## EdgeLD
This is the source code for our paper: **EdgeLD: Locally Distributed Deep Learning Inference on Edge Device Clusters**. A brief introduction of this work is as follows:
> Deep Neural Networks (DNN) have been widely used in a large number of application scenarios. However, DNN models are generally both computation-intensive and memory-intensive, thus difficult to be deployed on resource-constrained edge devices. Most previous studies focus on local model compression or remote cloud offloading, but overlook the potential benefits brought by distributed DNN execution on multiple edge devices. In this paper, we propose EdgeLD, a new framework for locally distributed execution of DNN-based inference tasks on a cluster of edge devices. In EdgeLD, DNN models' time cost will be firstly profiled in terms of computing capability and network bandwidth. Guided by profiling, an efficient model partition scheme is designed in EdgeLD to balance the assigned workload and the inference runtime among different edge devices. We also propose to employ layer fusion to reduce communication overheads on exchanging intermediate data among devices. Experiment results show that our proposed partition scheme saves up to 15.82% of inference time with regard to the conventional solution. Besides, applying layer fusion can speedup the DNN inference by 1.11-1.13X. When combined, EdgeLD can accelerate the original inference time by 1.77-3.57X on a cluster of 2-4 edge devices.
This work has been published by IEEE HPCC 2020 [link](https://ieeexplore.ieee.org/document/9408006). The technique report can be downloaded from [here](https://github.com/fangvv/EdgeLD/raw/master/TR-EdgeLD.pdf).
## Required software
PyTorch
## Citation
@inproceedings{xue2020edgeld,
title={Edgeld: Locally distributed deep learning inference on edge device clusters},
author={Xue, Feng and Fang, Weiwei and Xu, Wenyuan and Wang, Qi and Ma, Xiaodong and Ding, Yi},
booktitle={2020 IEEE 22nd International Conference on High Performance Computing and Communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)},
pages={613--619},
year={2020},
organization={IEEE}
}
## Contact
Feng Xue (17120431@bjtu.edu.cn)
> Please note that the open source code in this repository was mainly completed by the graduate student author during his master's degree study. Since the author did not continue to engage in scientific research work after graduation, it is difficult to continue to maintain and update these codes. We sincerely apologize that these codes are for reference only.
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
Locally Distributed Deep Learning Inference on Edge Device Clusters - - 不懂运行,下载完可以私聊问,可远程教学 该资源内项目源码是个人的毕设,代码都测试ok,都是运行成功后才上传资源,答辩评审平均分达到96分,放心下载使用! <项目介绍> 1、该资源内项目代码都经过测试运行成功,功能ok的情况下才上传的,请放心下载使用! 2、本项目适合计算机相关专业(如计科、人工智能、通信工程、自动化、电子信息等)的在校学生、老师或者企业员工下载学习,也适合小白学习进阶,当然也可作为毕设项目、课程设计、作业、项目初期立项演示等。 3、如果基础还行,也可在此代码基础上进行修改,以实现其他功能,也可用于毕设、课设、作业等。 下载后请首先打开README.md文件(如有),仅供学习参考, 切勿用于商业用途。 --------
资源推荐
资源详情
资源评论
收起资源包目录
EdgeLD-master.zip (48个子文件)
EdgeLD-master
项目代码
说明.txt 163B
EdgeMI
node_test
datanode_4.py 13KB
num_set_up.py 499B
datanode_0.py 13KB
datanode_5.py 13KB
namenode_0.py 20KB
network_op.py 19KB
server.py 1KB
datanode_3.py 13KB
datanode_1.py 13KB
client.py 840B
__pycache__
num_set_up.cpython-36.pyc 1KB
network_op.cpython-36.pyc 8KB
datanode_2.py 13KB
network_and_computing
plot1.py 16KB
divid_test.py 6KB
measure_computing.py 8KB
network_and_computing_record.py 2KB
__pycache__
network_and_computing_record.cpython-36.pyc 2KB
image
data
cat.jpg 5KB
getImageData.py 1KB
cat1.jpg 12KB
cat.jpg 5KB
VGG
mydefine_VGG13.py 9KB
mydefine_VGG13_K.py 9KB
tensor_op.py 13KB
mydefine_VGG16_K.py 18KB
vgg.py 8KB
__pycache__
tensor_op.cpython-36.pyc 6KB
mydefine_VGG16.cpython-36.pyc 4KB
mydefine_VGG19.cpython-36.pyc 4KB
mydefine_VGG13.cpython-36.pyc 4KB
vgg.cpython-36.pyc 6KB
easy_test.py 7KB
test.py 8KB
mydefine_VGG19.py 9KB
mydefine_VGG16.py 18KB
inference_stage
muilt_inference.py 57B
.idea
.name 4B
workspace.xml 47KB
misc.xml 295B
modules.xml 276B
Node.iml 438B
test.py 164B
实验介绍
软件、硬件介绍.docx 13KB
实验参数设置.docx 12KB
TR-EdgeLD.pdf 422KB
README.md 3KB
共 48 条
- 1
资源评论
机智的程序员zero
- 粉丝: 1533
- 资源: 4128
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功