/caltech101

Image classification and clustering on Caltech-101 dataset

Primary LanguageJupyter Notebook

Caltech 101 Dataset

Image classification and clustering on Caltech-101 dataset.

Overview

This repository contains 3 jupyter notebooks.

  • 1_exploration.ipynb contains initial exploration of the dataset inclusing finding out how many instances are there, and displaying a few instances.
  • 2_classification.ipynb deals with image classification using pre-trained models and fine-tuning.
  • 3_clustering.ipynb shows clustering of images of the dataset. The results and conclusions are shown at the end of each jupyter notebook.

Requirements

  • numpy
  • pandas
  • matplotlib
  • tqdm
  • cv2
  • sklearn
  • tensorflow
  • keras

References

[1] http://www.vision.caltech.edu/Image_Datasets/Caltech101/

[2] https://www.tensorflow.org/tutorials/images/transfer_learning

[3] https://scikit-learn.org/stable/modules/decomposition.html#pca

[4] https://scikit-learn.org/stable/modules/clustering.html#k-means