About Precision Reproduction

[PX-Xu]

Dear authors:
I really appreciate your work. But there are some problems when I reproduce your work.
Firstly, I used the weight that you provided in the Google driver. The result is below:

It seems like the mAP is lower than the number in your paper. The mAP in the paper is 48.9%. And I use the weight to reproduce the result. The mAP is 46.6%.

Furthermore, I follow the instructions in this repository to train and reproduce this work in foggy-cityscapes dataset. The result is below:

There are large gaps between the mAP in your paper and the reproduced result.

I wonder is any problem with my val dataset. Or are there any other settings when training?

Hope you respond!

Best wishes!

[github-actions]

👋 Hello @PX-Xu, 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://ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

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

$ git clone https://github.com/ultralytics/yolov5
$ cd yolov5
$ 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), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[qinhongda8]

Dear authors: I really appreciate your work. But there are some problems when I reproduce your work. Firstly, I used the weight that you provided in the Google driver. The result is below:

It seems like the mAP is lower than the number in your paper. The mAP in the paper is 48.9%. And I use the weight to reproduce the result. The mAP is 46.6%.

Furthermore, I follow the instructions in this repository to train and reproduce this work in foggy-cityscapes dataset. The result is below:

There are large gaps between the mAP in your paper and the reproduced result.

I wonder is any problem with my val dataset. Or are there any other settings when training?

Hope you respond!

Best wishes!

由于这个方法包含3个点，建议你复现出现问题的话，可以通过消融实验的方式来判断是哪一个部分出现了问题，可以按照我们论文中的实验流程，分别按源域训练、对抗部分和图像转换步骤来进行，并根据每次的mAP结果来分析。另外，这份代码为完整代码。

[PX-Xu]

Thanks for your response! I will follow your advice to try it.