YoelShoshan

Dooake

FPS shooter game implemented in C++. Doom3 monsters playable on top of Quake3Arena levels.

dump-dog

A windows centric crash dump framework including exception handling, memory dumps, watchdogs and summary

tiny_openfold

low dependencies utilities and helper functions from openfold

focal_loss_torch

Simple pytorch implementation of focal loss

GeneWarrior

A sandbox for humanoid action generation

fuse-med-ml

A python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)

gt4sd-core

GT4SD, an open-source library to accelerate hypothesis generation in the scientific discovery process.

hookit

Library hooking assisting tool - dll hooking - was hacked quickly in few hours and while VERY far from being robust was extremely useful. Allows to generate C++ class wrappers quickly, mostly for code injections and reverse engineering tasks.

iunets

A fully invertible U-Net for memory efficiency in Pytorch.

OCR

OCR project

OldInfants

A quake3arena clone with a board game twist.

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

paccmann_datasets

pytoda - PaccMann PyTorch Dataset Classes. Read the docs: https://paccmann.github.io/paccmann_datasets/

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch-summary

Model summary in PyTorch similar to `model.summary()` in Keras

pytorchviz

A small package to create visualizations of PyTorch execution graphs

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

readme-with-video

ResNeXt

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

Sapiens

Sapiens is a human antibody language model based on BERT.

SimpleBackupTool

Basic but useful backup tool which I used until I started using dropbox pro.

state-of-the-art-result-for-machine-learning-problems

This repository provides state of the art (SoTA) results for all machine learning problems. We do our best to keep this repository up to date. If you do find a problem's SoTA result is out of date or missing, please raise this as an issue or submit Google form (with this information: research paper name, dataset, metric, source code and year). We will fix it immediately.

stylegan2-pytorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

tensorflow

Computation using data flow graphs for scalable machine learning

transplant

Transplant is an easy way of calling Matlab from Python

zed_utils

Intended to be a collection of useful utilities, functions and classes in few languages to make creating new projects easier (for example - iterating on files, loading and saving images, 3d rendering boiler plates, etc.). The point is to prevent rewriting them every time :)