This is the code repository for Tensorflow 2.0 Computer Vision Cookbook, published by Packt.
Implement machine learning solutions to overcome various computer vision challenges
This book covers recipes for solving various computer vision tasks using TensorFlow, taking you through all the tips and tricks you need to overcome any challenges that you may face while building various computer vision applications. You will discover machine learning techniques to solve problems in image processing, feature extraction, and more.
This book covers the following exciting features:
- Understand how to detect objects using state-of-the-art models such as YOLOv3
- Use AutoML to predict gender and age from images
- Segment images using different approaches such as FCNs and generative models
- Learn how to improve your network’s performance using rank-N accuracy, label smoothing, and test time augmentation
- Enable machines to recognize people’s emotions in videos and real-time streams
If you feel this book is for you, get your copy today!
All of the code is organized into folders. For example, Chapter 2.
The code will look like the following:
def build_network():
input_layer = Input(shape=(32, 32, 1))
x = Conv2D(filters=32,
kernel_size=(3, 3),
padding='same',
strides=(1, 1))(input_layer)
x = ReLU()(x)
x = Dropout(rate=0.5)(x)
x = Flatten()(x)
x = Dense(units=3)(x)
output = Softmax()(x)
return Model(inputs=input_layer, outputs=output)
Following is what you need for this book: This book is for computer vision developers and engineers, as well as deep learning practitioners looking for go-to solutions to various problems that commonly arise in computer vision. You will discover how to employ modern machine learning (ML) techniques and deep learning architectures to perform a plethora of computer vision tasks. Basic knowledge of Python programming and computer vision is required.
With the following software and hardware list you can run all code files present in the book (Chapter 1-12).
| Chapter | Software required | OS required |
|---|---|---|
| 1-12 | Python 3.6+, TensorFlow 2.3+ | Mac OS X, and Linux (Debian Based) |
We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it
Click on the following link to see the Code in Action:
-
Mastering Computer Vision with TensorFlow 2.x [Packt] [Amazon]
-
Applied Deep Learning and Computer Vision for Self-Driving Cars [Packt] [Amazon]
Jesús Martínez He 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.