We may earn an affiliate commission when you visit our partners.
Course image
Laurence Moroney and Eddy Shyu

In this course, you will:

a) Explore image classification, image segmentation, object localization, and object detection. Apply transfer learning to object localization and detection.

Read more

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.

Enroll now

What's inside

Syllabus

Introduction to Computer Vision
Get a conceptual overview of image classification, object localization, object detection, and image segmentation. Also be able to describe multi-label classification, and distinguish between semantic segmentation and instance segmentation. In the rest of this course, you will apply TensorFlow to build object detection and image segmentation models.
Read more
Object Detection
This week, you’ll get an overview of some popular object detection models, such as regional-CNN and ResNet-50. You’ll use object detection models that you’ll retrieve from TensorFlow Hub, download your own models and configure them for training, and also build your own models for object detection. By using transfer learning, you will train a model to detect and localize rubber duckies using just five training examples. You’ll also get to manually label your own rubber ducky images!
Image Segmentation
This week is all about image segmentation using variations of the fully convolutional neural network. With these networks, you can assign class labels to each pixel, and perform much more detailed identification of objects compared to bounding boxes. You’ll build the fully convolutional neural network, U-Net, and Mask R-CNN this week to identify and detect numbers, pets, and even zombies!
Visualization and Interpretability
This week, you’ll learn about the importance of model interpretability, which is the understanding of how your model arrives at its decisions. You’ll also implement class activation maps, saliency maps, and gradient-weighted class activation maps to identify which parts of an image are being used by your model to make its predictions. You’ll also see an example of how visualizing a model’s intermediate layer activations can help to improve the design of a famous network, AlexNet.

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Focuses on model architecture and tools for advanced ML models
Suitable for learners with foundational TensorFlow understanding who seek advanced knowledge and skills
Taught by industry experts Laurence Moroney and Eddy Shyu, who have established reputations in the field
Emphasizes hands-on practice with building and training object detection and image segmentation models using TensorFlow
Covers topics highly relevant to industry and academic research
Requires learners to bring foundational TensorFlow knowledge and mathematical proficiency

Save this course

Save Advanced Computer Vision with TensorFlow to your list so you can find it easily later:
Save

Reviews summary

Praised computer vision course

learners say this course is highly praised and is part of a well-respected specialization in computer vision. Engaging assignments have you loading models and restoring checkpoints from new models found online. The course is excellent for practical implementation and will help you use the most of TensorFlow for Computer Vision. This course is a fantastic resource for anyone looking to dive into application-oriented tasks of computer vision and is a must-do in any AI field training.
Highest rated course in specialization
"I thought this was the best course in the tensorflow series so far!"
"This is by far the richest course I have ever taken on Coursera"
"This course is amazing."
"This class was probably the most challenging so far, but I learned some valuable deep learning techniques."
Excellent practical assignments
"Very informational with easy to do lab assignments with practical implementation for each topics which are shared on video."
"Excellent explanations and practical exercises to help you get going on object detection and semantic segmentation."
Clear explanations and presentations
"Excellent content and great presentation."
"Nicely designed course. great instructor too!"
Assignments can be buggy
"None of my assignment submitted without complaint."
"Course provider made all assignment with very poor ethics, all is good, you pass in the colab but on submission grader not taking your model."
Some assignments were too difficult
"Some of the assignments were really diffucult."
"The assignment of Week 2 on Object Detection as it required too much getting in the customization of a specific model."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Advanced Computer Vision with TensorFlow with these activities:
Review coding fundamentals
Prepare a solid technical foundation for the course by brushing up on basic coding concepts.
Browse courses on TensorFlow
Show steps
  • Review core data structures and algorithms
  • Practice coding in your preferred programming language
  • Explore online coding challenges
Seek guidance from experienced practitioners
Connect with experts in the field to gain valuable insights.
Show steps
  • Identify potential mentors through professional networks or online platforms
  • Reach out and request guidance
  • Attend industry events or workshops to connect with practitioners
Review concepts from linear algebra
Strengthen your mathematical foundation to support your understanding of TensorFlow.
Browse courses on Linear Algebra
Show steps
  • Review textbooks or online resources on linear algebra
  • Solve practice problems to reinforce concepts
  • Identify how linear algebra applies to TensorFlow
Five other activities
Expand to see all activities and additional details
Show all eight activities
Follow tutorials on image classification
Gain a practical understanding of image classification, a fundamental concept in computer vision.
Browse courses on Image Classification
Show steps
  • Identify reliable online tutorials
  • Follow the tutorials step-by-step
  • Experiment with the code snippets provided
Deep Learning with Python
Enhance your understanding of the theoretical foundations of deep learning.
Show steps
  • Read the book thoroughly
  • Work through the exercises and examples provided
  • Relate the concepts to your coursework
Practice exercises on object localization
Sharpen your skills in object localization by working through targeted exercises.
Browse courses on Object Localization
Show steps
  • Find online resources or textbooks with exercises
  • Solve the exercises independently
  • Compare your solutions to provided answers or discuss with peers
Participate in study sessions with peers
Collaborate with fellow students to reinforce concepts and challenge your understanding.
Show steps
  • Form or join a study group
  • Meet regularly to discuss course material
  • Work together on assignments or projects
Build a simple image segmentation model
Apply your knowledge of image segmentation by creating a functional model.
Browse courses on Image Segmentation
Show steps
  • Choose a dataset and define the problem statement
  • Select and implement an appropriate model architecture
  • Train and evaluate the model
  • Deploy the model and test its performance

