top of page

Deep Learning Modules for Computer Vision

  • A collection of implementations of state of the art convolutional neural network (CNN) architectures for computer vision applications.

  • Implementations are in Keras, using a Tensorflow 1.xx back end, and contains a basic Tensorflow 2.xx port with a few simple tweaks.

  • The project contains object oriented implementations of neural network architectures, pre-processing modules for image data processing, checkpointing modules, learning rate decay schedulers, and implementations of these concepts on several popular datasets such as CIFAR-10.

  • The project implements seminal architectures such as AlexNet, GoogLeNet and the Inception Module, LeNet, VGGNet to name a few.

  • Google Colaboratory Notebooks have also been created for these architectures.

cv-img_edited.jpg
googlenet.png
bottom of page