Back to Projects
Machine Learningbeginner

Object Detection with FasterRCNN using DVC Pipelines & DVC Data Versioning, Tensorboard, FastAPI and Postman

This project implements an end-to-end object detection workflow using Faster R-CNN, leveraging DVC for reproducible data versioning and automated pipeline orchestration. Training progress and model metrics are visualized through TensorBoard to ensure optimal performance, while the final model is deployed via FastAPI for high-performance inference.

14 lectures

What You Will Learn

By integrating TensorBoard, you will learn how to visually track metrics to make data-driven decisions during model tuning.
You will learn how to use DVC to create a Directed Acyclic Graph (DAG) that automates the transition from raw data to a trained model.
You will learn how to perform Data Versioning of big datasets using DVC with GCP Buckets.

System Architecture

Object Detection with FasterRCNN using DVC Pipelines & DVC Data Versioning, Tensorboard, FastAPI and Postman Architecture Diagram

High-level architecture overview of the Object Detection with FasterRCNN using DVC Pipelines & DVC Data Versioning, Tensorboard, FastAPI and Postman .

What You'll Build

  • You will build a version-controlled training workflow using DVC and Faster R-CNN. This includes a structured pipeline that tracks every version of your image dataset, manages model experiments, and logs performance metrics to TensorBoard, ensuring that any model you build can be perfectly recreated by other team members.
  • You will build a production-ready FastAPI web server capable of processing image uploads in real-time
  • You will also be able to test your API using Postman tool.
Object Detection with FasterRCNN using DVC Pipelines & DVC Data Versioning, Tensorboard, FastAPI and Postman
Premium
One Subscription. 40+ Projects. Unlimited Access.
AccessMobile & Web