paper-with-me

홈 › Papers

PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural Networks

2018-10-20 · NIPS Workshop CDNNRIA 2018 · Jiaxiang Wu, Yao Zhang, Haoli Bai, Huasong Zhong, Jinlong Hou, Wei Liu, Wenbing Huang, Junzhou Huang

Deep neural networks are widely used in various domains, but the prohibitive computational complexity prevents their deployment on mobile devices. Numerous model compression algorithms have been proposed, however, it is often difficult and time-consuming to choose proper hyper-parameters to obtain an efficient compressed model. In this paper, we propose an automated framework for model compression and acceleration, namely PocketFlow. This is an easy-to-use toolkit that integrates a series of model compression algorithms and embeds a hyper-parameter optimization module to automatically search for the optimal combination of hyper-parameters. Furthermore, the compressed model can be converted into the TensorFlow Lite format and easily deployed on mobile devices to speed-up the inference. PocketFlow is now open-source and publicly available at https://github.com/Tencent/PocketFlow.

📄 PDF Abstract BibTeX

Code (1)

Tencent/PocketFlow 공식 구현 tf

Tasks

Model Compression

Similar Papers 제목 키워드 기반

Generalized Protein Pocket Generation with Prior-Informed Flow Matching

2024-09-29 · Zaixi Zhang, Marinka Zitnik, Qi Liu

Designing ligand-binding proteins, such as enzymes and biosensors, is essential in bioengineering and protein biology. One critical step in this process involves designing protein pockets, the protein interface binding w…

valid

Accelerating Neural ODEs Using Model Order Reduction

2021-05-28 · Mikko Lehtimäki, Lassi Paunonen, Marja-Leena Linne

Embedding nonlinear dynamical systems into artificial neural networks is a powerful new formalism for machine learning. By parameterizing ordinary differential equations (ODEs) as neural network layers, these Neural ODEs…

modelTime SeriesTime Series AnalysisTime Series Classification

Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning

2019-03-25 · Chaohui Yu, Jindong Wang, Yiqiang Chen, Zijing Wu

Deep unsupervised domain adaptation (UDA) has recently received increasing attention from researchers. However, existing methods are computationally intensive due to the computation cost of Convolutional Neural Networks …

Domain AdaptationTransfer LearningUnsupervised Domain Adaptation

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

2026-05-11 · Ikbel Ghrab, Mohamed Dhieb, Ismail Khenissi, Ines Abdeljaoued-Tej arxiv

High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainability are essential. We presented an AI powered framework that automates…

Code Documentation GenerationPrompt Engineering

VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning

2024-06-07 · Oshin Dutta, Ritvik Gupta, Sumeet Agarwal

In recent years, there has been a growing emphasis on compressing large pre-trained transformer models for resource-constrained devices. However, traditional pruning methods often leave the embedding layer untouched, lea…