Explore

Advanced Computer Vision with TensorFlow

Approx. 24 hours to complete

Save Course

Go to Course

Course Summary

This course is designed for computer vision enthusiasts who want to learn advanced techniques using TensorFlow. Gain hands-on experience in object detection, image segmentation, and more.

Key Learning Points

Learn advanced computer vision techniques using TensorFlow
Implement object detection and image segmentation algorithms
Gain hands-on experience through coding exercises and projects

Learning Outcomes

Ability to implement advanced computer vision techniques using TensorFlow
Understanding of object detection and image segmentation algorithms
Hands-on experience through coding exercises and projects

Prerequisites or good to have knowledge before taking this course

Familiarity with Python and TensorFlow programming
Basic knowledge of computer vision and machine learning

Course Difficulty Level

Advanced

Course Format

Online
Self-paced

Similar Courses

Computer Vision Basics
Deep Learning
Convolutional Neural Networks

Related Education Paths

Related Books

Description

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.

Outline

Introduction to Computer Vision
Welcome to Course 3
Classification and Object Detection Intro
Segmentation Intro
Why Transfer Learning?
What is Transfer Learning?
Options in Transfer Learning
Transfer Learning with ResNet50
ResNet50 in code
Network architecture for Object Localization
Evaluating Object Localization
Pre-Requisite & References
Connect with your mentors and fellow learners on Slack!
Introduction and Concepts of Computer Vision

Object Detection
Object Detection and Sliding Windows
R-CNN
Fast R-CNN
Faster R-CNN
Getting the Model from TensorFlow Hub
Running the Model on an Image
Installation and overview of APIs
Visualization with APIs
Loading a RetinaNet Model
Loading Weights
Data Prep and Training Overview
Custom Training Loop Code
References: Amazon Rekognition, PowerAI & DIGITS
Reference: R-CNN, Fast R-CNN
Reference: TensorFlow Hub
Read about the Object Detection API
Use the Object Detection API
Reference: RetinaNet, Model Garden
Eager Few Shot Object Detection
Object Detection

Image Segmentation
Image Segmentation Overview
Popular Image Segmentation Architectures
FCN Architecture Details
Upsampling Methods
Encoder in Code
Decoder in Code
Evaluation with IoU and Dice Score
U-Net Overview
U-Net Code: Encoder
U-Net Code: Decoder
Instance Segmentation
References: FCN
Reference: CamVid
Reference: U-Net
Image Segmentation

Visualization and Interpretability
Why Interpretation Matters?
Class Activation Maps
Fashion MNIST Class Activation Map code walkthrough
Saliency
GradCAM
ZFNet
Reference: GradCam
Reference: ZFNet
References
Acknowledgments
Visualization and Interpretation

Summary of User Reviews

Key Aspect Users Liked About This Course

Real-world projects and hands-on experience with TensorFlow

Pros from User Reviews

In-depth coverage of advanced computer vision techniques
Excellent instructors with practical experience
Challenging and engaging projects that apply the concepts learned
Great platform for learning and practicing TensorFlow
Highly relevant and up-to-date content

Cons from User Reviews

Requires prior knowledge of computer vision and TensorFlow
Some projects may be too difficult for beginners
Course material can be overwhelming at times
Limited interaction with instructors
No certification or accreditation offered

Recommended for you

Master Computer Vision™ OpenCV4 in Python with Deep Learning

Master OpenCV4 like a pro while learning Dlib, Deep Learning Computer Vision (Keras, TensorFlow & Caffe) + 21 Projects! ====================================================== ======================================================...

Save Course

PyTorch for Deep Learning and Computer Vision

Build Highly Sophisticated Deep Learning and Computer Vision Applications with PyTorch PyTorch has rapidly become one of the most transformative frameworks in the field of Deep Learning....

Save Course

Build Virtual Reality Games for Android and iPhone

Complete guide to quickly build and publish VR games using Unity By now everyone has heard about Virtual Reality games. Now is the time to start making virtual reality games....

Save Course

How to Win a Data Science Competition: Learn from Top Kagglers

At the same time you get to do it in a competitive context against thousands of participants where each one tries to build the most predictive algorithm....

Save Course