/Deep-Learning-Dog-Breed-Identification

Kaggle Challenge - create a classifier capable of determining a dog's breed from a photo

Primary LanguageJupyter Notebook

Kaggle Challenge

Kaggle Challenge - create a classifier capable of determining a dog's breed from a photo

Deep Learning Project - Dog Breed Identification

This is a dog breed identification project from Kaggle. To build a deep neural network which can answer that ubiquitous question we all ask when meeting a four-legged stranger: what kind of puppy is that?

Data Description

Datasets include a training set and a test set of images of dogs. Each image has a filename that is its unique id. The dataset comprises 120 breeds of dogs. The goal of this project is to create a classifier capable of determining a dog's breed from a photo. Some example in the list of breeds is as follows:

  • affenpinscher
  • afghan_hound
  • african_hunting_dog
  • airedale
  • american_staffordshire_terrier
  • appenzeller
  • australian_terrier
  • basenji
  • basset
  • beagle
  • bedlington_terrier
  • bernese_mountain_dog ……

Data Overview

Total 690MB

  • File 1 - train.zip - the training set, image file, provided the breed for these dogs
  • File 2 - test.zip - the test set, image file, predict the probability of each breed for each image
  • File 3 - labels.csv - csv file with two columns: id and breed, the breeds for the images in the train set

Data Preprocessing & Model Development

Python Code:

Visualize Predictions