Martínez TensorFlow 2.0 Computer Vision Cookbook

Implement machine learning solutions to overcome various computer vision challenges
1. Auflage 2021
ISBN: 978-1-83882-068-8
Verlag: De Gruyter
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, 542 Seiten

No detailed description available for "TensorFlow 2.0 Computer Vision Cookbook".

Autoren/Hrsg.

Martínez, Jesús

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Theoretische Informatik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Mustererkennung, Biometrik
• Mathematik | Informatik EDV | Informatik Informatik Bildsignalverarbeitung
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Computer Vision

Inhaltsverzeichnis

Table of Contents - Getting Started with TensorFlow 2.x for Computer Vision
- Performing Image Classification
- Harnessing the Power of Pre-Trained Networks with Transfer Learning
- Enhancing and Styling Images with DeepDream, Neural Style Transfer, and Image Super-Resolution
- Reducing Noise with Autoencoders
- Generative Models and Adversarial Attacks
- Captioning Images with CNNs and RNNs
- Fine-Grained Understanding of Images through Segmentation
- Localizing Elements in Images with Object Detection
- Applying the Power of Deep Learning to Videos
- Streamlining Network Implementation with AutoML
- Boosting Performance

Über Autor(innen)

Martínez Jesús:
Jesús Martínez is the founder of the computer vision e-learning site DataSmarts. He is a computer vision expert and has worked on a wide range of projects in the field, such as a piece of people-counting software fed with images coming from an RGB camera and a depth sensor, using OpenCV and TensorFlow. He developed a self-driving car in a simulation, using a convolutional neural network created with TensorFlow, that worked solely with visual inputs. Also, he implemented a pipeline that uses several advanced computer vision techniques to track lane lines on the road, as well as providing extra information such as curvature degree.