nanmi

ROS系统安装

安装依赖

$ sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list'
$ sudo sh -c 'echo "deb http://mirrors.ustc.edu.cn/ros/ubuntu/ $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list'
$ sudo apt-key adv --keyserver hkp://ha.pool.sks-keyservers.net:80 --recv-key 0xB01FA116
$ sudo apt-get update
$ sudo apt-get install ros-kinetic-desktop-full

apt-get install libomp-dev

//omp.cc
#include <iostream>
#include <omp.h>
int main()
{

The Most Powerful NLP-Weapon Arsenal

NLP民工的乐园: 几乎最全的中文NLP资源库

词库
工具包
学习资料

在入门到熟悉NLP的过程中，用到了很多github上的包，遂整理了一下，分享在这里。

很多包非常有趣，值得收藏，满足大家的收集癖！

The project will be updated continuously ......

Pull requests are welcome!

Deep Learning Model Convertors

Note: This is not one convertor for all frameworks, but a collection of different converters. Because github is an open source platform, I hope we can help each other here, gather everyone's strength.

Because of these different frameworks, the awesome convertors of deep learning models for different frameworks occur. It should be noted that I did not test all the converters, so I could not guarantee that each was available. But I also hope this convertor collection may help you!

github: https://github.com/nanmi/cortex/edit/master/README.md

Deploy machine learning models in production

Cortex is an open source platform for deploying machine learning models—trained with nearly any framework—as production web services.

install • tutorial • docs • examples • we're hiring • email us • chat with us

NV显卡驱动安装

卸载驱动

cd /usr/bin
./nvidia-uninstall
sudo apt-get --purge remove "*nvidia*"
sudo apt autoremove

# To remove CUDA Toolkit:

NCNN的计算图和参数bin结构

参数和模型文件结构

网络参数

例

7767517
3 3
Input         input    0 1 data 0=4 1=4 2=1

安装Vulkan SDK

Download VulkanSDK

web: https://vulkan.lunarg.com/sdk/home#linux

move vulkan to spefic path

mv 1.1.130.0 vulkan-1.1.130.0
mv vulkan-1.1.130.0  /usr/local/

Conv和BN融合Pytorch代码

reference links: https://learnml.today/speeding-up-model-with-fusing-batch-normalization-and-convolution-3

import torch
    import torchvision
    
    def fuse(conv, bn):

	//CUDA C++
	//1D grid of 1D blocks
	__device__ int getGlobalIdx_1D_1D()
	{
	return blockIdx.x*blockDim.x + threadIdx.x;
	}

	//1D grid of 2D blocks
	__device__ int getGlobalIdx_1D_2D()
	{