Celebrating our 10th year on RU-vid! JetsonHacks provides information for developing on NVIDIA Jetson Development Kits. Jetsons are powerful single board computers built for powering AI projects where low power usage combined with GPU support are important.
As an Amazon Associate I earn from qualifying purchases. Visit the JetsonHacks storefront on Amazon: www.amazon.com/shop/jetsonhacks
Visit the website at jetsonhacks.com Sign up for the newsletter! newsletter.jetsonhacks.com Github accounts: github.com/jetsonhacks github.com/jetsonhacksnano
I tried this with a pcie mini to m2 nvme adapter with a nvme ssd. It somehow works to boot and use remote control with nomachine while still havin lots of pcie bus errors on my native screen.
Yes. They use machine learning models running on the Jetson to control their gait and animation kinematics. An operator directs the robot where to go and can trigger animations. There is additional hardware that could be used for autonomy in future development. Thanks for watching!
Can I ask for help to make a tutorial for installing Arduino Ide with ESP board on Jetson Orin? Because it always happens bootloop when I finish installing it. Thank you for the useful knowledge.
I can't read your question. Please ask for help on the official NVIDIA Jetson forums where NVIDIA engineers can help you through issues you may be encountering: forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/70
@@JetsonHacks My laptop is having trouble recognizing the jetson xaviernx developer kit. Can you tell me what it is to pin it at around 9 seconds in the video? Sorry if the sentence is weird using a translator. Answer me in English and I'll translate it and read it!
@@user-zx9cb8tj7i Ensure that your Jetson Xavier NX Developer Kit is powered off, and a 32GB or larger microSD card (preferably 64GB) is inserted in the SD card slot. Enable Force Recovery Mode by placing a jumper across pins 9 and 10 (FC REC and GND) of the button header (J14), located on the edge of the carrier board under the Jetson module.
@@JetsonHacks Should I connect pin 9 and pin 10 with an arm-arm jumper cable? Should I plug one side of the jumper cable into pin 9 and the other into pin 10?
First of all thank you for the great video, you helped through my first ai deployment I had a laugh seeing mine recognizing your voice testing yours through the speaker
It would be great if you could show closely which way up the threaded inserts are inserted. Either the non-knurled end goes downward or the knurled end, which is it ?
This video was made before I had camera skillz, so it isn't as clear as it could be. The non-knurled edge on this type of heat insert is smaller in diameter than the knurled side, insert the non-knurled edge first. The heat insert will partially seat, but will hang up once it hits the knurls. Once you heat up the insert, you will able to gently press the entire insert into the hole, with the plastic melting around the knurls. Once the plastic re-solidifies, the knurls will help when torque is applied to the inset. Thanks for watching!
Hello I use both of the commands on the github and It worked but after I install opencv using pip3 install opencv-python I can`t open my csi camera with those two command I wonder if I use the wrong way to download the opencv or what pls help thx
I believe that when you install opencv-python that will overwrite the native OpenCV package. The native OpenCV package has support for using the RPi camera with the Jetson. Thanks for watching!
Thank you for the good video. I'm using jetson orin nano like in the video and upgraded firmware to use ubuntu 22.04. I'm asking you a question because there's a problem downloading jetpack 6.0 and using it after a successful upgrade. I'm using the intel realsense camera D435i. To do this, I downloaded the realsense dummy package, downloaded realsense sdk. And then turned on the realsense-viewer, but there was a story that the camera was not connected, so I tried many things to solve it. I typed lsusb in the terminal, but it says the intel camera is connected, and I tried setting the camera permissions, but I still couldn't find the problem. I was wondering if I encountered something while upgrading firmware because I found a story that the camera might not turn on due to a kernel problem. Thank you for reading!
You are welcome. I am not sure what issue you are encountering. I don't have any experience running the RealSense on JetPack 6, you should ask on the RealSense Github or official NVIDIA Jetson forums for help. Thanks for watching!
