## TLEE
This is the source code for our paper: **TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices**. A brief introduction of this work is as follows:
> With the explosive growth in video streaming comes a rising demand for efficient and scalable video understanding. State-of-the-art video recognition approaches based on Convolutional Neural Network (CNN) have shown promising performance by adopting 2D or 3D CNN architectures. However, the large data volumes, high resource demands, and strict latency requirements have hindered the wide application of these solutions on resource-constrained Internet-of-Things (IoT) and edge devices. To address this issue, we propose a novel framework called TLEE that enables the input samples the abilities of both Temporal-wise and Layer-wise Early Exiting on 2D CNN backbones for efficient video recognition. TLEE consists of three types of modules: gating module, branch module, and feature reuse module. The gating module determines for an input video from which frame of this video to exit the per-frame computation, while the branch module determines for an input frame from which layer of the CNN backbone to exit the per-layer computation. Besides, based on the accumulated features of frame sequences from exit branches, the feature reuse module generates effective video representations to enable more efficient predictions. Extensive experiments on benchmark datasets demonstrate that the proposed TLEE can significantly outperform the state-of-the-art approaches in terms of computational cost and inference latency, while maintaining competitive recognition accuracy. In addition, we verify the superiority of TLEE on the typical edge device NVIDIA Jetson Nano.
> TLEE:用于边缘设备上高效视频识别的时间和层早期退出网络
This work will be published by IEEE IoTJ (IEEE Internet of Things Journal). Click [here](https://doi.org/10.1109/JIOT.2023.3293506) for our paper.
## Required software
PyTorch
## Citation
@ARTICLE{10176276,
author={Wang, Qingli and Fang, Weiwei and Xiong, Neal N.},
journal={IEEE Internet of Things Journal},
title={TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices},
year={2023},
volume={},
number={},
pages={1-1},
doi={10.1109/JIOT.2023.3293506}}
## Contact
Qingli Wang (20120418@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
Code for paper "TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices" - 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
TLEE-main.zip (78个子文件)
TLEE-main
read_config.py 78B
tools
random_exit.py 185B
lr_schedule.py 278B
FRM.py 1KB
__pycache__
lr_schedule.cpython-36.pyc 379B
MLPFRM.cpython-36.pyc 865B
random_exit.cpython-36.pyc 349B
FRM.cpython-36.pyc 2KB
cloud_start_basemodel.sh 317B
main.py 34KB
utils
utils.py 7KB
__init__.py 0B
compute_ap.py 1KB
metrics.py 6KB
misc.py 453B
__pycache__
misc.cpython-36.pyc 847B
__init__.cpython-36.pyc 137B
config.cpython-36.pyc 6KB
metrics.cpython-36.pyc 6KB
utils.cpython-36.pyc 6KB
config.py 8KB
cloud_ucf101_branch.sh 339B
dataset
__init__.py 0B
dataset.py 10KB
dataset.bk.py 7KB
transform.py 10KB
__pycache__
dataset.cpython-36.pyc 8KB
transform.cpython-36.pyc 11KB
__init__.cpython-36.pyc 139B
cloud_hmdb51_branch.sh 399B
cloud_ssv2_branch.sh 117B
time_test.py 5KB
env_config
fe.yaml 2KB
fe.txt 1KB
test.sh 89B
model
__init__.py 0B
branch.py 1KB
model_splits.py 4KB
branch_model.py 9KB
__pycache__
post_process.cpython-36.pyc 925B
model_splits.cpython-36.pyc 3KB
tse.cpython-36.pyc 10KB
branch.cpython-36.pyc 2KB
branch_model.cpython-36.pyc 6KB
__init__.cpython-36.pyc 137B
adaptive_models.cpython-36.pyc 10KB
tlee.py 14KB
cloud_test_branchmodel.sh 133B
cloud_time_test.sh 225B
__pycache__
read_config.cpython-36.pyc 235B
test.py 414B
README.md 3KB
log
__pycache__
_log.cpython-36.pyc 249B
_log.py 125B
arch
efficientnet.py 69B
mobilenetv2_tsm.py 5KB
mobilenetv2.py 66B
BN_Inception.py 46KB
VGG16.py 68B
__pycache__
mobilenetv2.cpython-36.pyc 205B
mobilenetv2_tsm.cpython-36.pyc 4KB
efficientnet.cpython-36.pyc 200B
VGG16.cpython-36.pyc 184B
config
cloud_hmdb51_vgg16_branch.yml 2KB
cloud_ucf101_mobilenetv2_branch.yml 2KB
cloud_ucf101_efficientnetb3_branch.yml 2KB
ucf101_train.yml 2KB
cloud_hmdb51_mobilenetv2_branch.yml 2KB
cloud_hmdb51_resnet50_branch.yml 2KB
cloud_ucf101_branch.yml 2KB
cloud_ucf101_vgg16_branch.yml 2KB
ucf101_branch.yml 2KB
ucf101.yml 1KB
cloud_hmdb51_efficientnetb3_branch.yml 2KB
cloud_ssv2_branch.yml 2KB
cloud_ucf101_resnet50_branch.yml 2KB
train_basemodel.py 6KB
cloud_test_tse.sh 132B
共 78 条
- 1
资源评论
机智的程序员zero
- 粉丝: 1822
- 资源: 4173
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
最新资源
- MI4407-VB一款SOP8封装P-Channel场效应MOS管
- java实验2.doc
- opencv-基于c++实现的opencv图像处理算法之区域生长分割算法.zip
- MI3475-VB一款SOT23封装P-Channel场效应MOS管
- Fortran语言教程&案例&相关项目资源
- Labview 互斥按钮
- java小说人物分析.doc
- opencv-基于c++实现的opencv图像处理算法之双线性插值算法.zip
- 《STM32单片机+DHT11温湿度+MQ甲醛浓度+BH1750光照强度+按键+OLED屏幕+蜂鸣器+继电器》源代码
- python爬虫基础知识原理及Scrapy框架以及scrapy-redis分布式策略入门知识.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
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