Explainable AI

Object Detection you own this product

This project is part of the liveProject series Transformers and Explainable AI for Computer Vision
prerequisites
intermediate Python (particularly TensorFlow or PyTorch) • intermediate knowledge of image-based object detection principles • intermediate knowledge of image visualization
skills learned
import computer vision datasets from other platforms like Roboflow• merge two or more object detection datasets and their annotations on Roboflow • set up training, test, and validation datasets for object detection • train and evaluate three variants of DETR models for construction vehicle detection
Anuradha Kar
1 week · 5-7 hours per week · INTERMEDIATE
Included with a Manning Online subscription
try now

pro $24.99 per month

  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose one free eBook per month to keep
  • exclusive 50% discount on all purchases

lite $19.99 per month

  • access to all Manning books, including MEAPs!

team

5, 10 or 20 seats+ for your team - learn more

Look inside

In this liveProject, you'll spearhead the development of AI-aided surveillance software for construction site supervision. You’ll build two computer vision applications capable of detecting construction vehicles and their types across a large worksite and a more powerful model that can detect building defects such as cracks and fissures. Start by working with a pre-trained DETR model, then explore the Roboflow platform to assist you as you create a multi-class object detection dataset from multiple datasets with non-identical classes. With these datasets, you will train different transformer models for object detection to identify construction vehicles and cracks in buildings.

This project is designed for learning purposes and is not a complete, production-ready application or solution.

book resources

When you start your liveProject, you get full access to the following books for 90 days.

project author

Anuradha Kar
Anuradha Kar is a researcher at the Institut Pasteur in Paris, working on deep learning applications in drug discovery. Before this, she worked at the Paris Brain Institute on applying attention-based deep learning models to understanding the evolution of Alzheimer's disease and at École normale supérieure de Lyon in France on deep learning-based analysis of 3D bio-image datasets. She has a Ph.D. in electrical engineering from the National University of Ireland, Galway. In 2021, she published a liveProject series with Manning Publications titled Transfer Learning for Dicom Image Classification.

prerequisites

This liveProject series is aimed at intermediate-level Python programmers who already know the basics of deep learning and computer vision.


TOOLS
  • Intermediate Python
  • Intermediate Jupyter Notebook
  • Intermediate TensorFlow
  • Intermediate PyTorch
  • Intermediate OpenCV

TECHNIQUES
  • Intermediate levels of deep learning and image classification
  • Intermediate levels of data science

you will learn

This liveProject will empower you to work with transfer learning, adapting pre-existing models to new tasks.


  • Learn how to process image data and annotations for object detection tasks.
  • Utilize image datasets from Hugging Face and Roboflow for training object detection transformer models.
  • Curate a multi-class object detection dataset from two or more open datasets hosted on Roboflow.
  • Create Hugging Face-compatible object detection datasets and upload them to the Hugging Face Hub.
  • Develop pipelines for training and evaluating transformer models for object detection.
  • Fine-tune three distinct object detection models from Hugging Face Transformers libraries for construction vehicle and building defect detection.
  • Display object detection results from the trained models.

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
book resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.

choose your plan

pro

monthly
annual
$24.99
$249.99
only $20.83 per month
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • Object Detection project for free

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • Object Detection project for free