## Objective: 

To classify images in the Caltech-256 dataset, which is an improvement over Caltech-101 dataset using a Convolutional Neural Network.

## Problem Statement

To build and implement a Convolutional Neural Network model to classify images in the Caltech-256 dataset.

At the end of this competition, you will be able to:

1. Load and extract features of images available in the Caltech-256 dataset using ImageDataGenerator
2. Build convolutional neural networks using either Keras or PyTorch deep learning libraries
3. Use the pre-trained models using either Keras or PyTorch deep learning libraries

## Description: 

Caltech-256 is an object recognition dataset containing approximately 30,000 real-world images, of different sizes, spanning 256 classes (256 object classes and an additional clutter class). Each class is represented by at least 80 images. The dataset is a superset of the Caltech-101 dataset.

Here is a handy link to Kaggle's competition documentation (https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on submitting predictions (https://www.kaggle.com/docs/competitions#making-a-submission).