April 2025
Intermediate to advanced
624 pages
17h 41m
Portuguese (Portugal, Brazil)
Content preview from Deep Learning para programadores com fastai e 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.
Capítulo 7. Treinar um modelo de última geração
Este trabalho foi traduzido com recurso a IA. Agradecemos o teu feedback e comentários: translation-feedback@oreilly.com
Este capítulo apresenta técnicas mais avançadas para treinar um modelo de classificação de imagens e obter resultados de última geração. Podes saltá-lo se quiseres aprender mais sobre outras aplicações da Deep Learning e voltar a ele mais tarde - o conhecimento deste material não será assumido em capítulos posteriores.
Veremos o que é a normalização, uma poderosa técnica de aumento de dados chamada Mixup, a abordagem de redimensionamento progressivo e o aumento do tempo de teste. Para mostrar tudo isto, vamos treinar um modelo de raiz (sem utilizar a aprendizagem por transferência) utilizando um subconjunto do ImageNet chamadoImagenette. Contém um subconjunto de 10 categorias muito diferentes do conjunto de dados ImageNet original, o que permite um treino mais rápido quando queremos fazer experiências.
Isto vai ser muito mais difícil de fazer bem do que com os nossos conjuntos de dados anteriores, porque estamos a utilizar imagens a cores e em tamanho real, que são fotografias de objectos de diferentes tamanhos, em diferentes orientações, com iluminação diferente, e assim por diante. Assim, neste capítulo vamos introduzir técnicas importantes para tirar o máximo partido do teu conjunto de dados, especialmente quando estás a treinar a partir do zero, ou a utilizar a aprendizagem por transferência para treinar um ...
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.