Yolov4 TensorRT engine DGPU & Jetson

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Both
• DeepStream Version 5
• JetPack Version (valid for Jetson only) 4.4
• TensorRT Version 7.0 for DGPU and 7.1 for Jetpack
• NVIDIA GPU Driver Version (valid for GPU only) 450
• Issue Type( questions, new requirements, bugs) questions
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) I have followed the steps at https://github.com/NVIDIA-AI-IOT/yolov4_deepstream/blob/master/deepstream_yolov4/README.md and created a tensorRT engine that works and runs on a DGPU. When I use the exact same model and config on a Jetson NX Xavier I get

ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:934 failed to build network since there is no model file matched.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:872 failed to build network.
0:00:20.557493110 12988 0x5608854d5e40 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1735> [UID = 1]: build engine file failed
0:00:20.557510437 12988 0x5608854d5e40 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1821> [UID = 1]: build backend context failed
0:00:20.557520575 12988 0x5608854d5e40 ERROR                nvinfer gstnvinfer.cpp:613:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1148> [UID = 1]: generate backend failed, check config file settings

I have tried to use a static batch size tensorRT built model and still get the same errors. Do I have to build the model on a Jetson to use it on the Jetson? Is this due to different TensorRT version on DGPU deepstream 7.0 and 7.1 on Jetpack 4.4?

Hi,
You need to build the engine for different platform, here is dGPU and iGPU (NX)

Works well, a fair bit more work to build model on Jetson with onxx runtime and pytorch for Jetson but worth it in the end