Is it possible to add ShuffleNetV2 as backbone in the official repo?

[superbayes]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

According to the information I found, ShuffleNetV2 has achieved a good balance in speed and accuracy. ShuffleNetV2 is conducive to the promotion of yoloV5 on various devices.
so,Is it possible to add ShuffleNetV2 as backbone in the official repo?

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Who is the king of lightweight CNN? Comprehensive evaluation in 7 dimensions mobilenet/shufflenet/ghostnet

Additional

No response

[github-actions]

👋 Hello @superbayes, 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):

• 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 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]

Hello! Thanks for bringing up the idea of incorporating ShuffleNetV2 as a backbone for YOLOv5. 🚀

We're always excited to explore ways to improve and adapt YOLOv5 for various device efficiencies and accuracies. While integrating a new backbone like ShuffleNetV2 can potentially enhance YOLOv5 for mobile and edge devices, such updates require thorough testing and validation to maintain the balance between speed, accuracy, and compatibility.

As of now, we encourage community contributions and experiments with different backbones. If you're interested in implementing ShuffleNetV2 yourself, you can fork the repo and try integrating it. This could be a valuable contribution to the community if shared back. Also, keep an eye on our updates; we're continually exploring new ideas!

For more guidance on contributing or custom modifications, check out the docs at https://docs.ultralytics.com/yolov5/.

Thanks for your enthusiasm and suggestions! 💡