Paper Implementations Python Packages

selective-search

Python implementation of selective search

mdrnn

Custom Keras layers for implementing multi-dimensional recurrent neural networks (MDRNNs) described in Alex Graves's paper https://arxiv.org/pdf/0705.2011.pdf

pytorch-bert

An implementation of BERT using PyTorch's TransformerEncoder

keras-htr

A toolkit for training CNN-1DRNN-CTC model to perform line-level Handwritten Text Recognition

qubo-nn

Classifying, auto-encoding and reverse-engineering QUBO matrices

garnn

TensorFlow implementation of Graphical Attention Recurrent Neural Networks based on work by Cirstea et al., 2019.

dgcnn

Clean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).

tversky-neural-network-pytorch

Implementation of Tversky Neural Networks, from Doumbouya et al. (2025), in PyTorch .