Course Overview
Computer Vision solutions are becoming increasingly common, making their way into fields such as health, automobile, social media, and robotics. Hands-On Computer Vision with Tensorflow is a hands-on course that thoroughly explores TensorFlow, the brand-new version of Google's open source framework for machine learning. You will understand how to benefit from using convolutional neural networks (CNNs) for visual tasks.
This course begins with the fundamentals of computer vision and deep learning, teaching you how to build a neural network from scratch. You will discover the features that have made TensorFlow the most widely used AI library, along with its intuitive Keras interface. You'll then move on to building, training, and deploying CNNs efficiently. Complete with concrete code examples, the course demonstrates how to classify images with modern solutions, such as Inception and ResNet, and extract specific content using You Only Look Once (YOLO), Mask R-CNN, and U-Net. You will also build generative adversarial networks (GANs) and variational autoencoders (VAEs) to create and edit images, and long short-term memory networks (LSTMs) to analyze videos. In the process, you will acquire advanced insights into transfer learning, data augmentation, domain adaptation, and mobile and web deployment, among other key concepts.
Who should attend
This course is geared for attendees with Intermediate IT skills who wish to learn Computer Vision with tensor flow 2.
Prerequisites
Students should have
- Basic to Intermediate IT Skills. have some knowledge of Python.
- Good basic understanding of image representation (pixels, channels, etc.)
- Understanding of Matrix manipulation (shapes, products, etc.)
Take Before: We recommend attendees have the skills in the course(s) listed below, or attend them as a pre-requisite:
- TTPS4800 Introduction to Python Programming Basics
Course Objectives
- Build, train, and serve your own deep neural networks with TensorFlow 2 and Keras
- Apply modern solutions to a wide range of applications such as object detection and video analysis
- Run your models on mobile devices and web pages and improve their performance.
- Create your own neural networks from scratch
- Classify images with modern architectures including Inception and ResNet
- Detect and segment objects in images with YOLO, Mask R-CNN, and U-Net
- Tackle problems faced when developing self-driving cars and facial emotion recognition systems
- Boost your application’s performance with transfer learning, GANs, and domain adaptation
- Use recurrent neural networks (RNNs) for video analysis
- Optimize and deploy your networks on mobile devices and in the browser
Outline: Deep Learning with Vision Systems | Hands-On Computer Vision (TTAI3020)
1. Computer Vision and Neural Networks
- Computer Vision and Neural Networks
- Technical requirements
- Computer vision in the wild
- A brief history of computer vision
- Getting started with neural networks
2. TensorFlow Basics and Training a Model
- TensorFlow Basics and Training a Model
- Technical requirements
- Getting started with TensorFlow 2 and Keras
- TensorFlow 2 and Keras in detail
- The TensorFlow ecosystem
3. Modern Neural Networks
- Modern Neural Networks
- Technical requirements
- Discovering convolutional neural networks
- Refining the training process
4. Influential Classification Tools
- Influential Classification Tools
- Technical requirements
- Understanding advanced CNN architectures
- Leveraging transfer learning
5. Object Detection Models
- Object Detection Models
- Technical requirements
- Introducing object detection
- A fast object detection algorithm – YOLO
- Faster R-CNN – a powerful object detection model
6. Enhancing and Segmenting Images
- Enhancing and Segmenting Images
- Technical requirements
- Transforming images with encoders-decoders
- Understanding semantic segmentation
7. Training on Complex and Scarce Datasets
- Training on Complex and Scarce Datasets
- Technical requirements
- Efficient data serving
- How to deal with data scarcity
8. Video and Recurrent Neural Networks
- Video and Recurrent Neural Networks
- Technical requirements
- Introducing RNNs
- Classifying videos
9. Optimizing Models and Deploying on Mobile Devices
- Optimizing Models and Deploying on Mobile Devices
- Technical requirements
- Optimizing computational and disk footprints
- On-device machine learning
- Example app – recognizing facial expressions