Boycelol's repositories
Boycelol
Config files for my GitHub profile.
000
Generalized-Convolutional-Neural-Network
This repository contains an implementation of CNNs from scratch. It has dropout regularization, both for convolution and fully connected layers. It also has batch normalization implemented - both for fully connected and convolution layers. It takes the model characteristics as input from the user. This, currently has implementation for Conv + relu and Max pool layers in the convolution segment of the network. Also, final layer before fully connected segment is a max pool layer. This implementation makes use of functions from generalized-neural-network repository for the fully connected layer's computation.
000