Training the model for our dataset

In this section, we will work through the process of creating the dataset, fine-tuning the model, and exporting the model for production.

Introduction to the Oxford-IIIT Pet dataset

The Oxford-IIIT Pet dataset contains 37 species of dogs and cats. Each class has 200 images with large variations in scale, pose, and lighting. The ground truth data has annotations for species, head position, and pixel segmentation for each image. In our application, we only use the species name as the class name for the model:

Dataset Statistics

The following...