I will build a custom yolov8 object detection model

Z
zahoor_develope
Z
zahoor_develope
Zahoor Ahmad

About this gig

Your camera footage already contains the answer. You just need software that can see it.


I train custom YOLOv8 detection models and deliver them as working systems. My last build spotted motorcycle riders without helmets in live CCTV, read their number plates with OCR, and logged every violation to a dashboard: 86.9% mAP@0.50, 89.3% precision, 43.7 FPS.


WHAT YOU GET

- A model trained on YOUR images, not a generic pretrained one

- Dataset annotation, cleaning and augmentation

- Accuracy report: mAP, precision, recall, confusion matrix

- Inference script for images, video files, or a live stream

- Optional FastAPI endpoint and web dashboard


WORKS FOR

Safety and PPE compliance, helmet detection, retail shelf and people counting, manufacturing defect detection, vehicle and license plate recognition, agriculture, medical imaging.


Send me 10-20 sample images and tell me what needs detecting. Before you order, I will tell you honestly whether it is achievable and what accuracy to realistically expect. I would rather turn down a job than miss a target I promised.


Message me first so we can scope it properly.

Get to know Zahoor Ahmad

Zahoor Ahmad

PRO

  • FromPakistan
  • Member sinceDec 2025
  • Avg. response time1 hour
  • Languages

    Urdu, English, Spanish
I build AI systems that run in production, not notebooks that run once. My focus is computer vision and applied machine learning: custom YOLOv8 detection models, OCR pipelines, and the web apps around them. My last detection system hit 86.9% mAP at 43.7 FPS on live video and shipped with a working dashboard, not a folder of scripts. Full stack: Python, PyTorch, OpenCV, FastAPI on the model side. Next.js, React, Supabase, PostgreSQL on the product side. That means I deliver the whole thing. Same-day replies. I tell you upfront if your accuracy target isn't realistic.

My Portfolio