search

ultralytics / yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
https://docs.ultralytics.com
GNU Affero General Public License v3.0
50.39k stars 16.26k forks source link

Is it able to run YOLOv5 inference on non-NVIDIA GPUs? #12688

Closed khanhtrannnn closed 7 months ago

khanhtrannnn commented 8 months ago

Search before asking

Question

I'm working with the Khadas VIM3 board, a single-board computer. It uses a Mali-G52 MP4 GPU, which is not an NVIDIA GPU. It appears that YOLOv5 is compatible only with CUDA devices, as the debug log indicates a requirement for either CPU-only or CUDA devices. 

python3 detect.py --weights yolov5s-fp16.tflite --img-size 384 640 --conf 0.01 --line-thickness=1 --source data/videos/traffic5s.mp4 --device 0

AssertionError: Invalid CUDA '--device 0' requested, use '--device cpu' or pass valid CUDA device(s)

Could someone please confirm if YOLOv5 can utilize non-NVIDIA GPU? Thank you.

Additional

No response

github-actions[bot] commented 8 months ago

👋 Hello @khanhtrannnn, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

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.

Requirements

Python>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Status

YOLOv5 CI

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics
glenn-jocher commented 8 months ago

@khanhtrannnn hello! YOLOv5 primarily supports NVIDIA GPUs through CUDA for acceleration. However, you can run YOLOv5 on CPU or use the ONNX/TFLite models for running on other platforms that may support those formats. For a Mali-G52 MP4 GPU, you might want to explore running the TFLite model with inference backends that support Mali GPUs, such as Arm NN or TFLite's GPU delegate. Keep in mind that performance may vary and you might need to handle additional integration steps. For more detailed guidance, please refer to our documentation. Happy coding! 😊🚀

github-actions[bot] commented 7 months ago

👋 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:

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 ⭐