Skip to content

Latest commit

 

History

History
39 lines (24 loc) · 1.1 KB

README.md

File metadata and controls

39 lines (24 loc) · 1.1 KB
Raw

Dog Breed Classification

Cover Picture

An effective deep learning model based on VGG-16 and RESNET50 architectures to classify any dog image from 133 different classes of dogs. Added advantage, you can pass images of humans as well. It is intelligent enough to classify between a human and a dog as too.

Usage

python3 script.py <FULL-PATH-TO-IMAGE-FILE>

Example

python3 script.py /home/mypc/Desktop/pexels-photo-356378.jpeg

IMAGE PATH:  /home/mypc/Desktop/pexels-photo-356378.jpeg
This is dog!
Your breed is most likely ... CANAAN DOG

VGG-16 Architecture

RESNET-50 Architecture

Scope Of Improvement

  • Classify images by passing URLs directly
  • Develop a stable and robust REST API
  • Current accuracy of Dog Breed Classification Sub-Model = 81%. This can be improved