An open API service indexing awesome lists of open source software.

https://github.com/khurramhashmi/cnn_cifar-10_keras-tensorflow

This repository is created solely for the intention of playing around with CIFAR10 dataset using different architectures to achieve optimal performance.
https://github.com/khurramhashmi/cnn_cifar-10_keras-tensorflow

cifar-10 cifar10 convolutional-neural-networks deep-learning keras keras-tensorflow tensorflow

Last synced: 3 months ago
JSON representation

This repository is created solely for the intention of playing around with CIFAR10 dataset using different architectures to achieve optimal performance.

Awesome Lists containing this project

README

          

# CNN_CIFAR-10_Keras-TensorFlow
This repository is created solely for the intention of playing around with CIFAR10 dataset using different architectures to achieve optimal performance. In order to achieve better accuracy, the dataset has been augmented as well as regularized. Code is quite trivial because Keras has been mainly used. The result achieved using the current network is almost 89% on 125 epochs.

## Usage
It's a simple python notebook executed on Google Collab. Feel free to use it as a base network and play around.
Happy Coding :)

## Prerequisites
-TensorFlow
-Keras

## Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

## Acknowledgement
Inspiration and direction has been taken from the following blog :
https://appliedmachinelearning.blog/2018/03/24/achieving-90-accuracy-in-object-recognition-task-on-cifar-10-dataset-with-keras-convolutional-neural-networks/