This is a PyTorch Tutorial to Object Detection.

This is the fourth in a series of tutorials I plan to write about implementing cool models on your own with the amazing PyTorch library.

Basic knowledge of PyTorch, convolutional neural networks is assumed.

If you're new to PyTorch, first read Deep Learning with PyTorch: A 60 Minute Blitz and Learning PyTorch with Examples.

Questions, suggestions, or corrections can be posted as issues.

I'm using PyTorch 0.4 in Python 3.6.

Objective

Concepts

Overview

Implementation

Training

Inference

Frequently Asked Questions

To build a model that can detect and localize specific objects in images.

We will be implementing the Single Shot Multibox Detector (SSD), a popular, powerful, and especially nimble network for this task. The authors' original implementation can be found here.

Here are a few examples of object detection in images not seen during training:

There will be more examples at the end of the tutorial.

I am still writing this tutorial.

In the meantime, you could take a look at the code – it works!

We achieve an mAP of 77.1 (against 77.2 in the paper) on VOC2007-test.