Skip to content
Avatar
Block or Report

Block or report Kolkir

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Kolkir/README.md

Hi there 👋

My name is Kirill Kolodiaznyi and I'm a software developer from Ukraine, living in Kharkiv. You can find me on Twitter, or on LinkedIn.

🔬 Research & Intersest

The research I’m working on now is the implementation of a robotic platform based on the NVIDIA Jetson Nano 2Gb device with monocular SLAM navigation. The main aim of this work is to improve feature matching algorithms used for camera positioning in a SLAM pipeline. The recent experiments are about using deep learning for SLAM, especially using the Local Feature Matching with Transformers for camera positioning.

Another topic of my interest is multi-threaded algorithms and using them for performance improvements in projects I’m working on. The result of this work is the library that represents higher-level, task-based parallelism. It’s based on the idea of the Intel TBB work-stealing threads management approach.

Also, I’m interested in learning and applying the C++ language for solving Machine Learning tasks. I wrote several articles and a book about the application of C++ to ML. Additionally, I made C++ implementations of popular object detection methods like Faster R-CNN and Mask R-CNN.

Publications

🔧 Technologies & Tools

Pinned

  1. mlcpp Public

    Set of examples of ML approaches implemented in C++

    C++ 276 60

  2. cpptask Public

    Lightweight approach to expressing task stealing and balanced parallelism in a C++ programs.

    C++ 74 5

  3. cppminer Public

    cppminer produces a code2seq compatible datasets from C++ code bases.

    Python 21 3

  4. code2seq Public

    Forked from tech-srl/code2seq

    Code for the model presented in the paper: "code2seq: Generating Sequences from Structured Representations of Code"

    Python 18 10

  5. Educational 2D SLAM implementation based on ICP and Pose Graph

    Python 19 1

  6. Distilled coarse part of LoFTR adapted for compatibility with TensorRT and embedded divices

    Python 45 13

62 contributions in the last year

Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Mon Wed Fri

Contribution activity

December 2022

Kolkir has no activity yet for this period.

Seeing something unexpected? Take a look at the GitHub profile guide.