Muhammad Maaz
Abu Dhabi, UAE, San Francisco, USA, Pakistan
Summary
🤩
RockstarMuhammad Maaz is a software engineer based in Abu Dhabi with six years of experience building computer vision and deep learning systems. Originally trained as an electrical engineer, he focuses on ML/DL solutions and practical model engineering for object detection. He has contributed to the widely used AlexeyAB/darknet (YOLOv4) codebase, notably improving the training experience by adding estimated remaining training time and loss-chart refinements. Combining hands-on model work with developer-focused tooling improvements, he brings pragmatic problem-solving and production awareness to ML projects.
6 years of coding experience
Github Skills (13)
neural-network10
object-detection10
computer-vision10
neuralnetwork10
c-language10
deep-learning10
deep-neural-networks10
neural-networks10
c-programming-language10
opencv29
opencv39
opencv9
cuda8
Programming languages (7)
Github contributions (5)
AlexeyAB/darknet
Mar 2020 - Mar 2020
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Role in this project:
ML Engineer
ML EngineerContributions:12 commits, 3 PRs, 9 comments in 21 days
Contributions summary:Muhammad primarily contributed to the implementation and refinement of training-related functionalities within the YOLOv4/Darknet framework. Their work focused on adding features to monitor training progress, specifically incorporating the calculation and display of estimated remaining training time. They modified code related to loss charts and training loops, suggesting a focus on improving the user experience and providing real-time feedback during model training.
dnncomputer-visionobject-detectiondeep-learning-tutorialdarknet
mmaaz60/EdgeNeXt
Jun 2022 - Oct 2022
Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications".
Contributions:3 releases, 29 commits, 4 PRs in 3 months
pytorchtransformer-architecturetransformersedge-computingvision
Find and Hire Top DevelopersWe’ve 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.