Comments (5)
👋 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:
-
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
-
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
- Install PyTorch:
sudo apt-get install -y libopenblas-base libopenmpi-dev wget https://nvidia.box.com/shared/static/3jq5z8a2j9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z0z9x1z
from ultralytics.
Related Issues (20)
- val step slow down during training HOT 7
- Batch inference speed same than looping through a bunch of imgs HOT 3
- Using YOLOv8(seg) with SHAP HOT 5
- yolov8 object_counting in and out doesn't differentiate for defined line HOT 4
- how to set `verbose:false` so that model can predict the batches without printing anything in the terminal HOT 1
- Questions about incremental training HOT 3
- How can I use the segmentation models of previous versions? HOT 4
- yolov8-obb plot train labels maybe error HOT 2
- Error Code 2: Internal Error (Assertion cublasStatus == CUBLAS_STATUS_SUCCESS failed. ) HOT 4
- Yolov10 Can't get attribute 'SCDown' on <module 'ultralytics.nn.modules.block' from 'C:\\Users\\ZHANG\\miniconda3\\lib\\site-packages\\ultralytics\\nn\\modules\\block.py'> HOT 20
- yolov8 -- After the cache is turned on, the memory occupied by reading val data is too large HOT 5
- YOLOv10 Performance Issue: Version 3.12 Fast, But 3.11 and Below Very Slow HOT 8
- yolo8 onnx in opencv HOT 2
- Is OBB available for yolov9 and v10 ? HOT 1
- Clamping in bbox2dist HOT 2
- Question about code of position embedding in rt-detr HOT 5
- Process group init fails when training YOLOv8 after successful tunning [Databricks] [single node GPU] HOT 4
- Train with single gpu HOT 3
- Yolo8-OnnxRuntime-CPP-Inference awful output HOT 6
- confusion matrix single HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ultralytics.