Skip to content

Latest commit

 

History

History
35 lines (26 loc) · 1.29 KB

README.md

File metadata and controls

35 lines (26 loc) · 1.29 KB
Raw

Dog-Breed-Classifier

A CNN trained to determine the dog breed based on the face provided in an image

Project Overview

It's the Convolutional Neural Network(CNN) project in the Deep Learning Nanodegree program of Udacity. I learned 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, my algorithm identifies an estimate of the dog's breed. If supplied an image of a human, the code identifies the resembling dog breed.

Project Instruction

Instructions

  1. Clone the repository and navigate to the downloaded folder. 
    	git clone https://github.com/ayowolet/Dog-breed-Classifier.git
	cd Dog-breed-Classifier
  2. Open the Dog-breed Classifier.ipynb file. The HTML version of the file is available. 
    	jupyter notebook Dog-breed Classifier.ipynb
  3. Read and follow the instructions! This repository doesn't include any dataset you need. You can check out the notebook to download them.

Project Information

Contents

  • Intro
  • Step 0: Import Datasets
  • Step 1: Detect Humans
  • Step 2: Detect Dog
  • Step 3: Create a CNN to Classify Dog Breeds (from Scratch)
  • Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)
  • Step 5: Write Your Algorithm
  • Step 6: Test Your Algorithm