To get the most out of this book

If you are a beginner in computer vision and TensorFlow and you're trying to master the subject, it is better to go through the book's chapters in sequence rather than jumping around. The book slowly builds on the concepts of computer vision and neural networks and then ends with a code sample. Be sure to get a good grasp of the concepts and architecture presented and then apply the code sample.

We could not upload our image data to GitHub due to size limitations. You can either use images from your own camera or download image datasets from Kaggle:

• Food images (for the burger-and-fries sample): Take photos using your cell phone camera.
• Kaggle furniture detector: https://www.kaggle.com/akkithetechie/furniture-detector

If you do not understand a concept at first, revisit it and also read any cited papers.

Most of the code is written in Jupyter Notebook environments, so make sure that you have downloaded Anaconda. You also need to download TensorFlow 2.0 – follow the instructions in Chapter 1, Computer Vision and TensorFlow Fundamentals, for that.

Much of the object detection training is done using Google Colab – Chapter 10, Object Detection Using R-CNN, SSD and R-FCN, and Chapter 11, Deep Learning on Edge with CPU/GPU Optimization, provide explanations of how to use Google Colab.

If you want to deploy your computer vision code to edge devices and you're thinking about what to purchase, visit Chapter 11, Deep Learning on Edge Devices with CPU/GPU Optimization, for a detailed analysis of various devices.

The book relies heavily on terminal usage – make sure you have developed a basic understanding of that before reading anything from Chapter 7, Object Detection Using YOLO, onward.

Chapter 12, Cloud Computing Platform for Computer Vision, deals with cloud computing, so you must have an Amazon Web Services, Azure, or Google Cloud Platform account for this. Cloud computing can get expensive if you are not keeping track of your hours. Many providers give you free access to services for some time, but after that, charges can go up if your project is still open, even if you are not training. Remember to shut down your project before you end your account to stop accruing charges. If you have technical questions on cloud computing and are stuck, then you can read the documentation of the relevant cloud computing platform. Also, you can open a technical work ticket for a fee; typically, they are addressed within 1-2 business days.

The best way to get the most out of this book is to read the theory, get an understanding of why a model is developed the way it is, try the sample exercises, and then update the code to suit your needs.

If you have any questions about any section of the book and get stuck, you can always contact me on LinkedIn (https://www.linkedin.com/in/krish-kar-554739b2/ext).

Download the example code files

You can download the example code files for this book from your account at www.packt.com. If you purchased this book elsewhere, you can visit www.packt.com/support and register to have the files emailed directly to you.

You can download the code files by following these steps:

1. Log in or register at www.packt.com.
2. Select the SUPPORT tab.
3. Click on Code Downloads & Errata.
4. Enter the name of the book in the Search box and follow the onscreen instructions.

Once the file is downloaded, please make sure that you unzip or extract the folder using the latest version of:

• WinRAR/7-Zip for Windows
• Zipeg/iZip/UnRarX for Mac
• 7-Zip/PeaZip for Linux

The code bundle for the book is also hosted on GitHub at https://github.com/PacktPublishing/Mastering-Computer-Vision-with-TensorFlow-2.0. In case there's an update to the code, it will be updated on the existing GitHub repository.

We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!

Download the color images

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. You can download it here: https://static.packt-cdn.com/downloads/9781838827069_ColorImages.pdf.

Conventions used

There are a number of text conventions used throughout this book.

CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "Each image that is read is converted to grayscale using the OpenCV BGR2GRAY command."

A block of code is set as follows:

faceresize = cv2.resize(detected_face, (img_size,img_size))
        img_name = "dataset/opencv_frame_{}.jpg".format(img_counter)
        cv2.imwrite(img_name, faceresize)

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "The convolutional neural network (CNN) is the most widely used tool in computer vision for classifying and detecting objects."

Warnings or important notes appear like this.

Tips and tricks appear like this.