Learn the five major steps that make up semantic segmentation. First, the Image Labeler app allows you to ground truth label your objects at the pixel level. Then, you create two datastores and partition them into training and test sets. Next, you import a pretrained convolution neural network and modify it to be a semantic segmentation network. Finally, you train and evaluate your network.
To learn more, see the semantic segmentation using deep learning example.
You can also select a web site from the following list:
Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.