Dog Breed Classifier in PyTorch

This is a repo for the Dog Breed Classifier Project in Udacity Nanodegree

It is implemented by using PyTorch library.

Project Overview

Welcome to the Convolutional Neural Networks (CNN) project in the Deep learning Nanodegree! In this project, you will learn how to build a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, your algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.

Along with exploring state-of-the-art CNN models for classification and localization, you will make important design decisions about the user experience for your app. Our goal is that by completing this lab, you understand the challenges involved in piecing together a series of models designed to perform various tasks in a data processing pipeline. Each model has its strengths and weaknesses, and engineering a real-world application often involves solving many problems without a perfect answer. Your imperfect solution will nonetheless create a fun user experience!

Import Datasets

• Download the dog dataset
• Download the human_dataset

CNN Structures (Building a model on my own)

---

    Layer (type)               Output Shape         Param 

        Conv2d-1         [-1, 16, 224, 224]             448
        
        Conv2d-2         [-1, 32, 112, 112]           4,640
        
        Conv2d-3           [-1, 64, 56, 56]          18,496
        
        Conv2d-4          [-1, 128, 28, 28]          73,856
        
        Linear-5                  [-1, 500]      12,544,500
        
        Linear-6                  [-1, 133]          66,633

Transfer Learnings

Used VGG16 for transfer learnings