Career center

Learners who complete Advanced Computer Vision with TensorFlow will develop knowledge and skills that may be useful to these careers:
Computer Vision Scientist
Computer Vision Scientists research new computer vision algorithms and techniques. They may work on a variety of topics, from image classification to object detection to image segmentation. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Autonomous Vehicle Engineer
Autonomous Vehicle Engineers design, build, and maintain autonomous vehicles. They may work on a variety of technologies, from computer vision to sensor fusion to control systems. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Computational Photographer
Computational Photographers use computer vision techniques to enhance and manipulate photographs. They may work on a variety of applications, from photo editing to image forensics. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Human-Computer Interaction Researcher
Human-Computer Interaction Researchers study how people interact with computers. They may work on a variety of topics, from user interface design to user experience. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Medical Image Analyst
Medical Image Analysts use computer vision techniques to analyze medical images. They may work on a variety of applications, from disease diagnosis to treatment planning. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Product Manager
Product Managers plan and develop software products. They may work on a variety of topics, from market research to product design to product launch. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
User Experience Designer
User Experience Designers design and develop user interfaces for websites, mobile applications, and other software products. They may work on a variety of topics, from information architecture to visual design. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Remote Sensing Scientist
Remote Sensing Scientists use computer vision techniques to analyze images taken from satellites or airplanes. They may work on a variety of applications, from land use mapping to environmental monitoring. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Computer Graphics Engineer
Computer Graphics Engineers design, develop, and maintain computer graphics systems. They may work on a variety of applications, from video games to movies to virtual reality. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Artificial Intelligence Researcher
Artificial Intelligence Researchers develop new artificial intelligence algorithms and techniques. They may work on a variety of topics, from machine learning to natural language processing to computer vision. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Machine Learning Engineer
Machine Learning Engineers research, design, and build artificial intelligence systems. They may work on natural language processing, speech recognition, computer vision, or other areas of machine learning. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Software Engineer
Software Engineers design, develop, and maintain software systems. They may work on a variety of software applications, from web applications to mobile applications to desktop applications. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Robotics Engineer
Robotics Engineers design, build, and maintain robots. They may work on a variety of robots, from industrial robots to medical robots to autonomous vehicles. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Computer Vision Engineer
Computer Vision Engineers develop, test, and maintain computer vision systems. These systems use artificial intelligence to interpret and understand the visual world. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.
Data Scientist
Data Scientists use data to solve business problems. They may work on data analysis, machine learning, or other areas of data science. This course "Advanced Computer Vision with TensorFlow" may be useful to someone working in this role because it provides an overview of image classification, object localization, object detection, and image segmentation, which are all important tasks in computer vision.

Reading list

We've selected eight books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Advanced Computer Vision with TensorFlow.
Provides a comprehensive and up-to-date overview of computer vision, covering topics such as image formation, feature extraction, object recognition, and image segmentation. It valuable resource for both beginners and experienced practitioners in the field.
Provides a comprehensive overview of digital image processing, covering topics such as image enhancement, image restoration, image compression, and image analysis. It valuable resource for those who want to learn the fundamentals of digital image processing.
Provides a comprehensive overview of computer vision algorithms and techniques, covering topics such as image formation, feature extraction, object recognition, and image segmentation. It valuable resource for both beginners and experienced practitioners in the field.
Provides a practical guide to deep learning for computer vision tasks, covering topics such as image classification, object detection, and semantic segmentation. It good resource for those who want to learn how to apply deep learning to real-world computer vision problems.
Provides a practical guide to OpenCV 4 computer vision with Python 3, covering topics such as image processing, feature extraction, object recognition, and image segmentation. It good resource for those who want to learn how to use OpenCV 4 for computer vision tasks.
Provides a comprehensive overview of pattern recognition and machine learning, covering topics such as supervised and unsupervised learning, dimensionality reduction, and Bayesian methods. It valuable resource for those who want to learn the foundations of machine learning.
Provides a practical guide to deep learning with Python, covering topics such as building and training neural networks, using pre-trained models, and deploying models to production. It good resource for those who want to learn how to use Python for deep learning tasks.
Provides a practical guide to computer vision with Python, covering topics such as image processing, feature extraction, object recognition, and image segmentation. It good resource for those who want to learn how to use Python for computer vision tasks.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Advanced Computer Vision with TensorFlow.
Machine Learning in ArcGIS : Map Land Use Land Cover in...
Most relevant
Object-based Image Analysis & Classification in QGIS...
Most relevant
Object Localization with TensorFlow
Most relevant
Visual Perception for Self-Driving Cars
Most relevant
Deep Learning Applications for Computer Vision
Most relevant
Machine Learning: Modern Computer Vision & Generative AI
Most relevant
Creating an Object Detection Application Using TensorFlow
Most relevant
Implementing Image Recognition Systems with TensorFlow 1
Most relevant
Generative Deep Learning with TensorFlow
Most relevant
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser