Skip to content

A three-layered convolutional neural network implemented using Keras to construct a multiclass image classifier

Notifications You must be signed in to change notification settings

potter1024/Image-Classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Image-Classifier

Implemented a 3 layered neural network using keras to make a multiclass image classifier.

Used the dataset from keras (cifar10 dataset of 60,000 images uniformly distributed into 10 classes) Used 50,000 images for training and 10,000 images for testing.

The performance i.e the F-value using precision and recall, calculated from comfusion matrix is 67.1%

About

A three-layered convolutional neural network implemented using Keras to construct a multiclass image classifier

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published