YOLOV5 no longer works on Nvidia Jetson Nano about yolov5 HOT 4 OPEN

@gilmotta3 hello! I'm sorry to hear you're experiencing issues running YOLOv5 on the NVIDIA Jetson Nano. 🙁

The error message you're seeing indicates a problem with importing a module from the Ultralytics package. This sounds like there might be an issue with the package installation or a compatibility issue with the setup on the Jetson Nano.

To help solve this, please ensure that you've followed all the steps for installation as listed in our documentation, and all dependencies are correctly installed in your environment. Since you're using specific versions of PyTorch and torchvision recommended for the Jetson Nano, please double-check that these versions are fully compatible with the latest YOLOv5 code from our main branch. Sometimes, updates or changes in YOLOv5 might require newer versions of these libraries.

If after checking the compatibility and ensuring all installations are correct the issue persists, it might be beneficial to try installing YOLOv5 in a fresh virtual environment to rule out any conflicts with other installed packages.

We're continually working to improve compatibility and ease of use on a wide range of devices, including the NVIDIA Jetson series. Your feedback is valuable to us in this process.

If the problem continues, please provide additional details including any error messages or logs, and we'll do our best to assist you further.

👍 Thank you for your support and patience.

from yolov5.

@glenn-jocher I have followed the instructions and tried to install new virtual environments. I have been doing this for the last three days and I deviated my focus from the actual business because YOLO does not work and the repo is broken and I am trying to see the issue. I have watched dozens of videos on YouTube from a year ago or so to find out that I am doing the same exact things but now they don't work. I came across other developers who are having the same issue but for some reason they did not open a bug ticket.

I am telling categorically that YOLOv5 is broken for Nvidia Jetson Nano. Unless you have the hardware yourself you aren't going to see the issue. I am now trying to switch to a Docker Container solution but even Docker is now failing to install.

from: https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart

(video) video@video-desktop:/development/docker$ sudo docker pull ultralytics/yolov5:latest
[sudo] password for video:
latest: Pulling from ultralytics/yolov5
no matching manifest for linux/arm64/v8 in the manifest list entries
(video) video@video-desktop:/development/docker$

only to find out tha there is no support for ARM

if you would like to solve this problem I can make myself available in whatever time zone you are but I ran out of options and I will start looking for other options. Maybe Jetson Nano is old and I made a mistake picking up this board.

I can make this board available to anyone willing to help via SSH.

Anyone reading this ticket if there is no update here, I would suggest you not waste your time.

Good Luck!

from yolov5.

@gilmotta3, I'm genuinely sorry to hear about the troubles you've been experiencing with getting YOLOv5 up and running on the NVIDIA Jetson Nano. It's clear you've invested a lot of effort into this, and it's frustrating when things don't go as planned. 🙁

The error you're encountering with Docker and the ARM architecture is unfortunately a known compatibility issue due to the lack of an ARM build for our Docker image. This is indeed a limitation for users on ARM-based devices like the Jetson Nano.

While we currently don't have a ready-made solution for ARM devices in our Docker images, I appreciate your offer to make the board available for testing. This could be beneficial for community-driven solutions, though our capacity to personally dive into hardware-specific issues is limited.

For now, I would suggest:

• Cross-verifying all software versions (Python, PyTorch, etc.) are within the compatibility range of the YOLOv5 version you're using.
• Considering a manual setup outside of Docker, ensuring all dependencies are correctly installed for your platform. Sometimes, installation from source rather than pre-built wheels (where possible) can resolve unexpected issues.

Your situation also highlights a gap in our support for ARM architectures, which we'll take as valuable feedback for our roadmap.

Though I understand if this situation necessitated exploring alternatives, I hope you'll stay connected to future updates. The YOLOv5 community is continually growing, with improvements and solutions contributed regularly.

Thank you for your patience and your detailed feedback. 🙏

from yolov5.

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

from yolov5.