Name: Evgenii Zheltonozhskii
Type: User
Company: Technion
Bio: Physics PhD student (condensed matter) at Technion. MSc in computer science (deep learning, self supervised learning).
Twitter: evgeniyzhe
Location: Haifa, Israel
Blog: https://evgeniizh.com/
Evgenii Zheltonozhskii's Projects
D2Det, CVPR2020
Differentiable architecture search for convolutional and recurrent networks
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Deep Convolutional Generative Adversarial Networks
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Dockerfiles for C++ CI testing images
Implementation of DropBlock in Pytorch
Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
This repository reproduces the results of the paper: "Fixing the train-test resolution discrepancy" https://arxiv.org/abs/1906.06423
Flappy Bird Bot using Reinforcement Learning
A new version of old chess engine
Rust packages
General Mission Analysis Tool https://sourceforge.net/projects/gmat/
An implementation of training for GPT2, supports TPUs
Contains information about accepted GSoC 2017 Projects across various organizations along with the proposals.
A toolkit for developing and comparing reinforcement learning algorithms.
🍻 A CLI workflow for the administration of macOS applications distributed as binaries
Implementation of "Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect" in pytorch
The LaTeX beamerposter package
Qalculate! library and CLI
Code for ICLR2020 "Improving Adversarial Robustness Requires Revisiting Misclassified Examples"
A tiny autograd engine and a neural net library on top of it, potentially for educational purposes