Why is the infer time of the same yolov3 model different under YOLOv3 detect.py and YOLOv5 detect.py?

[Forever518]

Search before asking

• I have searched the YOLOv3 issues and discussions and found no similar questions.

Question

I have trained a YOLOv3 model with COCO dataset and I got different inference time when I used detect.py of YOLOv3 and YOLOv5. The V100 detection time per image under YOLOv3 is about 9ms but under YOLOv5 it's about 13ms+. So I wonder what's the difference between the validation or detection of YOLOv3 and YOLOv5?

Additional

BTW I found the YOLOv5 code can be used to train YOLOv3 when config yolov3.yaml. However the yolov3 model got higher performance than the one trained under YOLOv3 code where I have seen some training tricks from v4 and v5. What are the training optimizations of YOLOv5 or YOLOv4 that this YOLOv3 code has not implemented yet?

[github-actions]

👋 Hello @Forever518, thank you for your interest in YOLOv3 🚀! 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://ultralytics.com or email Glenn Jocher at [email protected].

Requirements

Python>=3.6.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

$ git clone https://github.com/ultralytics/yolov3
$ cd yolov3
$ pip install -r requirements.txt

Environments

YOLOv3 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 YOLOv3 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@Forever518 you are not correct, yolov3.pt inference times between this repo and ultralytics/yolov3 are identical:

[Forever518]

Ohh I find I didn't update my local repo......So what are the remaining differences between this yolov3 repo and the yolov5 repo after merging YOLOv5 v6.0 compatibility update #1857? @glenn-jocher

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv3 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov3/wiki
• Tutorials – https://github.com/ultralytics/yolov3#tutorials
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

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 YOLOv3 🚀 and Vision AI ⭐!

[glenn-jocher]

@Forever518 the remaining differences between the YOLOv3 repo and the YOLOv5 repo are mainly related to the architecture design and specific optimizations implemented in YOLOv5, such as different anchor box priors, model scaling, and training strategies. The YOLOv5 model brings in improvements and optimizations developed through experience working on v4 and v5. Feel free to explore the YOLOv5 codebase to learn more about the advancements and optimizations not present in the YOLOv3 codebase.