Dog-Breed Classifier using CNN (Pytorch)
This project is a part of Udacity Deep Learning Nanodegree Program.
The aim of this project is to build a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. The code accepts any user-supplied image as input and performs the following tasks:
If supplied an image of a human, the code will identify the resembling dog breed.
Convolutional Neural Network models are used to perform the above classifications.
Python (version 3.6.3)
Jupyter Notebook
Detect Human Faces: OpenCV’s implementation of Haar feature-based cascade classifiers is used to detect human faces in images.
Detect Dogs: Pre-trained VGG-16 model is used to detect dogs.
Create a CNN to Classify Dog Breeds (from Scratch): The CNN is built from scratch to perform the above classification.
Create a CNN to Classify Dog Breeds (using Transfer Learning): Pre-trained VGG-19 model is used for transfer learning.