/Dog-Breed-Identification

This repo deals with building a dog breed identifier, which predicts the dog breed from 120 unique breeds. This Machine Learning model is trained on 10,000+ dogs and tested again on 10,000+ images.

Primary LanguageJupyter Notebook

Multi Class Dog Breed Classification

This repo deals with building an end-to-end multi-class image classifier using Tensorflow 2.0 and Tensorflow Hub.

1. Problem

Identifying the breed of a dog given an image of a dog.

2. Data

The data in this project is from Kaggle:
https://www.kaggle.com/c/dog-breed-identification/data

3. Evaluation

The evaluation is a file with prediction probabilities for each dog breed of each test image.
https://www.kaggle.com/c/dog-breed-identification/overview/evaluation

4. Features

Information about the data:

Dealing with images (Unstructured Data) - Deep Learning / Transfer Learning.

  • 120 breeds of dogs -> means there are 120 differnt classes.
  • There are around 10,000+ images in the training set (Images have labels).
  • There are around 10,000+ images in the test set (Images have no labels, we have to predict them).