Skip to content

CIFAR10-ObjectDetection with ResNet50 achieves 83.2% accuracy on the test set & 89.5% on the train set

Notifications You must be signed in to change notification settings

Mithun691/CIFAR10

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

CIFAR10

CIFAR10-ObjectDetection with ResNet50 achieves 83.2% accuracy on the test set & 89.5% on the train set

CIFAR-10 contains images of 10 classes which need to be classified

The images are low resolution 32*32 rgb images making the task even difficult

The .ipynb file contains implementation of ResNet50 inspired architecture

It achieves 83.2% accuracy on the test set after 20 epochs but is subject to a bit of variation each time due to the randomness involved in Stochastic Gradient descent

About

CIFAR10-ObjectDetection with ResNet50 achieves 83.2% accuracy on the test set & 89.5% on the train set

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published