In this project, I built a CNN abd Transfer Learning based deep learning mini-app that accepts any user-supplied image as input.
- If a dog is detected in the image, it will provide an estimate of the dog's breed.
- If a human is detected, it will provide an estimate of the dog breed that is most resembling.
The main artefacts are:
-dog_app.ipynb : Jupuyter notebook that goes through the process, including:
- Importing Datasets
- Detecting Humans
- Detecting Dogs
- Creating a CNN to Classify Dog Breeds (from Scratch)
- Create a CNN to Classify Dog Breeds (using Transfer Learning)
- Combine all previous steps into a unified system.
- Testing the system on real user-provided images of dogs and humans