Skip to content

Latest commit

 

History

History
62 lines (44 loc) · 2.45 KB

README.md

File metadata and controls

62 lines (44 loc) · 2.45 KB

IMAGE CLASSIFIER

ABOUT

This project aims to classify images into various classes using Convolution Neural Network using Tensorflow Library. The Classifier can distinguish between-

  1. Airplane
  2. Automobile
  3. Bird
  4. Cat
  5. Deer
  6. Dog
  7. Frog
  8. Horse
  9. Ship
  10. Truck

DATASET USED

The CIFAR-10 is labeled subsets of the 80 million tiny images dataset. It was collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton.

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.

CLICK HERE TO DOWNLOAD THE DATASET


MISCLASSIFIED IMAGES

Below are some interesting examples where the model failed to predict the correct output


RESULTS AND ANALYSIS

Loss per Iteration

Accuracy per Iteration

Confusion Matrix makes visualizion of the result very easy and highlights the correct prediction with blue.

Confusion_matrix


AUTHOR

Divyanshu Gupta gupta.divyanshuu@gmail.com

Github

Linkedin


LICENSE & COPYRIGHT

© Divyanshu gupta

Licensed under the MIT License.