学习pytorch--》手势识别--》机器人学习

FOA，我这个是个人笔记，很乱，别看

Pytorch

Linux 和 Windows 查看 CUDA 和 cuDNN 版本
https://www.cnblogs.com/wuliytTaotao/p/11453265.html#%E6%9F%A5%E7%9C%8B-cuda-%E7%89%88%E6%9C%AC

Ubuntu16.04安装pytorch（pip）
https://blog.csdn.net/u013832707/article/details/80076917
官方：
https://pytorch.org/get-started/previous-versions/

他妈的，可能是双屏幕的原因 一直发现pip install torchvision0.2.1 每次都是卡死。
1.换chorme
2.关闭其他应用pip install torchvision0.2.1

–》

    0% |▎                               | 5.4MB 1.0MB/s eta 0:12    99% |████████████████████████████████| 753.4MB 6.6MB/s eta 0:00:01Exception:
Traceback (most recent call last):
  File "/usr/lib/python2.7/dist-packages/pip/basecommand.py", line 209, in main
    status = self.run(options, args)
  File "/usr/lib/python2.7/dist-packages/pip/commands/install.py", line 328, in run
    wb.build(autobuilding=True)
  File "/usr/lib/python2.7/dist-packages/pip/wheel.py", line 748, in build
    self.requirement_set.prepare_files(self.finder)
  File "/usr/lib/python2.7/dist-packages/pip/req/req_set.py", line 360, in prepare_files
    ignore_dependencies=self.ignore_dependencies))
  File "/usr/lib/python2.7/dist-packages/pip/req/req_set.py", line 577, in _prepare_file
    session=self.session, hashes=hashes)
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 810, in unpack_url
    hashes=hashes
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 649, in unpack_http_url
    hashes)
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 871, in _download_http_url
    _download_url(resp, link, content_file, hashes)
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 595, in _download_url
    hashes.check_against_chunks(downloaded_chunks)
  File "/usr/lib/python2.7/dist-packages/pip/utils/hashes.py", line 46, in check_against_chunks
    for chunk in chunks:
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 563, in written_chunks
    for chunk in chunks:
  File "/usr/lib/python2.7/dist-packages/pip/utils/ui.py", line 139, in iter
    for x in it:
  File "/usr/lib/python2.7/dist-packages/pip/download.py", line 552, in resp_read
    decode_content=False):
  File "/usr/share/python-wheels/urllib3-1.13.1-py2.py3-none-any.whl/urllib3/response.py", line 344, in stream
    data = self.read(amt=amt, decode_content=decode_content)
  File "/usr/share/python-wheels/urllib3-1.13.1-py2.py3-none-any.whl/urllib3/response.py", line 301, in read
    data = self._fp.read(amt)
  File "/usr/share/python-wheels/CacheControl-0.11.5-py2.py3-none-any.whl/cachecontrol/filewrapper.py", line 54, in read
    self.__callback(self.__buf.getvalue())
  File "/usr/share/python-wheels/CacheControl-0.11.5-py2.py3-none-any.whl/cachecontrol/controller.py", line 224, in cache_response
    self.serializer.dumps(request, response, body=body),
  File "/usr/share/python-wheels/CacheControl-0.11.5-py2.py3-none-any.whl/cachecontrol/serialize.py", line 81, in dumps
    ).encode("utf8"),
MemoryError
You are using pip version 8.1.1, however version 20.1.1 is available.
You should consider upgrading via the 'pip install --upgrade pip' command.

