Ahmed Abbas's repositories
DOGE-Train
A fast, scalable, data-driven approach for solving relaxations of 0-1 integer linear programs on GPU.
aabbas90.github.io
My homepage's source code
awesome-ml4co
Awesome machine learning for combinatorial optimization papers.
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
CMC
[ECCV 2020] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
FADOP
An integer linear program solver using a Lagrange decomposition into binary decision diagrams. Lagrange multipliers are updated through dual block coordinate ascent.
global-divergences
MMD, Hausdorff and Sinkhorn divergences scaled up to 1,000,000 samples.
gym
A toolkit for developing and comparing reinforcement learning algorithms.
how_attentive_are_gats
Code for the paper "How Attentive are Graph Attention Networks?"
LPMP
Solving LPs with convergent message passing
minimal-light
A simple and elegant Jekyll theme for an academic personal homepage
MVSNet_pytorch
PyTorch Implementation of MVSNet
panopticapi
COCO 2018 Panoptic Segmentation Task API (Beta version)
PlotNeuralNet
Latex code for making neural networks diagrams
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
structured-prediction-problem-archive
Archive of structured prediction problems from computer vision and machine learning