Monthly Subscription Starting at AED 99 + VAT

Advanced Computer Vision with TensorFlow
  • Level Professional
  • Duration 19 hours
  • Course by DeepLearning.AI
  • Offered by

About

In this course, you will: a) Explore image classification, image segmentation, object localization, and object detection. Apply transfer learning to object localization and detection. b) Apply object detection models such as regional-CNN and ResNet-50, customize existing models, and build your own models to detect, localize, and label your own rubber duck images. c) Implement image segmentation using variations of the fully convolutional network (FCN) including U-Net and d) Mask-RCNN to identify and detect numbers, pets, zombies, and more. d) Identify which parts of an image are being used by your model to make its predictions using class activation maps and saliency maps and apply these ML interpretation methods to inspect and improve the design of a famous network, AlexNet. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

Modules

Concepts in Computer Vision

    • 3 Videos
    • 2 Readings
Show info about module content

3 Videos

  • Welcome to Course 3
  • Classification and Object Detection Intro
  • Segmentation Intro

2 Readings

  • Prerequisite & References
  • [IMPORTANT] Have questions, issues or ideas? Join our Forum!

Transfer Learning

    • 3 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Transfer Learning

3 Videos

  • Why Transfer Learning?
  • What is Transfer Learning?
  • Options in Transfer Learning

Advanced Transfer Learning

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Transfer Learning with ResNet 50

2 Videos

  • Transfer Learning with ResNet50
  • ResNet50 in code

Object Localization and Detection

    • 2 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Image Classification and Object Localization

2 Videos

  • Network architecture for Object Localization
  • Evaluating Object Localization

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 1

Week 1 Quiz: Introduction and Concepts of Computer Vision

    • 1 Assignment
Show info about module content

1 Assignment

  • Introduction and Concepts of Computer Vision

Assignment: Bird Boxes

    • 1 Programming
Show info about module content

1 Programming

  • Bird Boxes

Object Detection

    • 4 Videos
    • 2 Readings
Show info about module content

4 Videos

  • Object Detection and Sliding Windows
  • R-CNN
  • Fast R-CNN
  • Faster R-CNN

2 Readings

  • References: Amazon Rekognition, PowerAI & DIGITS
  • Reference: R-CNN, Fast R-CNN

Object Detection in TensorFlow

    • 2 Videos
    • 1 Readings
    • 2 Lab
Show info about module content

2 Labs

  • Implement Simple Object Detection
  • Predicting Bounding Boxes for Object Detection

2 Videos

  • Getting the Model from TensorFlow Hub
  • Running the Model on an Image

1 Readings

  • Reference: TensorFlow Hub

Object Detection APIs

    • 2 Videos
    • 2 Readings
Show info about module content

2 Videos

  • Installation and overview of APIs
  • Visualization with APIs

2 Readings

  • Read about the Object Detection API
  • Use the Object Detection API

Retraining with the Object Detection API

    • 4 Videos
    • 2 Readings
Show info about module content

4 Videos

  • Loading a RetinaNet Model
  • Loading Weights
  • Data Prep and Training Overview
  • Custom Training Loop Code

2 Readings

  • Reference: RetinaNet, Model Garden
  • Eager Few Shot Object Detection

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 2

Week 2 Quiz: Object Detection

    • 1 Assignment
Show info about module content

1 Assignment

  • Object Detection

Assignment: Zombie Detector

    • 1 Programming
Show info about module content

1 Programming

  • Zombie Detector

Image Segmentation Overview

    • 7 Videos
    • 2 Readings
    • 1 Lab
Show info about module content

1 Labs

  • Implement a Fully Convolutional Neural Network

7 Videos

  • Image Segmentation Overview
  • Popular Image Segmentation Architectures
  • FCN Architecture Details
  • Upsampling Methods
  • Encoder in Code
  • Decoder in Code
  • Evaluation with IoU and Dice Score

2 Readings

  • References: FCN
  • Reference: CamVid

U-Net

    • 3 Videos
    • 1 Readings
    • 1 Lab
Show info about module content

1 Labs

  • Implement a UNet

3 Videos

  • U-Net Overview
  • U-Net Code: Encoder
  • U-Net Code: Decoder

1 Readings

  • Reference: U-Net

Instance Segmentation

    • 1 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Instance Segmentation Demo

1 Videos

  • Instance Segmentation

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 3

Week 3 Quiz: Image Segmentation

    • 1 Assignment
Show info about module content

1 Assignment

  • Image Segmentation

Assignment: Image Segmentation of Handwritten Digits

    • 1 Programming
Show info about module content

1 Programming

  • Image Segmentation of Handwritten Digits

Intro to Visualization and Interpretation

    • 3 Videos
    • 2 Lab
Show info about module content

2 Labs

  • Class Activation Maps with Fashion MNIST (Lab #1)
  • Class Activation Maps "Cats vs Dogs" (Lab #2)

3 Videos

  • Why Interpretation Matters?
  • Class Activation Maps
  • Fashion MNIST Class Activation Map code walkthrough

Saliency

    • 1 Videos
    • 1 Lab
Show info about module content

1 Labs

  • Saliency Maps (Lab #3)

1 Videos

  • Saliency

Gradients and Class Activation Maps

    • 1 Videos
    • 1 Readings
    • 1 Lab
Show info about module content

1 Labs

  • GradCAM (Lab #4)

1 Videos

  • GradCAM

1 Readings

  • Reference: GradCam

Improving a model with Interpretation

    • 1 Videos
    • 1 Readings
Show info about module content

1 Videos

  • ZFNet

1 Readings

  • Reference: ZFNet

Lecture Notes (Optional)

    • 1 Readings
Show info about module content

1 Readings

  • Lecture Notes Week 4

Week 4 Quiz: Visualization and Interpretation

    • 1 Assignment
Show info about module content

1 Assignment

  • Visualization and Interpretation

End of Access to Lab Notebooks

    • 1 Readings
Show info about module content

1 Readings

  • [IMPORTANT] Reminder about end of access to Lab Notebooks

Assignment: Cats vs Dogs Saliency Maps

    • 1 Programming
Show info about module content

1 Programming

  • Cats vs Dogs Saliency Maps

Course Resources

    • 1 Readings
Show info about module content

1 Readings

  • References

Acknowledgments

    • 1 Readings
Show info about module content

1 Readings

  • Acknowledgments

Auto Summary

Explore advanced computer vision techniques with TensorFlow in this professional course by Coursera. Learn image classification, segmentation, object localization, and detection using models like regional-CNN, ResNet-50, and Mask-RCNN. Designed for early and mid-career software and ML engineers, this 1140-minute course delves into transfer learning, model customization, and ML interpretation methods. Expand your expertise with hands-on projects and advanced TensorFlow features. Available with a Starter subscription.

Laurence Moroney
Instructor

Laurence Moroney