本来就是自己的下载方式不对吧。不是屏幕或者浏览器的问题。

---

还是下载anaconda 然后学习pytorch吧/

---

教程

PyTorch 60 分钟入门视频教程- Jupyter 下载
PyTorch官方教程中文版
楼上 对应快速的镜像
PyTorch 1.0 中文文档 & 教程
知识图谱推荐系统
http://pytorchchina.com/

anaconda2 pytorch cuda ubuntu16

---

http://pytorch.panchuang.net/FirstSection/InstallIutorial/ 官方py3.5–》anaconda3.5

https://blog.csdn.net/u012180351/article/details/70304919?locationNum=3&fps=1
conda install pytorch1.1.0 torchvision0.3.0 cudatoolkit=9.0 -c pytorch

pip install torch1.1.0 torchvision0.3.0
ok

---

教程看到了https://pytorch.apachecn.org/docs/1.0/data_loading_tutorial.html 这里，搁置一下，
直接开始手势识别demo吧–》06/23/10：27

主要参考：https://blog.csdn.net/weixin_44678052/article/details/102513621
次要参考：https://blog.csdn.net/york1996/article/details/82466712

---

avoidance learn

ros gazebo 创客智造
https://www.ncnynl.com/archives/201707/1786.html

https://emanual.robotis.com/docs/en/platform/turtlebot3/example/
https://emanual.robotis.com/docs/en/platform/turtlebot3/overview/
https://emanual.robotis.com/docs/en/platform/turtlebot3/overview/
真就弄一下v2 - - - ray的我要开始去网上冲浪了，不然都是国内的垃圾页面

https://www.ncnynl.com/archives/201707/1817.html
有了gezebo之后进行激光或者画面 以及cmd的同时间戳data收集
然后训练，之后部署
主要关系两个一个是雷达的msg到python这边数据变换
或者图像msg到python的数据变化
当然如果是RGBD进行训练肯定也ok
不过还需要看

ubuntu16.04+kinetic 环境下进行turtlebot2仿真+gazebo正确显示
在sudo apt-get install ros-kinetic-turtlebot ros-kinetic-turtlebot-apps ros-kinetic-turtlebot-interactions ros-kinetic-kobuki-ftdi ros-kinetic-ar-track-alvar-msgs ros-kinetic-turtlebot-simulator
terminal提示

191214-001034+0000) ...
Setting up ros-kinetic-kobuki-capabilities (0.7.6-0xenial-20200109-042340+0000) ...
Setting up ros-kinetic-kobuki-dashboard (0.5.7-0xenial-20200229-053706+0000) ...
Setting up ros-kinetic-kobuki-description (0.7.6-0xenial-20191214-080002+0000) ...
Setting up ros-kinetic-kobuki-gazebo-plugins (0.5.7-0xenial-20200508-190557+0000) ...
Setting up ros-kinetic-laptop-battery-monitor (0.2.0-0xenial-20191214-104245+0000) ...
Setting up ros-kinetic-librealsense (1.12.1-0xenial-20191214-013909+0000) ...

Creating symlink /var/lib/dkms/uvcvideo/1.1.1-3-realsense/source ->
                 /usr/src/uvcvideo-1.1.1-3-realsense

DKMS: add completed.

Kernel preparation unnecessary for this kernel.  Skipping...

Running the pre_build script:

dkms: Pre-build script started...

