book

Deep Learning with MXNet Cookbook

Name: Deep Learning with MXNet Cookbook
Author: Andrés P. Torres
ISBN: 9781800569607

by Andrés P. Torres

December 2023

Intermediate to advanced

370 pages

8h 55m

English

Packt Publishing

Read now

Unlock full access

Deep Learning with MXNet Cookbook
ForewordContributorsAbout the authorAbout the reviewers
Preface
Who is this book for?What this book coversTo get the most out of this bookDownload the example code filesConventions usedGet in touchShare Your ThoughtsDownload a free PDF copy of this book
Chapter 1: Up and Running with MXNet
Technical requirementsInstalling MXNet, Gluon, GluonCV, and GluonNLPGetting readyHow to do it...How it works...There’s more…NumPy and MXNet ND arraysGetting readyHow to do it...How it works...There’s more…
Chapter 2: Working with MXNet and Visualizing Datasets – Gluon and DataLoader
Technical requirementsUnderstanding regression datasets – loading, managing, and visualizing the House Sales datasetGetting readyHow to do it...How it works...There’s more…Understanding classification datasets – loading, managing, and visualizing the Iris datasetGetting readyHow to do it...How it works...There’s more…Understanding image datasets – loading, managing, and visualizing the Fashion-MNIST datasetGetting readyHow to do it...How it works...There’s more…Understanding text datasets – loading, managing, and visualizing the Enron Email datasetGetting readyHow to do it...How it works...There’s more…
Chapter 3: Solving Regression Problems
Technical requirementsUnderstanding the math of regression modelsGetting readyHow to do it...How it works...There’s more…Defining loss functions and evaluation metrics for regressionGetting readyHow to do it...How it works...There’s more...Training regression modelsGetting readyHow to do it...How it works...There’s more...Evaluating regression modelsGetting readyHow to do it...How it works...There’s more...
Chapter 4: Solving Classification Problems
Technical requirementsUnderstanding math for classification modelsGetting readyHow to do it...How it works...There’s more…Defining loss functions and evaluation metrics for classificationGetting readyHow to do it...How it works...There’s more...Training for classification modelsGetting readyHow to do it...How it works...There’s more...Evaluating classification modelsGetting readyHow to do it...How it works...There’s more...
Chapter 5: Analyzing Images with Computer Vision
Technical requirementsUnderstanding convolutional neural networksGetting readyHow to do it...How it works…There’s more...Classifying images with MXNet – GluonCV Model Zoo, AlexNet, and ResNetGetting readyHow to do it...How it works...There’s more...Detecting objects with MXNet – Faster R-CNN and YOLOGetting readyHow to do it...How it works...There’s more...Segmenting objects in images with MXNet – PSPNet and DeepLab-v3Getting readyHow to do it...How it works...There’s more...
Chapter 6: Understanding Text with Natural Language Processing
Technical requirementsIntroducing NLP networksGetting readyHow to do it...Introducing Recurrent Neural Networks (RNNs)Improving RNNs with Long Short-Term Memory (LSTM)Introducing GluonNLP Model ZooPaying attention with TransformersHow it works...There’s more...Classifying news highlights with topic modelingGetting readyHow to do it...How it works...There’s more...Analyzing sentiment in movie reviewsGetting readyHow to do it...How it works...There’s more...Translating text from Vietnamese to EnglishGetting readyHow to do it...How it works...There’s more...
Chapter 7: Optimizing Models with Transfer Learning and Fine-Tuning
Technical requirementsUnderstanding transfer learning and fine-tuningGetting readyHow to do it...How it works…There’s more...Improving performance for classifying imagesGetting readyHow to do it...Revisiting the ImageNet-1k and Dogs vs Cats datasetsHow it works…There’s more...Improving performance for segmenting imagesGetting readyHow to do it...How it works…There’s more...Improving performance for translating English to GermanGetting readyHow to do it...How it works…There’s more...
Chapter 8: Improving Training Performance with MXNet
Technical requirementsIntroducing training optimization featuresGetting readyHow to do it...How it works...There’s more…Optimizing training for image segmentationGetting readyHow to do it...How it works...There’s more…Optimizing training for translating text from English to GermanGetting readyHow to do it...How it works...There’s more…

Chapter 9: Improving Inference Performance with MXNet
Technical requirementsIntroducing inference optimization featuresGetting readyHow to do it...How it works...There’s more…Optimizing inference for image segmentationGetting readyHow to do it...How it works...There’s more…Optimizing inference when translating text from English to GermanGetting readyHow to do it...How it works...There’s more…
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare Your ThoughtsDownload a free PDF copy of this book

Overview

Deep Learning with MXNet Cookbook is your hands-on guide to creating high-performance AI models using the Apache MXNet deep learning framework. With step-by-step practical recipes, this book helps you unlock the potential of MXNet in fields like computer vision and NLP, enhancing scalability and efficiency.

What this Book will help me do

Building deep learning models using the MXNet and Gluon libraries for classification and regression tasks.
Applying techniques such as transfer learning to fine-tune models for specific applications, including vision and text.
Creating and managing neural network architectures like CNNs, RNNs, LSTMs, and Transformers.
Deploying models on various platforms using scalable and efficient methods.
Optimizing both training and inference processes for accuracy and performance.

Author(s)

Andrés P. Torres, the author of this book, is a seasoned expert in artificial intelligence and deep learning technologies. With years of experience working on neural network architectures and deploying advanced AI solutions, Andrés brings a wealth of practical knowledge to his writing. His approach ensures readers not only understand but also effectively apply concepts to real-world scenarios.

Who is it for?

This book is crafted for data scientists, machine learning engineers, and developers keen on leveraging Apache MXNet to build robust deep learning solutions. Suitable for learners with Python programming knowledge and a working coding environment setup, it also benefits those with a foundational understanding of mathematics in AI. If you're aspiring to enhance scalability and performance in your projects, this book is for you.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Mastering ARKit: Apple’s Augmented Reality App Development Platform

Publisher Resources

ISBN: 9781800569607

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills