Skip to content

Using a Convolutional Neural Network to classify images based on CIFAR10 dataset

Notifications You must be signed in to change notification settings

Anshdeep-Singh/CIFAR10_Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

CIFAR10_Classification

Using a Convolutional Neural Network to classify images based on CIFAR10 dataset

AUTHOR - ANSHDEEP SINGH

The Folder Contains 2 files excluding Readme.txt -Testing_Model.ipynb -Training_Model.ipynb

Libraries Required for the program to run 1.Numpy 2.Pandas 3.Scikit learn 4.Tensorflow and keras 5.Matplotlib

To download any of the libraries go to command prompt and type 'pip install library_name' in the terminal or command prompt. NOTE: YOU MUST HAVE PYTHON INSTALLED IN YOUR SYSTEM

=========================================== INSTRUCTIONS =================================================

  1. I recommend using Google Colab and If you want to see the model and all the layers in it, check 'Training_Model.ipynb'. Executing this file will start re-trainig the model and might take a while to train so if you are using Google Colab then enable gpu under Edit -> Notebook settings.

2.If you want to test the model that is already saved in the the folder (CIFAR10_.h5), check 'Testing_Model.ipynb'. And while using Google Colab you need to upload the CIFAR10_.h5 file under the Files section on the left and the uploading takes a while. After the file has been uploaded you may start executing the cells sequencially. NOTE: ALL CELLS IN THIS FILE SHOULD BE EXECUTED SEQUENCIALLY (one after another in sequence)

And If you are using Jupyter Notebook or any other editor then make sure that the CIFAR10_.h5 file is in the same folder as the Testing_Model.ipynb file

============================================= THANK YOU ===================================================

About

Using a Convolutional Neural Network to classify images based on CIFAR10 dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published