Browse categories
Explore
Fiverr Pro
English
$
USD
I will do object detection, recognition and classification using python
Machine Learning Engineer, Software Developer
I am a machine learning engineer and software developer with 10+ years of freelancing experience in creating custom AI solution, computer vision projects, Natural language processing projects and web ...
About this Gig
I will train object detection models and build custom algorithms for detecting, tracking, and counting objects in images, videos, or live streams. I can collect data, create high-quality datasets, and handle preprocessing and annotation using OpenCV.
I also develop classification models to identify object classes and integrate them into real-world applications. I can deliver complete ML solutions with frontend and backend, including APIs, dashboards, and deployment for desktop or web environments.
Services include: image annotation, object detection & classification, object counting & direction tracking, image preprocessing, and high-speed, high-accuracy solutions.
Project types: model training & deployment, image segmentation, and desktop/web apps for deployed models.
Models: YOLO (v3v8), SSD MobileNet, EfficientDet, Detectron2, SAM
Tools: OpenCV, TensorFlow, PyTorch, Keras, Scikit-learn, Flask, FastAPI, ByteTrack, DeepSORT
Languages: Python, SQL, HTML, CSS, Node.js
Deployment: AWS, Docker, Kubernetes
Please contact me before placing an order. THANK YOU!
Programming language:
Python
•
Colab
•
NoSQL
•
MLflow
•
Amazon SageMaker
Frameworks:
Scikit-learn
•
Google ML Kit
•
Keras
•
PyTorch
•
Panda
Clients I’ve worked with
Paktive
Travel & Tourism Blog/Channel
RFM Loyalty wanted to have one portal for managing the details of employees located in different locations. We have worked on his project and built an amazing web portal. It supports many features like authentication, authorization, and file uploads
Mar 2020-May 2021
Predictable Growth as a Service
Marketing Agency
It is a website widget/calculator where users will get the growth plan based on their current metrics and annual growth. This project consists of the following features: Generate result as PDF, email the result and share the result.
Apr 2021-Jun 2021
My Portfolio
FAQ
What do you need from me to start?
A clear problem description, sample images/videos (or stream details), and expected output (e.g., detection, counting, tracking). If you have a dataset, share it; otherwise, I can help collect and annotate one.
Do you provide datasets and annotation?
Yes. I can collect data, clean it, and create high-quality annotated datasets tailored to your use case.
Which models and technologies do you use?
I work with YOLO (v3–latest), SSD MobileNet, EfficientDet, Detectron2, SAM using PyTorch, TensorFlow, and OpenCV.
Can you deploy the model into an application?
Yes. I can integrate models into desktop or web apps, build APIs (Flask/FastAPI), and provide a usable frontend dashboard if needed.
Will the model work in real-time?
Yes, depending on your hardware and requirements. I optimize models for real-time performance on CPUs/GPUs.
Do you support live video streams (CCTV, RTSP, etc.)?
Yes, I can process live streams and implement detection, tracking, and counting in real time.
What accuracy can I expect?
Accuracy depends on data quality and problem complexity. I aim for high accuracy and will share evaluation metrics (precision, recall, mAP).
Do you offer revisions and support after delivery?
Yes, I provide revisions based on agreed scope and can offer post-delivery support if needed.
