/Cifar10-with-CNN

A repository with my course practice in MGMT590 Machine Learning at Krannert School of Management, Purdue University.

Cifar10-with-CNN

Convolutional models with Data Augmentation, Early Stopping and visualization.

Datset

CIFAR-10 dataset is provided by Keras directly. The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images. Classes in dataset: ["airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck"] More information can be found here: https://www.cs.toronto.edu/~kriz/cifar.html

Programming language

Python

Authors

  • Yichen Zhang (Professor)
  • Li-Ci Chuang

Libraries

  • matplotlib.pyplot
  • pandas
  • numpy
  • time
  • %matplotlib inline
  • tensorflow.keras
  • tensorflow.keras.layers
  • tensorflow.keras.optimizers
  • tensorflow.keras.models
  • tensorflow.keras.regularizers
  • tensorflow.keras.callbacks import LearningRateScheduler
  • tensorflow.keras.preprocessing.image import ImageDataGenerator