Should I have argument while training?

[AlecMaxPro]

Search before asking

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

Question

I use the version of Yolov5-6.1. I notice there is no the default of cfg argument. But others basic argument have all defaults. Should I have "--cfg models/yolov5s.yaml" while I'm training my own models? Whether there is a bad influence in results, if I don't have this cfg(models/yolov5s.yaml).

But I also find whether I add "--cfg yolov5s.yaml" or not, the layers of this models (yolov5s) can always be run.

Thanks a lot!

Additional

No response

[github-actions]

👋 Hello @AlecMaxPro, 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>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. 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 @AlecMaxPro, thank you for your question! The --cfg argument specifies which configuration file to use, which contains the model architecture and hyperparameters. If it is not specified, YOLOv5 will use the default configuration file for the selected model size (yolov5s.yaml for --weights yolov5s.pt, yolov5m.yaml for --weights yolov5m.pt, etc). However, it is recommended to specify the --cfg argument to ensure reproducibility between training and inference. It should not have a bad influence on the results if you don't specify it, but it is always better to be explicit.

Regarding the layers of the model being able to run without specifying the --cfg argument, this is because the default configuration file for each model size is used. If you specify a different configuration file, the architecture and hyperparameters of the model will be different, which can impact the results.

Please let me know if you have any further questions or concerns.

[AlecMaxPro]

Ok, I know it. That's a very explicit answer.

Thanks again!

[glenn-jocher]

You're welcome, @AlecMaxPro! I'm glad I could help. If you have any more questions or run into any issues in the future, don't hesitate to ask. Have a great day!