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 are the dataset for dogs and cats breed:

1.  Dog breeds:

Breed	Total
American Bulldog	200
American Pit Bull Terrier	200
Basset Hound	200
Beagle	200
Boxer	199
Chihuahua	200
English Cocker Spaniel	196
English Setter	200
German Shorthaired	200
Great Pyrenees	200
Havanese	200
Japanese Chin	200
Keeshond	199
Leonberger	200
Miniature Pinscher	200
Newfoundland	196
Pomeranian	200
Pug	200
Saint Bernard	200
Samoyed	200
Scottish Terrier	199
Shiba Inu	200
Staffordshire Bull Terrier...