Saved in:
Bibliographic Details
Main Authors: Watson, Matthew, Sreepathihalli, Divyashree Shivakumar, Chollet, Francois, Gorner, Martin, Sodhia, Kiranbir, Sampath, Ramesh, Patel, Tirth, Jin, Haifeng, Kovelamudi, Neel, Rasskin, Gabriel, Saadat, Samaneh, Wood, Luke, Qian, Chen, Bischof, Jonathan, Stenbit, Ian, Sharma, Abheesht, Mishra, Anshuman
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.20247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916274274041856
author Watson, Matthew
Sreepathihalli, Divyashree Shivakumar
Chollet, Francois
Gorner, Martin
Sodhia, Kiranbir
Sampath, Ramesh
Patel, Tirth
Jin, Haifeng
Kovelamudi, Neel
Rasskin, Gabriel
Saadat, Samaneh
Wood, Luke
Qian, Chen
Bischof, Jonathan
Stenbit, Ian
Sharma, Abheesht
Mishra, Anshuman
author_facet Watson, Matthew
Sreepathihalli, Divyashree Shivakumar
Chollet, Francois
Gorner, Martin
Sodhia, Kiranbir
Sampath, Ramesh
Patel, Tirth
Jin, Haifeng
Kovelamudi, Neel
Rasskin, Gabriel
Saadat, Samaneh
Wood, Luke
Qian, Chen
Bischof, Jonathan
Stenbit, Ian
Sharma, Abheesht
Mishra, Anshuman
contents We present the Keras domain packages KerasCV and KerasNLP, extensions of the Keras API for Computer Vision and Natural Language Processing workflows, capable of running on either JAX, TensorFlow, or PyTorch. These domain packages are designed to enable fast experimentation, with a focus on ease-of-use and performance. We adopt a modular, layered design: at the library's lowest level of abstraction, we provide building blocks for creating models and data preprocessing pipelines, and at the library's highest level of abstraction, we provide pretrained ``task" models for popular architectures such as Stable Diffusion, YOLOv8, GPT2, BERT, Mistral, CLIP, Gemma, T5, etc. Task models have built-in preprocessing, pretrained weights, and can be fine-tuned on raw inputs. To enable efficient training, we support XLA compilation for all models, and run all preprocessing via a compiled graph of TensorFlow operations using the tf.data API. The libraries are fully open-source (Apache 2.0 license) and available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20247
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KerasCV and KerasNLP: Vision and Language Power-Ups
Watson, Matthew
Sreepathihalli, Divyashree Shivakumar
Chollet, Francois
Gorner, Martin
Sodhia, Kiranbir
Sampath, Ramesh
Patel, Tirth
Jin, Haifeng
Kovelamudi, Neel
Rasskin, Gabriel
Saadat, Samaneh
Wood, Luke
Qian, Chen
Bischof, Jonathan
Stenbit, Ian
Sharma, Abheesht
Mishra, Anshuman
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Software Engineering
I.2.5; I.2.7; I.2.10
We present the Keras domain packages KerasCV and KerasNLP, extensions of the Keras API for Computer Vision and Natural Language Processing workflows, capable of running on either JAX, TensorFlow, or PyTorch. These domain packages are designed to enable fast experimentation, with a focus on ease-of-use and performance. We adopt a modular, layered design: at the library's lowest level of abstraction, we provide building blocks for creating models and data preprocessing pipelines, and at the library's highest level of abstraction, we provide pretrained ``task" models for popular architectures such as Stable Diffusion, YOLOv8, GPT2, BERT, Mistral, CLIP, Gemma, T5, etc. Task models have built-in preprocessing, pretrained weights, and can be fine-tuned on raw inputs. To enable efficient training, we support XLA compilation for all models, and run all preprocessing via a compiled graph of TensorFlow operations using the tf.data API. The libraries are fully open-source (Apache 2.0 license) and available on GitHub.
title KerasCV and KerasNLP: Vision and Language Power-Ups
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Software Engineering
I.2.5; I.2.7; I.2.10
url https://arxiv.org/abs/2405.20247