I will do python computer vision, object detection, and image segmentation

Need a computer vision model that works on your own images? I train, fine-tune and review object detection and image segmentation models in Python.

What I can do:

• Object detection with YOLO: custom classes, counting, defect detection
• Image segmentation: semantic and instance segmentation, UNet, SAM, high-resolution images
• Review an existing pipeline: low accuracy, noisy labels, poor results on new data
• Clear metrics (mAP, IoU, Dice) and a look at where the model fails

Why me:

• Data Scientist / ML Engineer with ~4 years of industry experience
• Improved YOLOv8 detection by +0.05 mAP50 for traffic monitoring
• Built a SAM-based pipeline for 24MP images with noisy labels on limited GPU memory
• Kaggle Bronze Medal (top 5%) in medical image segmentation

How it works:

1. Send a sample of your images, labels and the result you expect
2. I confirm scope and timeline before starting
3. You receive code, model weights and a short report

Results depend on data quality. I don't promise a specific metric, but I report exactly what was achieved and why.

Please message me before ordering. Not included: data labeling, edge deployment, real-time video systems.