Double Vision
Freelance at Upwork
Gujarat, India
Summary
🤩
Rockstar🎓
Top School
Top expert inArtificial Intelligence and Computer Vision Technologies
Double Vision is a freelance software and ML engineer from Gujarat with eight years of experience blending front-end web skills and deep learning engineering. Comfortable juggling client work on platforms like Upwork and Fiverr, he pairs strong communication and project management with hands-on HTML/CSS and cross-client testing expertise. His open-source contributions to the PaddlePaddle ecosystem span documentation, OCR and detection model work, and low-level operator fixes—evidence of both ML research curiosity and production-grade C++/CUDA debugging. He has implemented and refined OCR pipelines (PaddleOCR) and distillation techniques in PaddleDetection, showing a practical focus on model efficiency and deployment. Known for analytical problem-solving and UX-aware development, he brings measurable digital-content thinking to ML projects. Trained in Computer Engineering at CHAROTAR University, he combines academic grounding with real-world contributions to a major open-source deep learning framework.
8 years of coding experience
Bachelor of Technology - BTech, Computer Engineering, Bachelor of Technology - BTech, Computer Engineering at CHAROTAR UNIVERSITY OF SCIENCE AND TECHNOLOGY
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (31)
c-language10
python10
image-classification10
ocr10
machine-learning10
numpy10
mask-rcnn10
deep-learning10
tensorflow10
ocra10
neural-network10
paddlepaddle10
object-detection10
computer-vision10
faster-rcnn10
Programming languages (6)
Github contributions (5)
PaddlePaddle/PaddleOCR
May 2020 - Jan 2023
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
Role in this project:
ML Engineer
ML EngineerContributions:751 reviews, 1583 commits, 831 PRs in 2 years 8 months
Contributions summary:Double uploaded the PaddleOCR code and modified files related to the EAST text detection algorithm. The changes included modifications to the `east_process.py` file, indicating involvement in data processing and preprocessing. The commits focus on core components of the PaddleOCR library, aligning with the development of a multilingual OCR toolkit.
synthesisultrapracticaltrainingtoolkits
PaddlePaddle/models
Feb 2020 - Jun 2022
Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
Role in this project:ML Engineer
ML EngineerContributions:12 reviews, 25 commits, 42 PRs in 2 years 4 months
Contributions summary:Double primarily focused on updating and refining OCR models within the PaddlePaddle framework. Their work involved integrating new APIs, fixing code style issues, and modifying various model components such as attention models, CRNN CTC models, and inference scripts. They addressed issues related to model loading and parameter handling, ensuring compatibility with the latest API updates. The user also contributed to the VOT (Visual Object Tracking) models, including SiamFC and ATOM implementations, to fit the project.
nlpdeep-learningpaddlepaddlerecommendationcomputer-vision
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.