Convert onnx model to tensorrt

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano
1

@dusty_nv
hello
I trained a model in docker container (jetson-inference) and converted to the .onnx format now when I want to use a model with detecnet and convert it to tensorRT engine and predict a video
command: detectnet --model=models/SatModel/ssd-mobilenet.onnx --labels=data/SatData/labels.txt --input-blob=input_0 --ouput-cvg=scores --output-bbox=boxes data/videos/T1_East.mp4
it gives me a this Error:

[TRT]       binding 0
                -- index   0
                -- name    'input_0'
                -- type    FP32
                -- in/out  INPUT
                -- # dims  4
                -- dim #0  1
                -- dim #1  3
                -- dim #2  300
                -- dim #3  300
[TRT]       binding 1
                -- index   1
                -- name    'scores'
                -- type    FP32
                -- in/out  OUTPUT
                -- # dims  3
                -- dim #0  1
                -- dim #1  3000
                -- dim #2  3
[TRT]       binding 2
                -- index   2
                -- name    'boxes'
                -- type    FP32
                -- in/out  OUTPUT
                -- # dims  3
                -- dim #0  1
                -- dim #1  3000
                -- dim #2  4
[TRT]    
[TRT]    binding to input 0 input_0  binding index:  0
[TRT]    binding to input 0 input_0  dims (b=1 c=3 h=300 w=300) size=1080000
[TRT]    3: Cannot find binding of given name: coverage
[TRT]    failed to find requested output layer coverage in network
[TRT]    device GPU, failed to create resources for CUDA engine
[TRT]    failed to create TensorRT engine for models/SatModel/ssd-mobilenet.onnx, device GPU
[TRT]    detectNet -- failed to initialize.
detectnet:  failed to load detectNet model

what can I do with that ?!
I try many ways, but…

3

Hi,

Do you enable the Nvidia plugin when launching the container? (--runtime nvidia)
Thanks.

4

@AastaLLL
No, but I Trained a model on a custom dataset before and don’t have any problem.

5

Hi,

Please give it a try.
On Jetson, some CUDA-related library is mounted.

Thanks.

1 Like
6

thank you,
that solved my problem

8

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