September 2024
Intermediate to advanced
624 pages
18h 22m
German
Content preview from Deep Learning für Programmierer mit fastai und PyTorch
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,
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.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.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.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.
Kapitel 11. Data Munging mit der fastai Mid-Level API
Diese Arbeit wurde mithilfe von KI übersetzt. Wir freuen uns über dein Feedback und deine Kommentare: translation-feedback@oreilly.com
Wir haben gesehen, was Tokenizer und Numericalize mit einer Sammlung vonTexten machen und wie sie in der Datenblock-API verwendet werden, die diese Transformationen direkt über TextBlock abwickelt. Aber was ist, wenn wir nur eine dieser Transformationen anwenden wollen, entweder um Zwischenergebnisse zu sehen oder weil wir bereits tokenisierte Texte haben? Was können wir generell tun, wenn die Datenblock-API nicht flexibel genug ist, um unseren speziellen Anwendungsfall zu erfüllen? Dazu müssen wir die mittlere API von fastai für die Verarbeitung von Daten nutzen. Die Datenblock-APIbaut auf dieser Schicht auf und ermöglicht es dir, alles zu tun, was die Datenblock-API kann, und noch viel mehr.
Tieferer Einblick in die fastai-API (Layered API)
Die fastai-Bibliothek ist auf einer mehrschichtigen API aufgebaut. In der obersten Schicht befinden sich Anwendungen, mit denen wir ein Modell in fünf Codezeilentrainieren können, wie wir in Kapitel 1 gesehen haben. Bei der Erstellung vonDataLoaders für einen Textklassifikator haben wir z. B. diese Zeile verwendet:
fromfastai.text.allimport*dls=TextDataLoaders.from_folder(untar_data(URLs.IMDB),valid='test')
Die Werksmethode TextDataLoaders.from_folder ist sehr praktisch, wenndeine Daten genau so angeordnet sind wie der IMDb-Datensatz, aber in der ...
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.
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.
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.
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.