- Jia, Kewei (kj2408@columbia.edu)
- Zhang, Yini (yz3005@columbia.edu)
- Zhu, Chenyun (cz2434@columbia.edu)
The CIFAR-10 Dataset is an important image classification dataset. It consists of 60000 32x32 colour images in 10 classes (airplanes, automobiles, birds, cats, deer, dogs, frogs, horses, ships, and trucks), with 6000 images per class. There are 50000 training images and 10000 test images.
The GOALS of this project are to:
- Learn how to preprocess the image data
- Implement different Convolutional Neural Networks (CNN) classifiers using GPU-enabled Tensorflow and Keras API
- Compare different CNN architectures
Tools:
- GPU-enabled Tensorflow
- Keras API
Following suggestions by RICH FITZJOHN (@richfitz). This folder is orgarnized as follows.
proj/
├── lib/
├── data/
├── doc/
├── figs/
└── output/
Please see each subfolder for a README file.