Worth: $65.99
(as of Aug 07, 2025 13:37:11 UTC – Particulars)
“We lastly have the definitive treatise on PyTorch! It covers the fundamentals and abstractions in nice element. I hope this ebook turns into your prolonged reference doc.” —Soumith Chintala, co-creator of PyTorch
Key Options
Written by PyTorch’s creator and key contributors
Develop deep studying fashions in a well-recognized Pythonic method
Use PyTorch to construct a picture classifier for most cancers detection
Diagnose issues together with your neural community and enhance coaching with information augmentation
Buy of the print ebook features a free eBook in PDF, Kindle, and ePub codecs from Manning Publications.
About The Guide
Each different day we hear about new methods to place deep studying to good use: improved medical imaging, correct bank card fraud detection, lengthy vary climate forecasting, and extra.
PyTorch places these superpowers in your palms. Immediately acquainted to anybody who is aware of Python information instruments like NumPy and Scikit-learn, PyTorch simplifies deep studying with out sacrificing superior options. It’s nice for constructing fast fashions, and it scales easily from laptop computer to enterprise.
Deep Studying with PyTorch teaches you to create deep studying and neural community programs with PyTorch. This sensible ebook will get you to work straight away constructing a tumor picture classifier from scratch. After overlaying the fundamentals, you’ll study greatest practices for the whole deep studying pipeline, tackling superior initiatives as your PyTorch abilities turn out to be extra subtle. All code samples are simple to discover in downloadable Jupyter notebooks.
What You Will Be taught
Understanding deep studying information constructions akin to tensors and neural networksBest practices for the PyTorch Tensor API, loading information in Python, and visualizing resultsImplementing modules and loss functionsUtilizing pretrained fashions from PyTorch HubMethods for coaching networks with restricted inputsSifting by way of unreliable outcomes to diagnose and repair issues in your neural networkImprove your outcomes with augmented information, higher mannequin structure, and positive tuning
This Guide Is Written For
For Python programmers with an curiosity in machine studying. No expertise with PyTorch or different deep studying frameworks is required.
About The Authors
Eli Stevens has labored in Silicon Valley for the previous 15 years as a software program engineer, and the previous 7 years as Chief Technical Officer of a startup making medical gadget software program. Luca Antiga is co-founder and CEO of an AI engineering firm positioned in Bergamo, Italy, and a daily contributor to PyTorch. Thomas Viehmann is a Machine Studying and PyTorch speciality coach and advisor based mostly in Munich, Germany and a PyTorch core developer.
Desk of Contents
PART 1 – CORE PYTORCH
1 Introducing deep studying and the PyTorch Library
2 Pretrained networks
3 It begins with a tensor
4 Actual-world information illustration utilizing tensors
5 The mechanics of studying
6 Utilizing a neural community to suit the information
7 Telling birds from airplanes: Studying from photographs
8 Utilizing convolutions to generalize
PART 2 – LEARNING FROM IMAGES IN THE REAL WORLD: EARLY DETECTION OF LUNG CANCER
9 Utilizing PyTorch to battle most cancers
10 Combining information sources right into a unified dataset
11 Coaching a classification mannequin to detect suspected tumors
12 Enhancing coaching with metrics and augmentation
13 Utilizing segmentation to seek out suspected nodules
14 Finish-to-end nodule evaluation, and the place to go subsequent
PART 3 – DEPLOYMENT
15 Deploying to manufacturing
Writer : Manning
Publication date : Aug. 4 2020
Version : First Version
Language : English
Print size : 520 pages
ISBN-10 : 1617295264
ISBN-13 : 978-1617295263
Merchandise weight : 885 g
Dimensions : 18.75 x 2.79 x 23.5 cm
Finest Sellers Rank: #77,047 in Books (See High 100 in Books) #11 in Machine Principle #17 in Algorithms Textbooks #21 in AI Principle of Computing
Buyer Critiques: 4.4 4.4 out of 5 stars 133 rankings var dpAcrHasRegisteredArcLinkClickAction; P.when(‘A’, ‘prepared’).execute(perform(A) { if (dpAcrHasRegisteredArcLinkClickAction !== true) { dpAcrHasRegisteredArcLinkClickAction = true; A.declarative( ‘acrLink-click-metrics’, ‘click on’, { “allowLinkDefault”: true }, perform (occasion) { if (window.ue) 0) + 1); } ); } }); P.when(‘A’, ‘cf’).execute(perform(A) { A.declarative(‘acrStarsLink-click-metrics’, ‘click on’, { “allowLinkDefault” : true }, perform(occasion){ if(window.ue) 0) + 1); }); });
