/Intel_Classification

Practice Problem Intel Scene Classification Challenge

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Practice Problem Intel Scene Classification Challenge

Problem Statement

  • In this practice problem, we are provided with a dataset of ~25k images from a wide range of natural scenes from all around the world such as a forest or a mountain. Our task is to identify which natural scene can the image be categorized into.

Dataset Description

  • There are 17034 images in training dataset and 7301 images for test data. The categories of natural scenes and their corresponding labels in the dataset are as follows - {'buildings' -> 0, 'forest' -> 1, 'glacier' -> 2, 'mountain' -> 3, 'sea' -> 4, 'street' -> 5 }

EVALUATION METRIC

  • The Evaluation metric for this competition is accuracy.

  • Got 91% accuracy on test dataset.

  • Checkout the competition here