Latest code can't reproduce YOLOv5s on coco

[leedewdew]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

Training

Bug

With latest code pulled Yesterday, I can't reproduce YOLOv5s on coco which is 37.4%, while I get 30.4%.
However, when I train YOLOv5s with the version mentioned in this wandb workspace, the mAP at the end of each epoch nearly match what the log shows in wandb. But the latest code doesn't.

Environment

No response

Minimal Reproducible Example

python -m torch.distributed.run --master_port 1234 --nproc_per_node 4 train.py
--batch 64
--data data/coco.yaml
--weights ''
--cfg models/yolov5s.yaml
--device 0,1,2,3

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[github-actions]

👋 Hello @leedewdew, 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 support@ultralytics.com.

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):

• 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.

[glenn-jocher]

@leedewdew related to DDP mAP drop issue #9545

[glenn-jocher]

@leedewdew good news 😃! Your original issue may now be fixed ✅ in PR #9545. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[leedewdew]

Thank you for quick response. I'll try.

[leedewdew]

I get 36.7% for YOLOv5s. Is that normal?

python train.py --epochs 300 --batch 64 --data data/coco.yaml --weights '' --cfg models/yolov5s.yaml --noplots --device 0,1,2,3,4,5,6,7 --project /runs/train --name v5

[glenn-jocher]

@leedewdew seems about right. For README results you should train on segmentation labels:

bash get_coco.sh --train --val --segments