Skip to content

A basic CNN from scratch using python + openCL to classify MNIST digits

Notifications You must be signed in to change notification settings

uttejh/CNN-v3.0

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CNN-v3.0

A Convolutional Neural Network used for the recognition of Handwritten characters (numbers) using Deep Learning. The system was purely implemented from the scratch in python without using any existing tools such as Tensorflow, Matlab, Keras, etc... and the performance was parallelized with the help of OpenCl. The architecture is based on the book by Michael Nielsen. The system was trained using very small datasets for around 30000 epochs and has achieved an accuracy of 79%.

Built-With

  • Pyhton
  • Opencl - open standard for parallel programming of heterogeneous systems

Changes

The changes from the previous version (v2) are as follows:-

  • The activation function is changed from ReLu to Sigmoid
  • Normalisation layers were added
  • Redundant functions were removed

Authors

License

  • The project uses open-source software
  • Acknowledgements

    About

    A basic CNN from scratch using python + openCL to classify MNIST digits

    Topics

    Resources

    Stars

    Watchers

    Forks

    Releases

    No releases published

    Packages

    No packages published

    Languages