From the course: Hands-On AI: Computer Vision Projects with Ultralytics and OpenCV

Unlock this course with a free trial

Join today to access over 24,700 courses taught by industry experts.

Training and inference for an image-segmentation model

Training and inference for an image-segmentation model - OpenCV Tutorial

From the course: Hands-On AI: Computer Vision Projects with Ultralytics and OpenCV

Start my 1-month free trial Buy for my team

Training and inference for an image-segmentation model

“

- [Narrator] In this video, we will work through how to train the Ultralytics YOLO11 segmentation model on a custom dataset. Image segmentation takes object detection concept a step further, by not only identifying objects in an image, but also separating each one individually from the background and from other objects. The model output include the set of masks or counters for each detected object. Previously, we converted the detection dataset into a segmentation dataset using the Segment Anything model. We will be using the same dataset in this video. All the resources used in this video are available in the Course code subdirectory 03-04. Since we already have our dataset prepared, the next step is to set up the YAML file. Open the data.yaml file located inside 03-04 subdirectory. This is the same YML file we worked with in the video two of this chapter. We will just tweak it a bit to make it suitable for the segmentation model. On line number 1, you will notice that dataset…

Contents