ratings
Computer vision solutions are becoming increasingly common, making their way into fields such as health, automobile, social media, and robotics. Hands-On Computervision with TensorFlow 2 is a hands-on course that thoroughly explores TensorFlow 2, the brand-new version of Google's open source framework for machine learning
Unlimited Duration
March 4, 2021
This “skills-centric” course is about 50% hands-on lab and 50% lecture, with extensive practical exercises designed to reinforce fundamental skills, concepts and best practices taught throughout the course.In this course you learn about:
· 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
Course Curriculum
-
- Computer Vision and Neural Networks 00:00:00
- Technical requirements 00:00:00
- Computer vision in the wild 00:00:00
- A brief history of computer vision 00:00:00
- Getting started with neural networks 00:00:00
-
- TensorFlow Basics and Training a Model 00:00:00
- Technical requirements 00:00:00
- Getting started with TensorFlow 2 and Keras 00:00:00
- TensorFlow 2 and Keras in detail 00:00:00
- The TensorFlow ecosystem 00:00:00
- Modern Neural Networks 00:00:00
- Technical requirements 00:00:00
- Discovering convolutional neural networks 00:00:00
- Refining the training process 00:00:00
- Object Detection Models 00:00:00
- Technical requirements 00:00:00
- Introducing object detection 00:00:00
- A fast object detection algorithm – YOLO 00:00:00
- Faster R-CNN – a powerful object detection model 00:00:00
- Training on Complex and Scarce Datasets 00:00:00
- Technical requirements 00:00:00
- Efficient data serving 00:00:00
- How to deal with data scarcity 00:00:00
- Optimizing Models and Deploying on Mobile Devices 00:00:00
- Technical requirements 00:00:00
- Optimizing computational and disk footprints 00:00:00
- On-device machine learning 00:00:00
- Example app – recognizing facial expressions 00:00:00
Course Reviews

Students