How Coding My Own Object Detection Program, but with My Own Models

I have follow the tutorial : jetson-inference/ at master · dusty-nv/jetson-inference · GitHub

And I have make run the detection programe done like this. But I don’t understand how do the same programme but with a model created with the méthode of this tutoriel : jetson-inference/ at master · dusty-nv/jetson-inference · GitHub

How should I do?


Please check the suggestion from the below comment first:


1 Like

I have try to change net, by net = jetson.inference.detectNet(argv=[’–model=/home/jetson-inference/python/training/detection/ssd/model/task_dif_pinces/ssd-mobilenet.onnx’, ‘–labels=~/jetson-inference/python/training/detection/ssd/model/task_dif_pinces/labels.txt’, ‘–input-blob=input_0’, ‘–output-cvg=scores’, ‘–output-bbox=boxes’])

But whene I try to run I have the error :
error: model file ‘/home/jetson-inference/python/training/detection/ssd/model/task_dif_pinces/ssd-mobilenet.onnx’ was not found.
if loading a built-in model, maybe it wasn’t downloaded before.

    Run the Model Downloader tool again and select it for download:

       $ cd <jetson-inference>/tools
       $ ./

[TRT] detectNet – failed to initialize.
jetson.inference – detectNet failed to load network

And I have verify the existance of the file “ssd-mobilenet.onnx” in that model, it existe.


Is the model located at /home/jetson-inference/python/training/detection/ssd/model/task_dif_pinces/?
The error indicates that it cannot find the ONNX model in that folder.

Could you try to verify with the following command?

ll /home/jetson-inference/python/training/detection/ssd/model/task_dif_pinces/ssd-mobilenet.onnx