Welcome to 'YOLO: Custom Object Detection in Python'

Object Detection is the most used applications of Computer Vision, where computer/machine can able to locate and classify the object in an image.

In this course we specifically using YOLO (You Only Look Once) and powerful and popular unified object detection model. YOLO uses neural networks to provide real-time object detection. This algorithm is popular because of its speed and accuracy. It has been used in various applications to detect traffic signals, people, parking meters, and animals.

This course is divided into two halves. The first half deals with object detection with custom dataset where we will locate 20 classes of objects. And in second half we will create an web app and give the Graphical User Interphase experience to the use. Not only that we will also deploy our model in Cloud platform.

Now let us see the topics in the course

1. Introductory theory session about YOLO Object Detection

After that, we are ready to proceed with preparing our computer for Python coding by downloading and installing the Python package and will check and see if everything is installed fine.

• 2. Data Preparation for YOLO model

          a.   Thumb rules to follow in Collect Data

          b.   Label image for  object detection: Here we will use LabelImg tool which is an open source tool to label the label.

          c.   Parse data from XML files and extract information like filename, size, bounding box info like (xmin, xmax, ymin, ymax)

          d.   Process the data from XML in pandas dataframe. And then split the image and save the respective label information into train and test set.

3.  Train YOLO v5 Model

• We will train the YOLO model in Google Colab GPU environment.
• Understand the evaluation metrics from the Model results.

4.  Get Prediction

• Create a pipeline for predictions. 
• Here we will load the model in OpenCV Python and get the detection with OpenCV.

That's all about the topics which are currently included in this quick course. The code, images and weights used in this course has been uploaded and shared in a folder. I will include the link to download them in the last session or the resource section of this course. You are free to use the code in your projects with no questions asked.