SCENIC: A JAX Library for Computer Vision Research and Beyond
SCENIC: A JAX Library for Computer Vision Research and Beyond
复制标题
DOI：
10.1109/cvpr52688.2022.02070
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Mostafa Dehghani;A. Gritsenko;Anurag Arnab;Matthias Minderer;Yi Tay
中科院分区：
文献类型：
--
作者：
Mostafa Dehghani;A. Gritsenko;Anurag Arnab;Matthias Minderer;Yi Tay
Scenic是一个开源11 https：github.com/google-research/scenic JAX库，专注于基于transformer的模型，用于计算机视觉研究及其他领域。该工具包的目标是促进新体系结构和模型的快速实验、原型设计和研究。Scenic支持多种任务（例如，分类、分割、检测），并有助于处理多模态问题，沿着GPU/TPU支持大规模、多主机和多设备训练。Scenic还提供最先进的研究模型的优化实施，涵盖广泛的模式。Scenic已成功用于许多项目和发表的论文，并继续作为快速原型设计和发表新研究想法的首选库。
Scenic is an open-source11https://github.com/google-research/scenic JAX library with a focus on transformer-based models for computer vision research and beyond. The goal of this toolkit is to facilitate rapid experimentation, prototyping, and research of new architectures and models. Scenic supports a diverse range of tasks (e.g., classification, segmentation, detection) and facilitates working on multi-modal problems, along with GPU/TPU support for large-scale, multi-host and multi-device training. Scenic also offers optimized implementations of state-of-the-art research models spanning a wide range of modalities. Scenic has been successfully used for numerous projects and published papers and continues serving as the library of choice for rapid prototyping and publication of new research ideas.