daoudma
November 1, 2020, 10:29pm
1
hello,
iam new to jetson nano and deep learning, i followed hello AI world tutorial and everything works fine.
but iam facing a problem with training my own ssd-mobilenet, iam not finding any clear tutorial on training from scratch, like labeling type (pascal voc, kitti,…), or how to actually train the model.
i worked with yolov3 on colab and it was easy.
any help?
thanks.
Hi,
Have you checked this tutorial before?
<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="pytorch-collect.md">Back</a> | <a href="pytorch-collect-detection.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
<br/>
<sup>Transfer Learning - Object Detection</sup></s></p>
# Re-training SSD-Mobilenet
Next, we'll train our own SSD-Mobilenet object detection model using PyTorch and the [Open Images](https://storage.googleapis.com/openimages/web/visualizer/index.html?set=train&type=detection&c=%2Fm%2F06l9r) dataset. SSD-Mobilenet is a popular network architecture for realtime object detection on mobile and embedded devices that combines the [SSD-300](https://arxiv.org/abs/1512.02325) Single-Shot MultiBox Detector with a [Mobilenet](https://arxiv.org/abs/1704.04861) backbone.
<a href="https://arxiv.org/abs/1512.02325"><img src="https://github.com/dusty-nv/jetson-inference/raw/dev/docs/images/pytorch-ssd-mobilenet.jpg"></a>
In the example below, we'll train a custom detection model that locates 8 different varieties of fruit, although you are welcome to pick from any of the [600 classes](https://github.com/dusty-nv/pytorch-ssd/blob/master/open_images_classes.txt) in the Open Images dataset to train your model on. You can visually browse the dataset [here](https://storage.googleapis.com/openimages/web/visualizer/index.html?set=train&type=detection).
<img src="https://github.com/dusty-nv/jetson-inference/raw/dev/docs/images/pytorch-fruit.jpg">
To get started, first make sure that you have [JetPack 4.4](https://developer.nvidia.com/embedded/jetpack) or newer and [PyTorch installed](pytorch-transfer-learning.md#installing-pytorch) for **Python 3.6** on your Jetson. JetPack 4.4 includes TensorRT 7.1, which is the minimum TensorRT version that supports loading SSD-Mobilenet via ONNX. And the PyTorch training scripts used for training SSD-Mobilenet are for Python3, so PyTorch should be installed for Python 3.6.
## Setup
> **note:** first make sure that you have [JetPack 4.4](https://developer.nvidia.com/embedded/jetpack) or newer on your Jetson and [PyTorch installed](pytorch-transfer-learning.md#installing-pytorch) for **Python 3.6**
This file has been truncated. show original
This tutorial can guide you to retrain a custom model with ssd_mobilenet .
Thanks.
thank you for the info, do you have any idea about the annotation format of the dataset? is it pascal voc?
thanks.
It supports OpenImages dataset format and Pascal VOC dataset format. For custom datasets, Pascal VOC format is used.