Skip to content

Files

Latest commit

 

History

History

Image Segmentation Tutorial - Unet - Pet Dataset

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 

Image Segmentation Tutorial - Unet - Pet Dataset

Complete Video Tutorial: https://youtu.be/ceUvzxgyop0

Dataset Download Link: https://www.kaggle.com/datasets/tanlikesmath/the-oxfordiiit-pet-dataset

Project Information

This tutorial will guide you through the process of performing image segmentation using the U-Net architecture on a pet dataset. U-Net is a popular convolutional neural network architecture specifically designed for semantic segmentation tasks.

The Oxford-IIIT Pet Dataset is a 37 category pet dataset with roughly 200 images for each class created by the Visual Geometry Group at Oxford. The images have a large variations in scale, pose and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel level trimap segmentation.

Libraries

  • tensorflow
  • keras
  • numpy

Model Architecture

  • U-Net