Excellent video. I am setting up a group of jetson orin nano’s for a graduate class. The SSD drives are in, but the computers are slowly coming in. I am using a stand alone ubuntu 22.04 system to setup the SSD with the SDK Wizard. Can I create all of the SSD drives before the Jetson Orin Nano’s come in or do I have to wait until the actual computers come in. I noticed that if I plug in a SSD that was setup on a Jetson Orin Nano into a new computer, it does not boot. Is there a recommended practice to set this up? I want the systems to be identical for the class. The students would not have access to a stand alone linux system to run the wizard on their own. This way i can insure that the systems are identical and they will be starting with the same environment.
That's a good question. Typically people use mass flash when they are trying to create multiple SSDs like you describe. There are a couple of issues, depending on which Orin Nanos you receive. You may have to flash the Orins to update the QSPI to the version of JetPack that you are running. There's a lot here to parse, it's beyond what I can describe in a RU-vid comment. Your best bet is to ask on the Jetson Orin Nano forums where a NVIDIA engineer can help you get started on the process: forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/jetson-orin-nano/632 Thanks for watching!
hey sir !!! in my jetson xavier agx i have an ubuntu linux 16.04 ...now i forgot the password of that version ....how to download a new version in the xavier agx can you please tell me to go through my project....
You should ask for help on the official NVIDIA Jetson forums so that NVIDIA Engineers can help you find the issue: forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/70 Thanks for watching!
You are asking a different question. You are trying to start a venv at startup. One way to do that would be to write a service to start the venv and put into systemd. Thanks for watching!
@@JetsonHacks alright, just doing other methods of installation and came across a few questions as well.. from what i am trying to understand... it is possible to simply install the SDK for realsense and then install the ros wrapper with the apt-get installation process right? The method through the github is another option besides the apt-get install. Is this correct? Also curious how the SDK installation has anything to do with simply the apt-get installation? I've been unable to run the realsense ros wrapper without the SDK already installed, or am I doing something wrong? - really trying to understand the process here, thanks in advance!
@@sulaiman-hd8pz The SDK is a driver for the RealSense camera, and installs the libraries and samples. The ROS wrapper calls the libraries. If the libraries are not installed, the ROS wrapper does not have anything to work with. I would expect something like: $ sudo apt install ros-noetic-realsense2-camera to work. You can check what the package installs to see if the RealSense libraries are installed along with it.
Hello. I installed opencv 4.7.0 version on jetson nano with cuda. When I check in jtop, I can see that it says "opencv:4.7.0 with CUDA:YES". When I check it with python codes and terminl commands, I see CUDA is usable. However, when I want to detect objects with the yolov4-tiny model, I get an average of 2 fps. What's the problem? Can you help?
I don't know the answer. CUDA enabled code must be called. It sounds like your code does not call it. You should ask on the official NVIDIA forums or YOLO forums.
Hello, great tutorial exactly. Thanks a lot! Btw, there's something I'm curious about. Is Raspberry Pi camera module v2 compatible with Jetson Orin Nano?
Hı I have jetson orin nano and ı try to use csı camera named ımx219 but when I run opencv code it doesn't work. Then I checked GStreamer enable status on opencv it tell me GStreamer=NO how can I fix that problem.
import cv2 # GStreamer pipeline string for capturing from IMX219 camera on Jetson Nano pipeline = "nvarguscamerasrc sensor-id=0 ! video/x-raw(memory:NVMM), width=1280, height=720, format=NV12, framerate=21/1 ! nvvidconv ! video/x-raw, format=BGRx ! videoconvert ! video/x-raw, format=BGR ! appsink" # Open the capture pipeline cam = cv2.VideoCapture(pipeline, cv2.CAP_GSTREAMER) if not cam.isOpened(): print("Cannot open camera") exit() while True: ret, frame = cam.read() if not ret: print("Failed to grab frame") break cv2.imshow('Frame', frame) if cv2.waitKey(1) & 0xFF == ord('q'): break # Release the camera and close OpenCV windows cam.release() cv2.destroyAllWindows() here my code when I run it get me cannot open camera
awesome Vid and explanation. I have this camera . Just wondering how to capture the pointcloud and export it in a 3d format. Are there any simple apps that can do this? I was able to see eaverything as you did in the Femto bolt viewer. Thanks for any help.
