在服务器的个人账户下上安装cuda

  1. cuda archive里找到对应的cuda版本的runfile文件,通过sh xxx.run来安装

  2. 安装的时候,需要去Options里更改toolkit和library的path,设置完后即可进行install

  3. install完了之后,需要去bashrc里添加以下内容:

1
2
export PATH="/xxx/cuda/bin:$PATH"
export LD_LIBRARY_PATH="/xxx/cuda/lib64:$LD_LIBRARY_PATH"
  1. 然后source一下bashrc,再nvcc -V,如果显示版本号,则说明安装成功

  2. 遇到需要本地cuda的时候,可以

export CUDA_HOME=="/xxx/cuda/"

在服务器个人账户下安装GCC

  1. 去清华源下载需要的gcc的版本,网址在这里: https://mirrors.tuna.tsinghua.edu.cn/gnu/gcc/

  2. 解压完后,进入文件夹gcc-x.x.x,执行命令:./contrib/download_prerequisites

  3. make build,新建一个文件夹,cd build../configure --prefix=/home/xxx/gcc-x.x.0 --enable-shared --enable-threads=posix --enable-languages=c,c++,fortran --disable-multilib

  4. make -j10 && make install

  5. 打开 .bashrc,添加一下内容:

1
2
3
export PATH=/path/to/install/gcc-5.4/bin:$PATH
export LD_LIBRARY_PATH=/path/to/install/gcc-5.4/lib/:/path/to/install/gcc-5.4/lib64:$LD_LIBRARY_PATH`

  1. source一下bashrc,然后gcc --version,如果显示版本号,则说明安装成功
    阅读全文 »

Matplotlib 绘图

  1. 3D plot时候的需要注意的地方

https://www.codenong.com/48442713/

https://www.coder.work/article/2032713#google_vignette

绘图软件推荐

  • Visio
  • PPT
  • 飞书
  • MATLAB

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking[1]

作者是来自CMU、上海AI Lab和英伟达的Junkun Cao, Jiangmiao Pang, Xinshuo Weng, Rawal Khirodkar, Kris Kitani. 论文引用[1]:Cao, Jinkun et al. “Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking.” 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022): 9686-9696.

Time

  • 2023.Feb

Key Words

  • limitations of SORT: sensitivity to the noise of state estimations, error accumulation over time and being estimation-centric
  • Observation-Centric SORT, Simple,Online, and Real-Time
  • occlusion and non-linear object motion
阅读全文 »

MixFormer: End-to-End Tracking with Iterative Mixed Attention[1]

作者是来自南大的Yutao Cui, Cheng Jiang, Limin Wang, Gangshan Wu. 论文引用[1]:Cui, Yutao et al. “MixFormer: End-to-End Tracking with Iterative Mixed Attention.” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022): 13598-13608.

Time

  • 2022.Mar

Key Words

  • compact tracking framework
  • unify the feature extraction and target integration solely with a transformer-based architecture

VOT,MOT,SOT的区别

  1. VOT是标首帧,MOT是多目标追踪,SOT是单目标追踪。

动机

  1. Tracking经常用多阶段的pipeline:feature extraction,target information integration,bounding box estimation。为了简化这个pipeline,作者提出了一个紧凑的tracking框架,名为MixFormer。

  2. target information integration解释: fuse the target and search region information

阅读全文 »

在Ubuntu 20.04里安装 Nvidia RTX 3060显卡的驱动

  1. 之前照着网上的教程弄过一次,记得是通过命令行来弄的,结果搞得黑屏,好不容易解决了黑屏的问题,进入桌面之后,显示不了Wifi和蓝牙,好像缺了很多东西,搞得很狂躁。这两天跑Tracking,大部分是Ubuntu环境下的,就趁这次机会重装一下系统,然后找个新的教程

  2. 找到了两个方式:

    • 通过 Ubuntu 自带的Software & updates里头的additional drivers里,能看到有 Nvidia的显卡驱动,勾一个合适的就行,很简单。。全程没有什么bug。。害得我上次弄了好久。
    • 去nvidia官网上下载驱动,名称一般是 Nvidia-Linux-xxx.run,运行的时候需要先禁用掉 nouveau,在哪个文件里加上: blacklist nouveau, options nouveau modeset=0,然后重启,看看lsmod一下,看看nouveau有没有被禁用掉。然后运行 .run文件,在运行.run文件的时候:提示可以用Ubuntu里 additional drivers来安装。

Masked Autoencoders with Saptial-Attention Dropout for Tracking Tasks[1]

作者是来自CityU、IDEA、Tecent AI Lab、CUHK(SZ)的 Qiangqiang Wu、Tianyu Yang、Ziquan Liu、Baoyuan Wu、Ying Shan、Antoni B.Chan. 论文引用[1]:Wu, Qiangqiang et al. “DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks.” 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023): 14561-14571.

Time

  • 2023.Apr

Key Words

  • masked autoencoder
  • temporal matching-based
  • spatial-attention dropout

动机

  1. 将MAE应用到下游任务如: visual object tracking(VOT) and video object segmentation(VOS). 简单的扩展MAE是mask out frame patches in videos and reconstruct the frame pixels.然而作者发现这个会严重依赖于spatial cues, 当进行frame reconstruction的时候忽略temporal relations, 这个导致sub-optimal temporal matching representations for VOT and VOS.
阅读全文 »

Fully Convolution Networks for Semantic Segmentation[1]

作者是来自UC Berkeley的Jonathan Long, Evan Shelhamer, Trevor Darrell. 论文引用[1]:Shelhamer, Evan et al. “Fully convolutional networks for semantic segmentation.” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014): 3431-3440.

Time

  • 2014.Nov

Key Words

  • fully convolutional network

动机

  1. 目的是建一个fully convolution network, 接收任意尺寸的输入,产生相应尺寸的输出 with efficient inference and learning.
阅读全文 »
0%