Failed to bind input tensor

Robotics & Edge Computing Jetson & Embedded Systems Jetson AGX Xavier
,
1

Description

When I transform the onnx exported from Pytorch (1.8.0) to DLA TensorRT engine in Xavier ( 5.2.6) with FP16, the error has raised.

Module_id 33 Severity 2: NVMEDIA_DLA 718
Module_id 33 Severity 2: Failed to bind input tensor. err: 0x00000b
Module_id 33 Severity 2: NVMEDIA_DLA 2911
Module_id 33 Severity 2: Failed to bind input tensor args. status: 0x000007

Environment

TensorRT Version: 6.0.1
GPU Type: Xavier Drive OS 5.2.6
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version: 7.6
Operating System + Version: Xavier Drive OS 5.2.6
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 1.8.0
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
2

Hi @wei.tao2,

We recommend you to please post your concern on Jetson & Embedded Systems - NVIDIA Developer Forums to get better help.

Thank you.

4

Hi,

Could you validate the software you used first?
TensorRT doesn’t have a v6.5.0 release.

More, may I know do you use Jetson Xavier or DRIVE Xavier?
For Jetson, it’s recommended to upgrade to our latest JetPack 4.6 which has TensorRT v8.0 and DLA 1.3.6 package.

Thanks.

5

Hi,
TensorRT is 6.0.1 and I user the Drive Xavier.

6

Hi,

Could you file a topic on the DRIVE AGX board first?

Thanks.