Share E-Book
Scan to open this page

Scan with your phone to open this page

AuthorAnirudh Koul, Siddha Ganju, Meher Kasam

Whether you're a software engineer aspiring to enter the world of deep learning, a veteran data scientist, or a hobbyist with a simple dream of making the next viral AI app, you might have wondered where to begin. This step-by-step guide teaches you how to build practical deep learning applications for the cloud, mobile, browsers, and edge devices using a hands-on approach. If your goal is to build something creative, useful, scalable, or just plain cool, this book is for you. Relying on decades of combined industry experience transforming deep learning research into award-winning applications, Anirudh Koul, Siddha Ganju, and Meher Kasam guide you through the process of converting an idea into something that people in the real world can use. Train, tune, and deploy computer vision models with Keras, TensorFlow, Core ML, and TensorFlow Lite. Develop AI for a range of devices including Raspberry Pi, Jetson Nano, and Google Coral. Explore fun projects, from Silicon Valley's Not Hotdog app to 40+ industry case studies. Simulate an autonomous car in a video game environment and build a miniature version with reinforcement learning. Use transfer learning to train models in minutes. Discover 50+ practical tips for maximizing model accuracy and speed, debugging, and scaling to millions of users.

AI Reading Assistant

Whole-book reading guide from stratified index samples; jump to passages in the text

Brief outline
【One-Line Pitch】 Whether you're a software engineer aspiring to enter the world of deep learning, a veteran data scientist, or a hobby… 【Book Arc】 - **Opening (~0%–12%)**: If your goal is to build something creative, useful, scalable, or just plain cool, this book is for you.; Real-Time Object Classification on iOS with Core ML. - **Early (~12%–35%)**: Recipe for the Perfect Deep Learning Solution Before Gordon Ramsay starts cooking, he ensures he has all of the ingredients ready to go.; yer over other libraries, making rapid prototyping possible. - **Middle (~35%–65%)**: curacy for each PCA dimension') plt.xlabel('Test Time') plt.ylabel('Accuracy') plt.grid(True) plt.show() Figure 4-14.; The downside with that approach is that it’s not real time. - **Late (~65%–88%)**: t hundreds of images in three minutes or less with a Chrome extension called Fatkun Batch Download Image.; arison to images that the model can already easily classify. - **Ending (~88%–100%)**: Bringing our trained model to the browser is an easy task.; // PoseNet callback function poseNet.on('pose', function (results) { const poses results; 【Key Takeaways】 - **If your goal is to bui…** (Opening): If your goal is to build something creative, useful, scalable, or just plain cool, this book is for you. - **Real-Time Object Class…** (Opening): Real-Time Object Classification on iOS with Core ML. - **And then we pit them a…** (Opening): And then we pit them against each other in an open benchmark —you might be surprised who won. - **Recipe for the Perfect…** (Early): Recipe for the Perfect Deep Learning Solution Before Gordon Ramsay starts cooking, he ensures he has all of the ingredients ready to go. - **yer over other libraries** (Early): yer over other libraries, making rapid prototyping possible. - **a pretrained model** (Early): a pretrained model, remove the last few task-specific lay‐ ers, and append a new classifier layer. 【Reading Tips】 - Use Passage locations below to jump into the text and set reading anchors - If this is a brief outline, click Regenerate (top right) for a synthesized guide 【Coverage Limits】 Compressed outline without the model (~33 index chunks). Full structured guide needs AI available.
Page 11
ck 265 Summary 266 10. AI in the Browser with TensorFlow.js and ml5.js. . . . . . . . . . . . . . . . . . . . . . . . . . . . 267 JavaScript-Based Machine Le...
View in text
Excerpt 2
yer over other libraries, making rapid prototyping possible. This made the learning curve a lot less steep for beginners of deep learning. At the same time,...
View in text
Excerpt 3
training images. Not bad! And by the 10th step, we observe about 97% validation accuracy. That’s the power of transfer learning. Let us take a moment to appr...
View in text
Excerpt 4
None) # Passing the image through Grad CAM grid = explainer.explain(data, model, 'conv1', index) name = IMAGE_PATH.split(".jpg")[0] explainer.save(grid, '/tm...
View in text
Excerpt 5
rds, until it begins to perform well on the training set. 3. Train on a larger sample (or even the entire training set). 172 | Chapter 6: Maximizing Speed an...
View in text
Excerpt 6
od balance between precision and recall across all services. At a high confidence threshold such as 0.99, a classifier might be very accurate, but there migh...
View in text
Excerpt 7
silly. You like to dream big. How about 100 million people? That’s a nice round number. Now con‐ vincing 100 million people to download and install an app an...
View in text
Excerpt 8
he box, including the ability to run TensorFlow Lite models. Some of the features
View in text
Tags
AI categories
Python
ISBN: 149203486X
Publisher: O'Reilly Media
Publish Year: 2019
Language: English
Pages: 620
File Format: PDF
File Size: 18.8 MB
Text Preview (First 20 pages)
Registered users can read the full content for free

Register as a Gaohf Library member to read the complete e-book online for free and enjoy a better reading experience.

Generating text preview…