Model input-output names, no problem on TRT 7.3.1 , but ends up with an error with TRT 8.0.1

Autonomous Machines Jetson & Embedded Systems Jetson Nano
#1

Hi there.
I am running a pre-trained and pre-optimized and serialized model on jetson nano in the .Uff format. it is a Tensorflow developed model, and is converted from a .pb model saved model.
The problem arises when I tend to run the model, and I do not know the names of the input and output of the model. I improvised some names, it accepts the input’s name and rejects the output name, and fortunately worked for my jetson nano at hand (a developer kit) with:
python 3.6.9
TensorRT 7.3.1
CUDA 4.5.3-dev
JetPack v.4.5.1 (L4T 32.5.1)
python 3.6.9

the model runs at the end and gives me the right output, even with the wrong output_name provided, and the clear error about the wrong output name before running the model.
The problem starts when trying to replicate the working solution on another jetson nano kit, the TensorRT gives me the same error about not finding the model’s output name (just like before) but this time kills the program immediately.
the new jetson nano has:

Ubuntu 18.04.5 LTS
Jetpack 4.6 (L4T 32.6.1)
TensorRT 8.0.1
CUDA 4.1.1
python 3.6.9

Thanks for your help in advance.

#3

Hi,

Do you have the correct output name?
If yes, would you mind trying the TensorRT 8.0 with the correct output flag?

Thanks.

#4

Hi. well, the whole problem is the output name. I don’t have access to the model names and properties because I’m deploying a pre-trained and made TRT compatible for jetson nano. I haven’t found the possibility to explore the model’s characteristics via the TRT’s python API, so, stuck at this point!

#5

I have just read about the deprecation of the UFF and Caffe parsers from the TensorRT 8.0 onwards! I would appreciate any information regarding this change among TR versions and my problem, which I am exactly using a UFF format for my model.

#6

Hi,

When running convert_to_uff.py, you can use -t flag to get the layer name of the whole model.
Would you mind checking if you can find out the output layer with the tool?

Thanks.

#7

Hi, AastaLLL, and thanks for your response.
If you take another look at my problem definition, there is mentioned that I am not converting anything into the .UFF format. the model is ALREADY converted, in fact, that itself is the bottleneck, otherwise, I had access to the model properties via TF and I could get the names. but that’s not the case.

#8

Hi,

So you only have the uff file and it can work with TRT 7 but fail with TRT 8.
Is that correct?

If yes, would you mind sharing the file with us?
We need to run it locally before giving a further suggestion.

Thanks.

#9

That is completely true.
Here you are the model’s .uff file and the class labels file.

class_labels.txt (10 Bytes)
fire_detector.uff (56.1 MB)