you mean I should uninstall tensorrt 8.2.1.8 and install 8.0.1? please give me a hint. thx. ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [May 23, 2022, 9:25am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/5 "2022-05-23T09:25:14Z")
Sorry for above. Jetpack 4.6 includes TensorRT 8.0.1 Jetpack 4.6.1 includes TensorRT 8.2.1 Please check which Jetpack version you used, and use compatible TensorRT version accordingly. ---
**Author:** ![user53799](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user53799](https://forums.developer.nvidia.com/u/user53799)\ **Post date:** [May 23, 2022, 10:05am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/6 "2022-05-23T10:05:20Z")
Thanks again, I am trying. ---
**Author:** ![user53799](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user53799](https://forums.developer.nvidia.com/u/user53799)\ **Post date:** [May 28, 2022, 4:02am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/7 "2022-05-28T04:02:02Z")
I reflashed jetson nx to jetpack4.6 and it not worked yet. But the error appeared different: deepstream-app -c deepstream\_app\_config.txt Using winsys: x11 0:00:05.465532190 21034 0xf7b1f50 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() \ [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/sources/DeepStream-Yolo/./best\_exp.engine INFO: [Implicit Engine Info]: layers num: 5 0 INPUT kHALF images 3x640x640 1 OUTPUT kHALF 490 3x80x80x6 2 OUTPUT kHALF 558 3x40x40x6 3 OUTPUT kHALF 626 3x20x20x6 4 OUTPUT kFLOAT output 25200x6 0:00:05.465893821 21034 0xf7b1f50 INFO nvinfer gstnvinfer.cpp:638:gst\_nvinfer\_logger:\ NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() \ [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/sources/DeepStream-Yolo/./best\_exp.engine 0:00:05.475766009 21034 0xf7b1f50 INFO nvinfer gstnvinfer\_impl.cpp:313:notifyLoadModelStatus:\ [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-6.0/sources/DeepStream-Yolo/config\_infer\_primary\_yoloV5.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) \*\*PERF: 0.00 (0.00) \*\* INFO: \: Pipeline ready Opening in BLOCKING MODE NvMMLiteOpen : Block : BlockType = 260 NVMEDIA: Reading vendor.tegra.display-size : status: 6 NvMMLiteBlockCreate : Block : BlockType = 260 \*\* INFO: \: Pipeline running WARNING: Num classes mismatch. Configured: 1, detected by network: 0 deepstream-app: nvdsparsebbox\_Yolo.cpp:137: bool NvDsInferParseCustomYolo(const std::vector&, const NvDsInferNetworkInfo&, const NvDsInferParseDetectionParams&, std::vector&, const uint&, const uint&): Assertion `layer.inferDims.numDims == 3’ failed. Aborted (core dumped) ---
**Author:** ![Fiona.Chen](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/fiona.chen/32/15508_2.png) [@Fiona.Chen](https://forums.developer.nvidia.com/u/Fiona.Chen)\ **Post date:** [June 1, 2022, 7:23am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/8 "2022-06-01T07:23:30Z")
> [@user53799](#): > > deepstream-app: nvdsparsebbox\_Yolo.cpp:137: bool NvDsInferParseCustomYolo(const std::vector&, const NvDsInferNetworkInfo&, const NvDsInferParseDetectionParams&, std::vector&, const uint&, const uint&): Assertion `layer.inferDims.numDims == 3’ failed. > Aborted (core dumped) Please customize the Yolov5 postprocessing function(bbox parser function) by yourself. The Yolov4 postprocessing customization function can be a reference. [deepstream\_tao\_apps/post\_processor/nvdsinfer\_custombboxparser\_tao.cpp at master · NVIDIA-AI-IOT/deepstream\_tao\_apps · GitHub](https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps/blob/master/post_processor/nvdsinfer_custombboxparser_tao.cpp) ---
**Author:** ![user53799](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@user53799](https://forums.developer.nvidia.com/u/user53799)\ **Post date:** [June 2, 2022, 3:03am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/9 "2022-06-02T03:03:27Z")
Thank you. ---
**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\ **Post date:** [June 16, 2022, 3:04am UTC](https://forums.developer.nvidia.com/t/deepstream-implementation/215142/10 "2022-06-16T03:04:07Z")
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.