fastai

E701495

Python library deep learning library open-source software

fastai is a high-level deep learning library built on top of PyTorch that simplifies training and deploying state-of-the-art machine learning models.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label	Occurrences
fastai canonical	1

Statements (47)

Predicate	Object
instanceOf	Python library ⓘ deep learning library ⓘ open-source software ⓘ
basedOn	PyTorch NERFINISHED ⓘ
developer	Jeremy Howard NERFINISHED ⓘ Sylvain Gugger NERFINISHED ⓘ fast.ai NERFINISHED ⓘ
documentation	https://docs.fast.ai ⓘ
feature	GPU acceleration via PyTorch ⓘ built-in data augmentation ⓘ callbacks system ⓘ data block API ⓘ high-level API over PyTorch ⓘ learning rate finder ⓘ metrics and logging utilities ⓘ mixed-precision training ⓘ one-cycle training policy ⓘ transfer learning utilities ⓘ
hasSubmodule	fastai.collab ⓘ fastai.tabular NERFINISHED ⓘ fastai.text NERFINISHED ⓘ fastai.vision NERFINISHED ⓘ
integratesWith	Jupyter Notebook NERFINISHED ⓘ PyTorch ecosystem NERFINISHED ⓘ
license	Apache License 2.0 ⓘ
maintainer	fast.ai organization NERFINISHED ⓘ
programmingLanguage	Python ⓘ
purpose	simplify deployment of deep learning models ⓘ simplify training of deep learning models ⓘ
relatedTo	Practical Deep Learning for Coders NERFINISHED ⓘ fastai course ⓘ
repository	https://github.com/fastai/fastai ⓘ
supportsModel	convolutional neural networks ⓘ matrix factorization models ⓘ recurrent neural networks ⓘ tabular neural networks ⓘ transformer models ⓘ
supportsPlatform	Linux ⓘ Windows ⓘ macOS ⓘ
supportsTask	collaborative filtering ⓘ computer vision ⓘ natural language processing ⓘ tabular data modeling ⓘ time series modeling ⓘ
usedFor	educational purposes in deep learning courses ⓘ rapid prototyping of deep learning models ⓘ

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Adam optimizer → implementedIn → fastai ⓘ