Trouble installing Ultralytics on the Jetson Nano about ultralytics HOT 5 OPEN

👋 Hello @bwajster97, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

from ultralytics.

pip install ultralytics and pip install ultralytics==8.0.231 returns the error below on my Jetson Nano (JetPack 4.6.1):

Collecting torchvision>=0.9.0 (from ultralytics==8.0.231) Could not find a version that satisfies the requirement torchvision>=0.9.0 (from ultralytics==8.0.231) (from versions: 0.1.6, 0.1.7, 0.1.8, 0.1.9, 0.2.0, 0.2.1, 0.2.2, 0.2.2.post2, 0.2.2.post3) No matching distribution found for torchvision>=0.9.0 (from ultralytics==8.0.231)

Please help me resolve this error.

from ultralytics.

@bwajster97 hi there,

Thank you for reaching out and providing detailed information about the issue you're encountering on your Jetson Nano. Let's work through this together to get Ultralytics YOLOv8 up and running on your device.

Issue Breakdown

The errors you're seeing are related to the installation of torchvision and numpy packages, which are dependencies for Ultralytics. The Jetson Nano, being an ARM64 architecture, requires specific versions of these packages that are compatible with its architecture.

Solution Steps

1. Uninstall Existing Packages

First, let's ensure that any existing incompatible versions of torch and torchvision are uninstalled:

pip uninstall torch torchvision

2. Install Compatible PyTorch and Torchvision

Next, we'll install the compatible versions of PyTorch and Torchvision for JetPack 4.6.1. Follow these steps:

1. Install PyTorch:

   sudo apt-get install -y libopenblas-base libopenmpi-dev
   wget https://developer.download.nvidia.com/compute/redist/jp/v46/pytorch/torch-1.10.0+nv21.11-cp38-cp38-linux_aarch64.whl
   pip install torch-1.10.0+nv21.11-cp38-cp38-linux_aarch64.whl

2. Install Torchvision:

   sudo apt-get install -y libjpeg-dev zlib1g-dev
   git clone --branch v0.11.1 https://github.com/pytorch/vision torchvision
   cd torchvision
   python3 setup.py install --user

3. Install Ultralytics

Now, you can proceed to install the Ultralytics package with the necessary dependencies:

pip install ultralytics[export]

4. Install ONNX Runtime (Optional)

If you plan to use ONNX models, you'll need to install onnxruntime-gpu manually as the PyPI version does not support ARM64:

wget https://nvidia.box.com/shared/static/zostg6agm00fb6t5uisw51qi6kpcuwzd.whl -O onnxruntime_gpu-1.17.0-cp38-cp38-linux_aarch64.whl
pip install onnxruntime_gpu-1.17.0-cp38-cp38-linux_aarch64.whl
pip install numpy==1.23.5  # Reinstall numpy to fix potential issues

Additional Resources

For more detailed instructions, you can refer to our NVIDIA Jetson Guide. This guide provides comprehensive steps for setting up and running Ultralytics YOLOv8 on various Jetson devices.

If you encounter any further issues or have additional questions, feel free to ask. We're here to help! 😊

from ultralytics.

@glenn-jocher Thank you for the detailed response.

The command wget https://developer.download.nvidia.com/compute/redist/jp/v46/pytorch/torch-1.10.0+nv21.11-cp38-cp38-linux_aarch64.whl returns the error below:

wget https://developer.download.nvidia.com/compute/redist/jp/v46/pytorch/torch-1.10.0+nv21.11-cp38-cp38-linux_aarch64.whl --2024-06-14 11:52:59-- https://developer.download.nvidia.com/compute/redist/jp/v46/pytorch/torch-1.10.0+nv21.11-cp38-cp38-linux_aarch64.whl Resolving developer.download.nvidia.com (developer.download.nvidia.com)... 152.199.39.144 Connecting to developer.download.nvidia.com (developer.download.nvidia.com)|152.199.39.144|:443... connected. HTTP request sent, awaiting response... 404 Not Found 2024-06-14 11:53:00 ERROR 404: Not Found.
PS: I'm on JetPack 4.6.1, Cuda 10.2.300, Python 3.8.0 (OpenCV 4.8.0 with CUDA support)

Please help me resolve this.

from ultralytics.

Hi @bwajster,

Thank you for your patience and for providing the detailed error message. It looks like the specific PyTorch wheel for JetPack 4.6.1 is no longer available at the provided URL, resulting in a 404 error.

Let's resolve this by using an alternative source for the PyTorch wheel compatible with JetPack 4.6.1. Follow these updated steps:

1. Uninstall Existing Packages

First, ensure any existing incompatible versions of torch and torchvision are uninstalled:

pip uninstall torch torchvision

2. Install Compatible PyTorch and Torchvision

1. Install PyTorch:

   sudo apt-get install -y libopenblas-base libopenmpi-dev
   wget https://nvidia.box.com/shared/static/3jq5z8a2j9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z

from ultralytics.