Hope a DyT Try

[Chenpeel]

I came across a paper suggesting DyT functions could replace traditional normalization methods. Surprisingly, using this normalization-free approach actually boosted performance in certain models. Does this sound practical enough for us to test it out?

Paper URL

[UltralyticsAssistant]

👋 Hello @Chenpeel, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials for quickstart guides and advanced concepts, including Custom Data Training and 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 or feature suggestion, please provide as much information as possible, including links to relevant research (like the one you shared), implementation details, and any initial experiments or logs if available. Also, 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.

This is an automated response 🤖 — an Ultralytics engineer will review your suggestion and assist you soon!

[Y-T-G]

Isn't this for transformers?