-
CIFAR-10 is a dataset that consists of several images divided into the following 10 classes: 0. Airplanes
- Cars
- Birds
- Cats
- Deer
- Dogs
- Frogs
- Horses
- Ships
- Trucks
-
The dataset stands for the Canadian Institute For Advanced Research (CIFAR)
-
CIFAR-10 is widely used for machine learning and computer vision applications.
-
The dataset consists of 60,000 32x32 color images and 6,000 images of each class.
-
Images have low resolution (32x32).
-
In this notebook uses two models
-
frist one is CNN model with
- training accuracy: 87.7%
- test accuracy: 77.3%
-
second model is Upsampling layer ==> ResNet-50 ==> two Dense layers then one last Dense layer for output
- training accuracy: 97.8%
- test accuracy: 88.4%
-
each model runed for 10 epochs without data augmentation
-
Notifications
You must be signed in to change notification settings - Fork 0
abdo-ashraf/CIFAR_10-Dataset-Classifier
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Train CNN model able to classify CIFAR-10 Dataset well
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published