TensorRT Inferencing : gives error 719 after context.execute( )

AI & Data Science Deep Learning (Training & Inference) Frameworks
,
1

I am new to nvidia platform ( jetson nano )
I have trained yolov5 model (.pt) for object detection and then created onnx and .plan file .
I am trying to do inferencing but I am getting an error below. I have also attached detailed output here error (5.0 KB)

PWN(Sigmoid_230, Mul_231): 0.194115ms
Conv_269: 0.223125ms
[TensorRT] ERROR: engine.cpp (725) - Cuda Error in reportTimes: 719 (unspecified launch failure)
[TensorRT] ERROR: INTERNAL_ERROR: std::exception
[TensorRT] ERROR: engine.cpp (986) - Cuda Error in executeInternal: 719 (unspecified launch failure)
[TensorRT] ERROR: FAILED_EXECUTION: std::exception
transfering back from GPU to Host
[TensorRT] ERROR: engine.cpp (179) - Cuda Error in ~ExecutionContext: 719 (unspecified launch failure)
[TensorRT] ERROR: INTERNAL_ERROR: std::exception
[TensorRT] ERROR: Parameter check failed at: …/rtSafe/safeContext.cpp::terminateCommonContext::155, condition: cudnnDestroy(context.cudnn) failure.
[TensorRT] ERROR: Parameter check failed at: …/rtSafe/safeContext.cpp::terminateCommonContext::165, condition: cudaEventDestroy(context.start) failure.
[TensorRT] ERROR: Parameter check failed at: …/rtSafe/safeContext.cpp::terminateCommonContext::170, condition: cudaEventDestroy(context.stop) failure.
[TensorRT] ERROR: …/rtSafe/safeRuntime.cpp (32) - Cuda Error in free: 719 (unspecified launch failure)
terminate called after throwing an instance of ‘nvinfer1::CudaError’
what(): std::exception
Aborted (core dumped)

2

Bro the same with you !

[TensorRT] WARNING: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
StatefulPartitionedCall/sequential/conv2d/BiasAdd__6: 0.067396ms
StatefulPartitionedCall/sequential/conv2d/BiasAdd: 0.158542ms
StatefulPartitionedCall/sequential/conv2d/Elu: 0.055729ms
StatefulPartitionedCall/sequential/conv2d_1/BiasAdd: 0.326719ms
StatefulPartitionedCall/sequential/conv2d_1/Elu: 0.025885ms
StatefulPartitionedCall/sequential/conv2d_2/BiasAdd: 0.145729ms
StatefulPartitionedCall/sequential/conv2d_2/Elu: 0.016771ms
[TensorRT] ERROR: engine.cpp (725) - Cuda Error in reportTimes: 719 (unspecified launch failure)
[TensorRT] ERROR: INTERNAL_ERROR: std::exception
[TensorRT] ERROR: engine.cpp (986) - Cuda Error in executeInternal: 719 (unspecified launch failure)
[TensorRT] ERROR: FAILED_EXECUTION: std::exception
[TensorRT] ERROR: engine.cpp (179) - Cuda Error in ~ExecutionContext: 719 (unspecified launch failure)
[TensorRT] ERROR: INTERNAL_ERROR: std::exception
[TensorRT] ERROR: Parameter check failed at: ../rtSafe/safeContext.cpp::terminateCommonContext::155, condition: cudnnDestroy(context.cudnn) failure.
[TensorRT] ERROR: Parameter check failed at: ../rtSafe/safeContext.cpp::terminateCommonContext::165, condition: cudaEventDestroy(context.start) failure.
[TensorRT] ERROR: Parameter check failed at: ../rtSafe/safeContext.cpp::terminateCommonContext::170, condition: cudaEventDestroy(context.stop) failure.
[TensorRT] ERROR: ../rtSafe/safeRuntime.cpp (32) - Cuda Error in free: 719 (unspecified launch failure)
terminate called after throwing an instance of 'nvinfer1::CudaError'
  what():  std::exceptio