Downloading kernel sources...
Reading package lists...
Picking 'linux-signed-hwe' as source package instead of 'linux-image-4.15.0-45-generic'
Need to get 13.9 kB of source archives.
Get:1 http://mirrors.ustc.edu.cn/ubuntu xenial-proposed/main linux-signed-hwe 4.15.0-107.108~16.04.1 (dsc) [2,158 B]
Get:2 http://mirrors.ustc.edu.cn/ubuntu xenial-proposed/main linux-signed-hwe 4.15.0-107.108~16.04.1 (tar) [11.7 kB]
gpgv: Signature made 2020年06月12日 星期五 10时47分10秒 CST using RSA key ID 238F6A10
gpgv: Can't check signature: public key not found
dpkg-source: warning: failed to verify signature on ./linux-signed-hwe_4.15.0-107.108~16.04.1.dsc
dpkg-source: info: extracting linux-signed-hwe in linux-signed-hwe-4.15.0
dpkg-source: info: unpacking linux-signed-hwe_4.15.0-107.108~16.04.1.tar.xz
W: Can't drop privileges for downloading as file 'linux-signed-hwe_4.15.0-107.108~16.04.1.dsc' couldn't be accessed by user '_apt'. - pkgAcquire::Run (13: Permission denied)
Fetched 13.9 kB in 0s (43.8 kB/s)
grep: drivers/media/usb/uvc/uvc_driver.c: No such file or directory
INFO: No Intel RealSense(TM) cameras are currently supported.
Patching uvcvideo sources...
can't find file to patch at input line 5
Perhaps you used the wrong -p or --strip option?
The text leading up to this was:
--------------------------
|diff --git a/drivers/media/usb/uvc/Makefile b/drivers/media/usb/uvc/Makefile
|index c26d12fdb8f4..d86cf22155d1 100644
|--- a/drivers/media/usb/uvc/Makefile
|+++ b/drivers/media/usb/uvc/Makefile
--------------------------
File to patch: 
Skip this patch? [y] y
Skipping patch.
1 out of 1 hunk ignored
can't find file to patch at input line 14
Perhaps you used the wrong -p or --strip option?
The text leading up to this was:
--------------------------
|diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
|index d11fd6ac2df0..914164137a13 100644
|--- a/drivers/media/usb/uvc/uvc_driver.c
|+++ b/drivers/media/usb/uvc/uvc_driver.c
--------------------------
File to patch: 
Skip this patch? [y] y
Skipping patch.
1 out of 1 hunk ignored
can't find file to patch at input line 100
Perhaps you used the wrong -p or --strip option?
The text leading up to this was:
--------------------------
|diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
|index f0f2391e1b43..532ca19675a5 100644
|--- a/drivers/media/usb/uvc/uvcvideo.h
|+++ b/drivers/media/usb/uvc/uvcvideo.h
--------------------------
File to patch: 
Skip this patch? [y] y
Skipping patch.
1 out of 1 hunk ignored
can't find file to patch at input line 163
Perhaps you used the wrong -p or --strip option?
The text leading up to this was:
--------------------------
|diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
|index a0e87d16b726..e6c1ec69cba4 100644
|--- a/include/uapi/linux/videodev2.h
|+++ b/include/uapi/linux/videodev2.h
--------------------------
File to patch:  
Skip this patch? [y] y
Skipping patch.

没在意就直接y过去了
参考到“然后再catkin_make，显示成功就没问题啦。”
catkin_make没ok，准备ok之后执行：
roslaunch turtlebot_gazebo turtlebot_world.launch

就。。。运行成功了，之后再说吧turtlebot3的吧。

Turtlebot3-burger入门教程-PC安装
echo “source ~/catkin_ws/devel/setup.bash” >> ~/.bashrc
Turtlebot3与仿真-仿真环境搭建(kinetic版)
运行到$ export TURTLEBOT3_MODEL=burger

1.现在需要解决catkin_make不过的问题–》已经解决：https://blog.csdn.net/kuizhao8951/article/details/106929834
2.现在需要去论文里面下载数据集(ok 和查看libcnn的源码(大可不必 之后吧–》OK
3.我的小楼梯要找一下V2Ray的工具–》再说

---

我之前有常用的node的一个readme
现在不知道去哪了，等等去windows下看一下（再说）

---

现在反正有图像和cmd控制（joy）就差不多了。
现在是去用训练集训练一下。

---

如何把图像输入网络

https://blog.csdn.net/qq_39904393/article/details/102670416
https://blog.csdn.net/gbz3300255/article/details/105807220/
https://www.jianshu.com/p/eb5e0a22ed7a
https://www.cnblogs.com/ocean1100/p/9494640.html
一直找没有找到到底怎么样用自己的数据训练，上面这四个建议不看

---

https://blog.csdn.net/sinat_42239797/article/details/90641659#commentBox

---

对上面的内容已经不想看也不想有任何解释了，详情看我的github：RobotLearning