Browse categories
Explore
Fiverr Pro
English
$
USD
I will build a complete computer vision web app with dashboard and API
About this Gig
Need to detect, read or track things in images or video, and actually use the results? I'm a Senior Data Scientist with 7+ years in AI, and I architected a five-product vision suite that runs live on modest roadside hardware. I build the complete solution, not just a model file.
What you get:
Web app: upload images or video, or connect a live camera feed, and see detections, OCR text and tracks in real time.
Dashboard: events, counts, alerts, search and exports, with user logins and roles.
Backend API: REST API with a processing pipeline, database and webhooks into your own systems.
Models: detection, OCR, classification, tracking or anomaly detection, trained on your data (YOLO, OpenCV, PyTorch).
Deployment: Docker setup, cloud or GPU server or edge device, source code and documentation.
The web app comes first. A mobile app can be added later as an extension.
Send me a few sample images or a short clip and I will tell you the best package and what accuracy to expect before you order.
Programming language:
Python
•
Colab
•
Amazon SageMaker
Tools:
OpenCV
•
TensorFlow
•
CVAT
•
PyTorch
Other Data Science & ML Services I Offer
FAQ
How many images do I need?
It depends on the task. A few hundred labelled images per class is often enough to start with transfer learning. Send me samples and I will tell you before you order.
Can the model run on an edge device or without internet?
Yes. I optimize models with OpenVINO, ONNX or TensorRT for CPUs, Jetson-class GPUs and offline sites, and can bind the software to its hardware.
Do you label the data too?
Small labelling jobs are included in Standard and Premium. For large datasets I set up a labelling workflow in CVAT and we agree the scope first.
