How to run my own mobilenetv2 model on Nano?

AmateurPirate · October 2, 2020, 8:57pm

It seems like a straightforward enough task, but from searching I was unable to find a comprehensive guide on how to do this.

I’ve got a trained tf2 mobilenetv2 binary image classifier saved in h5 format. I just need it to perform inference @2 fps or so on a saved image.

Are there any step-by-step guides on how to get a tf2 model saved in h5 format running in TRT on the Jetson? If not, can someone please help.

Much appreciated!

AastaLLL · October 5, 2020, 7:51am

Hi,

We have couples of examples for mobilenetv2:

1. Only Inference

/usr/src/tensorrt/samples/sampleUffSSD/

2. Integrate with multimedia interface (Deepstream)

/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD/

3. Gstreamer interface(jetson-inference)

github.com

dusty-nv/jetson-inference/blob/master/docs/detectnet-console-2.md#detecting-objects-from-images

<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
<p align="right"><sup><a href="imagenet-tagging.md">Back</a> | <a href="detectnet-camera-2.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
<br/>
<sup>Object Detection</sup></s></p>

# Locating Objects with DetectNet
The previous recognition examples output class probabilities representing the entire input image.  Next we're going to focus on **object detection**, and finding where in the frame various objects are located by extracting their bounding boxes.  Unlike image classification, object detection networks are capable of detecting many different objects per frame.

<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/detectnet.jpg" >

The [`detectNet`](../c/detectNet.h) object accepts an image as input, and outputs a list of coordinates of the detected bounding boxes along with their classes and confidence values.  [`detectNet`](../c/detectNet.h) is available to use from [Python](https://rawgit.com/dusty-nv/jetson-inference/master/docs/html/python/jetson.inference.html#detectNet) and [C++](../c/detectNet.h).  See below for various [pre-trained detection models](#pre-trained-detection-models-available)  available for download.  The default model used is a [91-class](../data/networks/ssd_coco_labels.txt) SSD-Mobilenet-v2 model trained on the MS COCO dataset, which achieves realtime inferencing performance on Jetson with TensorRT. 

As examples of using the `detectNet` class, we provide sample programs for C++ and Python:

- [`detectnet.cpp`](../examples/detectnet/detectnet.cpp) (C++) 
- [`detectnet.py`](../python/examples/detectnet.py) (Python) 

These samples are able to detect objects in images, videos, and camera feeds.  For more info about the various types of input/output streams supported, see the [Camera Streaming and Multimedia](aux-streaming.md) page.

### Detecting Objects from Images

This file has been truncated. show original

Thanks.

Topic		Replies	Views
Running original tensorflow model for SSD mobilenet v2 with live USB camera capture on jetson nano Jetson Nano	2	1255	October 18, 2021
Loading custom Object Detection Model to Jetson Dev for real-time use Jetson Nano jetson-inference	4	592	October 15, 2021
Real time object detection on Jetson Nano Jetson Nano	7	2618	October 18, 2021
Running SSD mobilenet v2 object detection on saved file Jetson Nano	2	575	October 18, 2021
Own dataset(mobilenet ssd v2) not working - TRT Object Detection TensorRT tensorrt , tensorflow	5	1045	October 12, 2021
Multiple video stream input to SSD Mobilenet V2 TensorRT engine using Deepstream DeepStream SDK tensorrt , ssd	8	1613	October 12, 2021
Running Inference with DeepStream, but with unknown model architecture DeepStream SDK	6	948	October 12, 2021
How to deploy SSD Mobilenet V2 for inference in jetson nano Jetson Nano jetson-inference	2	1312	May 23, 2022
How to use tlt trained model on Jetson Nano TAO Toolkit tensorrt , jetson-inference	7	2088	October 12, 2021
Tensorflow model or onnx on my Jetson Nano Jetson Nano tensorrt , tensorflow , python	4	1319	October 15, 2021

How to run my own mobilenetv2 model on Nano?

1. Only Inference

2. Integrate with multimedia interface (Deepstream)

3. Gstreamer interface(jetson-inference)

Related topics