{%hackmd SybccZ6XD %}

# Jetson nano setup
- Acount and password
- Email
[e-mail]
Q——y1——3!
- System
1.user 123

# SDKmanger 安裝（ubuntu ver18.04 or ver20.04 required）
https://docs.nvidia.nvidiajetson/jetpack/install-jetpack/index.html
參考這個：https://docs.nvidia.com/sdk-manager/install-with-sdkm-jetson/index.html


> 建立一個Ubuntu系統（18.04）—>**HOST**
> 從系統再拉usb到jetson透過SDKmanager來安裝
> **Notes :
1.Burn in時候jetson必須切換（microUSB 旁邊的switch）
2.Burn in完後jetson必須切換回來才可以正常開關機**

# M.2 Format
https://www.forecr.io/blogs/bsp-development/change-root-file-system-to-m-2-ssd-directly
因為系統讀不到所以format為ext4
inux格式化指令：
> gnome-disks

# 參考資料(helloAI)：
https://github.com/dusty-nv/jetson-inference#system-setup

# Remote access

Step1 : Jetson nano system code required:
> sudo apt-get update
> sudo apt-get install nano
> sudo apt-get install xrdp
> sudo apt-get install xfce4
> echo xfce4-session > ~/.xsession

Step2 :
> sudo nano /etc/xrdp/startwm.sh
> 加入“startxfce4”在最後一行 --> Ctrl-X , Y , Enter (儲存離開)
> sudo service xrdp restart

Step3 : 確認Nano IP 以及 連線
> IP(nano): 140.118.115.36
> Username: user
> Password: 123


# System info

>sudo pip3 install -U jetson-stats
>jtop

https://github.com/rbonghi/jetson_stats
風扇手動全轉
>sudo sh -c 'echo 255 > /sys/devices/pwm-fan/target_pwm'

# Camera check
IPCam：

video-viewer rtsp://admin:123@140.118.115.65:554

USBCam

video-viewer v4l2:///dev/video0 

# Testing and problems
1A. Picture HelloAI現有的 要去./jetson-inference/....（會有個執行檔）

【C++】./imagenet --network=resnet-18 images/jellyfish.jpg images/test/output_jellyfish.jpg

1B. Picture (自己創.cpp)

> 參考：https://github.com/dusty-nv/jetson-inference/blob/master/docs/imagenet-example-2.md
> PASS FILE: https://drive.google.com/drive/folders/1Ysa01tHuDvW6usEV5yunuRpEnIpeKq_E?usp=share_link

my-regconition.cpp

#include <jetson-inference/imageNet.h>
#include <jetson-utils/loadImage.h>

int main( int argc, char** argv )
{
	// a command line argument containing the image filename is expected,
	// so make sure we have at least 2 args (the first arg is the program)
	if( argc < 2 )
	{
		printf("my-recognition:  expected image filename as argument\n");
		printf("example usage:   ./my-recognition my_image.jpg\n");
		return 0;
	}

	// retrieve the image filename from the array of command line args
	const char* imgFilename = argv[1];

	// these variables will store the image data pointer and dimensions
	uchar3* imgPtr = NULL;   // shared CPU/GPU pointer to image
	int imgWidth   = 0;      // width of the image (in pixels)
	int imgHeight  = 0;      // height of the image (in pixels)
		
	// load the image from disk as uchar3 RGB (24 bits per pixel)
	if( !loadImage(imgFilename, &imgPtr, &imgWidth, &imgHeight) )
	{
		printf("failed to load image '%s'\n", imgFilename);
		return 0;
	}

	// load the GoogleNet image recognition network with TensorRT
	// you can use imageNet::RESNET_18 to load ResNet-18 model instead
	imageNet* net = imageNet::Create(argc, argv);

	// check to make sure that the network model loaded properly
	if( !net )
	{
		printf("failed to load image recognition network\n");
		return 0;
	}

	// this variable will store the confidence of the classification (between 0 and 1)
	float confidence = 0.0;

	// classify the image, return the object class index (or -1 on error)
	const int classIndex = net->Classify(imgPtr, imgWidth, imgHeight, &confidence);

	// make sure a valid classification result was returned	
	if( classIndex >= 0 )
	{
		// retrieve the name/description of the object class index
		const char* classDescription = net->GetClassDesc(classIndex);

		// print out the classification results
		printf("image is recognized as '%s' (class #%i) with %f%% confidence\n", 
			  classDescription, classIndex, confidence * 100.0f);
	}
	else
	{
		// if Classify() returned < 0, an error occurred
		printf("failed to classify image\n");
	}
	
	// free the network's resources before shutting down
	delete net;
	return 0;
}

CMakeLists.txt

# require CMake 2.8 or greater
cmake_minimum_required(VERSION 2.8)

# declare my-recognition project
project(my-recognition)

# import jetson-inference and jetson-utils packages.
# note that if you didn't do "sudo make install"
# while building jetson-inference, this will error.
find_package(jetson-utils)
find_package(jetson-inference)

# CUDA is required
find_package(CUDA)

# add directory for libnvbuf-utils to program
link_directories(/usr/lib/aarch64-linux-gnu/tegra)

# compile the my-recognition program
cuda_add_executable(my-recognition my-recognition.cpp)

# link my-recognition to jetson-inference library
target_link_libraries(my-recognition jetson-inference)

結果：

./my-recognition my_image.jpg


- Live Demo
參考：https://github.com/dusty-nv/jetson-inference/blob/master/docs/imagenet-camera-2.md
2A. Camera detect （HelloAI）（usb）

【C++】./imagenet /dev/video0 

結果

2B. Camera detection （自己的）

- Load ONNX (Check later)
https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-ssd.md#processing-images-with-tensorrt

> detectnet --model=models/fruit/ssd-mobilenet.onnx --labels=models/fruit/labels.txt \
--input-blob=input_0 --output-cvg=scores --output-bbox=boxes \
csi://0

# TO DO
1.Running live camera with detection (pretrained model)

2.Image and video test with our simple model (.pth > .onnx)
>how to load model in C++
>(https://forums.developer.nvidia.com/t/how-to-load-object-detection-custom-data-trained-model-in-c/226849)
>Pytorch to onnx
>https://d246810g2000.medium.com/nvidia-jetson-nano-for-jetpack-4-4-03-%E8%BD%89%E6%8F%9B%E5%90%84%E7%A8%AE%E6%A8%A1%E5%9E%8B%E6%A1%86%E6%9E%B6%E5%88%B0-onnx-%E6%A8%A1%E5%9E%8B-17adcece9c34
>
3.Running live camera with our model

4.library : https://rawgit.com/dusty-nv/jetson-inference/master/docs/html/files.html

# Notes
pytorch-cpp:
https://github.com/prabhuomkar/pytorch-cpp
https://jumpml.com/howto-pytorch-c++/output/