Thank you for the kind words. Using the Orbbec SDK, you can look in the examples directory. Depending on which version of the SDK you are using (C, C++, Python), there are samples that save the point cloud to a file. For Python: github.com/orbbec/pyorbbecsdk/blob/main/examples/save_pointcloud_to_disk.py Thanks for watching!
@@JetsonHacks Thanks Jetson! I figured it out , you have to Orbbec viewer /under Point Cloud View /you click start and will save the pointcloud. I'm trying to figure out how to scan in 360 degree using the camera. Any software available that can do that? I'm more of an artist then a programmer.
@@fabianpalacios6711 The nano_build_opencv shell script will build the OpenCV libraries and place them into the system usr space. It will also place the Python wrappers in system-site-packages. A virtual environment will not include system python packages unless you specify it on creation with an option like --system-site-packages in the case of virtualenv. If for some reason this doesn't work you should be able to copy or link opencv from its installation path to your virtual env's python path. Like: $ ln -s /usr/local/lib/python3.6/dist-packages/cv2/ /path/to/venv/lib/python3.6/site-packages/ You can read more about it here: github.com/mdegans/nano_build_opencv/issues/32
This is a product that flys under the radar, it's mostly for professional users and people that have critical missions to fulfill. But if you need it, you need it. Thanks for watching!
@@JetsonHacks Yep. Currently, I maintain 5 Jetson Nano remotely. They have 4G connectivity. I configured Ngrok tunnels for each of them to connect with ssh and eventually VNC. I think that this product would be an overkill to me. Important to know the concept though.
@@hanshima_ I think that's smart way to do it. As you might guess, the whole thing can escalate quickly and get out of hand as you keep adding Jetsons. It depends on the application, but if you have to absolutely make sure it works and the Jetsons are remote, the Allxon solution is a good place to start looking. It's so familiar to see cloud based services for managing networked computers, such as on AWS and Google Cloud, that device specific solutions like this seem natural.
Hello. I'm getting the following error when attempting to manually flash ERROR: Flash Jetson Linux - flash: command terminated with error SUMMARY: DateTime Target Setup - target: Depends on failed component How should I go about fixing this?
I'm not sure what the error means. Please ask the question on the official NVIDIA Jetson forum where a NVIDIA engineer can help you through the issue. Good luck, and thanks for watching!
Hello, I have a funny problem: when I am trying to power board up it remains a brick, except three LED are going on but cooling fan jerks and not turning. Any idea how to start this baby? Thanks in advance. It is very important for me!
I'm not sure where you are in the process. Did you flash the machine? You should be asking for help in the official NVIDIA Jetson TX2 forum where NVIDIA engineers can help you through the process: forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/jetson-tx2/81 Good luck!
@@JetsonHacks I figured that out. The flashing fails at 83% saying waiting for the target to boot up it reached time out and then fails. The orin device fans spin up and stop intermittently. I also tried out your repo for booting up from external device. That also gave the same issue. What should be done here?
@@harshalbhat5638 It's difficult tell what the issue is. It will depend on which version of JetPack you are trying to install. You will probably need to use the serial debug console to determine where the flashing procedure is stopping. If you are using JetPack 6, you most likely need to flash the eMMC to update the bootloader firmware. Your best bet is to ask for help on the official NVIDIA Jetson Orin Forum where a NVIDIA engineer can walk you through the issues you are having: forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/jetson-agx-orin/486
Yes it does. The camera has an IR emitter which it uses to construct the point cloud. It does not work very well in direct sunlight for that reason. Most people use them indoors. Thanks for watching!
I just generated a new JetPack 6 system on a Jetson Orin Nano, and followed the video. The startup script appears after logging in. You appear to be having an issue of some sort, but it's difficult to tell from your description what it might be. Are you running the provided script? Does it run from the command line? What is your exact startup command that you placed in the startup application dialog?