BartlomiejĀ Olechno
Computer Vision Algorithms Developer at Flymingo
Warsaw, Masovian Voivodeship, Poland
Summary
š¤©
Rockstarš
Top SchoolBartlomiej Olechno is a Computer Vision Algorithms Developer with nine years of hands-on experience building deep learning applications across startups and R&D labs, currently based in Warsaw. He has progressed from Unity and game-dev roles to senior machine learning positions, applying research-grade computer vision to product-focused problems at companies like ECC Games, charactr, and Flymingo. His background in Control & Robotics (MSc, Warsaw University of Technology) informs a systems-minded approach to perception stacks and real-time inference. An active contributor to open-source tooling, he integrated PyTorch Ignite support into the popular livelossplot project to improve live training visualization in notebooks. Colleagues value his blend of prototyping speed and production engineering rigor, particularly when translating complex models into deployable components. He often combines game-development intuition with industrial control perspectives to solve atypical vision challenges.
9 years of coding experience
5 years of employment as a software developer
Master's degree Control Robotics and Industrial Computer Science, Master's degree Control Robotics and Industrial Computer Science at Warsaw University of Technology
Github Skills (4)
jupyter-notebook10
pytorch10
python10
deep-learning9
Programming languages (1)
Github contributions (5)
stared/livelossplot
Feb 2020 - Feb 2021
Live training loss plot in Jupyter Notebook for Keras, PyTorch and others
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 review, 104 commits, 25 PRs in 11 months
Contributions summary:Bartlomiej primarily contributed to the integration of the PyTorch Ignite library into the project, adding a plugin to utilize it for live loss plotting in Jupyter notebooks. Their work involved implementing a PlotLossesCallback class to handle the communication between the Ignite engine and the existing plotting functionality. They refactored f-strings to format and updated the code to be compatible with Python 3.5. The user also added an example showcasing the use of the Ignite plugin.
keras-visualizationpytorchpythondeep-learningjupyter-notebook
Bartolo1024/livelossplot
Feb 2020 - Aug 2020
Live training loss plot in Jupyter Notebook for Keras, PyTorch and others
Contributions:111 pushes, 43 branches in 6 months
pytorchpythondeep-learningjupyter-notebooknotebook
Find and Hire Top DevelopersWeāve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.