Running engine file on jetson nano using deep stream

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Hello, I am trying to run a custom Faster_rcnn model which I trained on my laptop. I copied the engine file to Jetson Nano and tried running on Jetson using deep stream. I created a Config file and ran it using deepstream-app -c. I am a neophyte in deep stream and deep learning. Can anyone help me solve these errors ?

Thank you,

Creating LL OSD context new
0:00:01.332581373 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): The engine plan file is not compatible with this version of TensorRT, expecting library version 5.1.6 got 5.1.5, please rebuild.
0:00:01.332696113 5690 0x3b85e730 WARN nvinfer gstnvinfer.cpp:515:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:useEngineFile(): Failed to create engine from file
0:00:01.333127055 5690 0x3b85e730 INFO nvinfer gstnvinfer.cpp:519:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:initialize(): Trying to create engine from model files
Weights for layer conv1_1 doesn’t exist
0:00:01.360603104 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): CaffeParser: ERROR: Attempting to access NULL weights
Weights for layer conv1_1 doesn’t exist
0:00:01.360655657 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): CaffeParser: ERROR: Attempting to access NULL weights
0:00:01.360706334 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): Parameter check failed at: …/builder/Network.cpp::addConvolution::104, condition: kernelWeights.values != nullptr
error parsing layer type Convolution index 0
0:00:01.360753262 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:generateTRTModel(): Failed while parsing network
0:00:01.360944045 5690 0x3b85e730 ERROR nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:initialize(): Failed to create engine from model files
0:00:01.361002118 5690 0x3b85e730 WARN nvinfer gstnvinfer.cpp:692:gst_nvinfer_start:<primary_gie_classifier> error: Failed to create NvDsInferContext instance
0:00:01.361040452 5690 0x3b85e730 WARN nvinfer gstnvinfer.cpp:692:gst_nvinfer_start:<primary_gie_classifier> error: Config file path: /home/jn1/deepstream_sdk_v4.0.1_jetson/samples/configs/deepstream-app/config_infer_primary_nano_copy.txt, NvDsInfer Error: NVDSINFER_TENSORRT_ERROR
** ERROR: main:651: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie_classifier: Failed to create NvDsInferContext instance
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(692): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie_classifier:
Config file path: /home/jn1/deepstream_sdk_v4.0.1_jetson/samples/configs/deepstream-app/config_infer_primary_nano_copy.txt, NvDsInfer Error: NVDSINFER_TENSORRT_ERROR
App run failed

2

See the error:
The engine plan file is not compatible with this version of TensorRT, expecting library version 5.1.6 got 5.1.5, please rebuild.

Did you follow GitHub - NVIDIA-AI-IOT/deepstream_4.x_apps: deepstream 4.x samples to deploy TLT training models ?

3

Also , where did you genenrate the trt engine?
Note that if you want to run trr engine in nano, please generate trt engine in nano instead of PC.

4

Hi vishwasrajput66,

We haven’t heard back from you in a couple weeks, so marking this topic closed.
Please open a new forum issue when you are ready and we’ll pick it up there.