LazyInstanceNorm2d need torch>=1.10

[Beb007]

Hello,

Fantastic work !
I faced an issue with my latest run:

Traceback (most recent call last):
  File "train.py", line 667, in <module>
    main(opt)
  File "train.py", line 562, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 154, in train
    bn = nn.BatchNorm2d, nn.LazyBatchNorm2d, nn.GroupNorm, nn.InstanceNorm2d, nn.LazyInstanceNorm2d, nn.LayerNorm
AttributeError: module 'torch.nn' has no attribute 'LazyInstanceNorm2d'

LazyInstanceNorm2d seems to be included from torch version 1.10, and not present in 1.9.1 usually used from Kaggle

I tried pip install torch==1.11 (latest) but got packages conflicts
With torch=1.10, no conficts, but faced another issue with protobuf.
My first though was to suggest a change in requirements, but, as theses packages conflicts can become really awkward... I leave it for now and just report it...

Best regards

PS: my bad, I should had put this in issue section

Originally posted by @Beb007 in #7380

[github-actions]

👋 Hello @Beb007, 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.

[Beb007]

Temporary, I use 'classifier' branch and it's working fine.

git clone --branch classifier https://github.com/ultralytics/yolov5

[rohitrrg]

Yes, I have the same issue with training the custom model.
few days ago, it was working fine with the same code and configurations.

[glenn-jocher]

@Beb007 @rohitrrg good news 😃! Your original issue may now be fixed ✅ in PR ##7392. This PR dynamically allocates a tuple of normalization layers based on the current torch version, so should be compatible with any torch release past or future.

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 🚀!