Learning to Track at 100 FPS with Deep Regression Networks 论文理解及应用笔记(二)

GOTURN算法实践及性能分析云笔记
 
算法实现:个人根据论文及github提示构建算法平台
测试环境为Caffe+OpenCV+Linux+GOTURN源码
硬件平台:CRSN本科生实验室服务器-- 128G运行内存,3.2GCPU频率、英伟达1080p显卡、酷睿I7、8核处理器
测试数据集:VOT2014公开数据集
 
一、环境搭建
1.OpenCV-2.4.9库安装
 
1.1 先从sourceforge上下载OpenCV的源码
 
 
1.2解压到任意目录
 
unzip opencv-2.4.9.zip
 
1.3进入源码目录,创建release目录
  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
As an AI language model, I can suggest the following steps to learn deep learning: 1. Learn the basics of machine learning: Before diving into deep learning, it is essential to understand the basics of machine learning, including supervised and unsupervised learning, regression, clustering, and classification. 2. Learn programming languages: To work with deep learning, one needs to have a strong foundation in programming languages such as Python and R, as most of the deep learning libraries are written in these languages. 3. Understand the mathematics behind deep learning: Deep learning involves a lot of math, including linear algebra, calculus, and probability. Understanding these concepts will help you better understand the algorithms used in deep learning. 4. Choose a deep learning framework: Popular deep learning frameworks include Tensorflow, Keras, PyTorch, and Caffe. Choose one and learn it. 5. Practice with datasets: Work with datasets to understand how deep learning works in practice. Kaggle is a great platform to get started with real-world datasets. 6. Read research papers: Read research papers to stay up-to-date with the latest advancements in deep learning. 7. Join communities: Join online communities such as Reddit, Discord, or GitHub to connect with other deep learning enthusiasts and learn from them. 8. Build projects: Building projects is the best way to learn deep learning. Start with simple projects and gradually move on to more complex ones. Remember, deep learning is a vast field, and it takes time and effort to master it. Keep practicing, and you will get there.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值