What are the other variants of released models?

[chunchet-ng]

❔Question

Hi there, I have noticed that there are several variants of the models being released this time. For instance, there are yolov5l6.pt, yolov5l7-s3.pt, yolov5m6.pt, yolov5s6.pt, and yolov5x6.pt. What are the main changes of these variants, and what does it mean by the additional "6" behind the model's name?

Additional context

You can find them on this page (release v4.0).

Thank you very much.

[github-actions]

👋 Hello @chunchet-ng, 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 screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at [email protected].

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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):

• Google Colab and Kaggle 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 (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[kinoute]

More informations about these models can be found here: #2110

[glenn-jocher]

@chunchet-ng models with a '6' suffix include a P6 output layer (P3, P4, P5, P6) and are trained at 1280. These generally achieve better mAP on COOC than their default counterparts, which include the normal 3 outputs P3, P4, P5 and are trained at 640.

We are planning on a v5.0 release soon which details all of this better in the README.

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.