paper-with-me

홈 › Papers

CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way

2020-03-14 · Shaoshan Liu, Bin Ren, Xipeng Shen, Yanzhi Wang

Assuming hardware is the major constraint for enabling real-time mobile intelligence, the industry has mainly dedicated their efforts to developing specialized hardware accelerators for machine learning and inference. This article challenges the assumption. By drawing on a recent real-time AI optimization framework CoCoPIE, it maintains that with effective compression-compiler co-design, it is possible to enable real-time artificial intelligence on mainstream end devices without special hardware. CoCoPIE is a software framework that holds numerous records on mobile AI: the first framework that supports all main kinds of DNNs, from CNNs to RNNs, transformer, language models, and so on; the fastest DNN pruning and acceleration framework, up to 180X faster compared with current DNN pruning on other frameworks such as TensorFlow-Lite; making many representative AI applications able to run in real-time on off-the-shelf mobile devices that have been previously regarded possible only with special hardware support; making off-the-shelf mobile devices outperform a number of representative ASIC and FPGA solutions in terms of energy efficiency and/or performance.

📄 PDF Abstract BibTeX arXiv:2003.06700

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

A Compression-Compilation Framework for On-mobile Real-time BERT Applications

2021-05-30 · Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang 외

Transformer-based deep learning models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. In this paper, we propose a compression-compilation co-design framework that can guaran…

Question AnsweringText Generation

YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design

2020-09-12 · Yuxuan Cai, Hongjia Li, Geng Yuan, Wei Niu 외

The rapid development and wide utilization of object detection techniques have aroused attention on both accuracy and speed of object detectors. However, the current state-of-the-art object detection works are either acc…

Computational EfficiencyCPUGPUObject+3

Less is More: The Influence of Pruning on the Explainability of CNNs

2023-02-17 · Florian Merkle, David Weber, Pascal Schöttle, Stephan Schlögl 외

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challen…

Network Pruning

Towards Efficient Model Compression via Learned Global Ranking

2019-04-28 · CVPR 2020 6 · Ting-Wu Chin, Ruizhou Ding, Cha Zhang, Diana Marculescu

Pruning convolutional filters has demonstrated its effectiveness in compressing ConvNets. Prior art in filter pruning requires users to specify a target model complexity (e.g., model size or FLOP count) for the resulting…

Model Compression

SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization

2024-12-11 · Zhentao Tan, Ben Xue, Jian Jia, Junhao Wang 외

This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTokenizer), a compact yet effective discretization approach for vision data. Our goal is to boost token…

Image ReconstructionRepresentation LearningVideo GenerationVideo Reconstruction