Getting error as Cuda Runtime(invalid argument)

I am getting the error when I executed my script. The script is attached

[TensorRT] INTERNAL ERROR: [defaultAllocator.cpp::free::85] Error Code 1: Cuda Runtime (invalid argument)

Environment

link.txt (185 Bytes)
The Jetson Nano board from NVIDIA
TensorRT Version: 8.0.1.6
GPU Type: GPU present on the Jetson Nano board
Nvidia Driver Version: -NA-
CUDA Version: -NA-
CUDNN Version: -NA-
Operating System + Version: Linux ubuntu 4.9.253-tegra #2 SMP PREEMPT Tue Nov 29 18:32:41 IST 2022 aarch64 aarch64 aarch64 GNU/Linux
Python Version (if applicable): 3.6
TensorFlow Version (if applicable): -NA-
PyTorch Version (if applicable): -NA-
Baremetal or Container (if container which image + tag): -NA-

Relevant Files

Files uploaded are
pytorch_tensorrt.py, link.txt and resnet_engine_pytorch_fp16.trt
The link.txt provides the link using which I have created the onnx model which was used to create the resnet_engine_pytorch_fp16.trt
The file resnet_engine_pytorch_fp16.trt is created using trtexec command on the jetson nano from the onnx file resnet50_pytorch.onnx
The onnx model is created using the link which is present in the attached file link.txt
link.txt (185 Bytes)

The trtexec command is used as below
trtexec --onnx=resnet50_pytorch.onnx --saveEngine=resnet_engine_pytorch_fp16.trt --explicitBatch --inputIOFormats=fp16:chw --outputIOFormats=fp16:chw --fp16
link.txt (185 Bytes)

resnet_engine_pytorch_fp16.trt (49.3 MB)
pytorch_to_tensorrt.py (322 Bytes)

Steps To Reproduce

  1. Place the file resnet_engine_pytorch_fp16.trt in the same directory where the script pytorch_tensorrt.py is present
  2. Execute the script with the command
    python3.6 pytorch_tensorrt.py

resnet_engine_pytorch_fp16.trt (49.3 MB)
pytorch_to_tensorrt.py (322 Bytes)

Hi @trivedi.nagaraj ,

This topic belongs in the Jetson Nano category. I will go ahead and move it over for you so the team has visibility.

Hi Tom, let me know where to check the Jetson Nano related messages.
Request you to point me to the link.

Hi @trivedi.nagaraj

You can find all the Jetson forums here: Latest Autonomous Machines/Jetson & Embedded Systems topics - NVIDIA Developer Forums

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.