Advanced Computer Vision with TensorFlow

Mark as Favorite Share
image

What Will You Learn?

In this course, you will:
Explore image classification, segmentation, object localization, and detection.
Apply transfer learning to object localization and detection.
Implement object detection models like regional-CNN and ResNet-50.
Customize existing models and build your own for detecting, localizing, and labeling images, including personalized rubber duck images.
Implement image segmentation using variations of fully convolutional networks (FCN), including U-Net and Mask-RCNN.
Identify and detect objects such as numbers, pets, and zombies through image segmentation.
Utilize class activation maps and saliency maps to interpret and improve the design of networks, with a focus on the famous AlexNet.
Inspect and enhance model predictions by understanding which parts of an image are used by the model in making predictions.
Apply machine learning interpretation methods to refine network design and improve performance.

About This Course

Provider: Coursera
Format: Online
Duration: 19 hours to complete [Approx]
Target Audience: Intermediate
Learning Objectives: Upon completion, you will master image classification, segmentation, object localization, and detection, applying transfer learning, customizing models, and building your own for tasks like rubber duck detection and image segmentation with FCN variants.
Course Prerequisites: Basic calculus, linear algebra, stats, Knowledge of AI, deep learning, Experience with Python, TF/Keras/PyTorch framework, decorator, context manager
Assessment and Certification: Earn a Certificate upon completion from the relevant Provider
Instructor: DeepLearning.AI
Key Topics: TensorFlow Object Detection API, Class Activation Maps, Model Interpretability, Image Segmentation, Salience, Computer Vision
Topic Covered: 
  1. - Classification and Object Detection Intro
  2. - Segmentation Intro
  3. - Why Transfer Learning?
  4. - What is Transfer Learning?
  5. - Options in Transfer Learning
  6. - Transfer Learning with ResNet50
  7. - ResNet50 in code
  8. - Network architecture for Object Localization
  9. - Evaluating Object Localization
  10. - Object Detection and Sliding Windows
  11. - R-CNN
  12. - Fast R-CNN
  13. - Faster R-CNN
  14. - Getting the Model from TensorFlow Hub
  15. - Running the Model on an Image
  16. - Installation and overview of APIs
  17. - Visualization with APIs
  18. - Loading a RetinaNet Model
  19. - Loading Weights
  20. - Data Prep and Training Overview
  21. - Custom Training Loop Code
  22. - Image Segmentation Overview
  23. - Popular Image Segmentation Architectures
  24. - FCN Architecture Details
  25. - Upsampling Methods
  26. - Encoder in Code
  27. - Decoder in Code
  28. - Evaluation with IoU and Dice Score
  29. - U-Net Overview
  30. - U-Net Code: Encoder
  31. - U-Net Code: Decoder
  32. - Instance Segmentation
  33. - Why Interpretation Matters?
  34. - Class Activation Maps
  35. - Fashion MNIST Class Activation Map code walkthrough
  36. - Saliency
  37. - GradCAM
  38. - ZFNet

0 Comments

No reviews yet !!

Please login first