zero-mAP fix remove torch.empty() forward pass in .train() mode

[0zppd]

Signed-off-by: 0zppd 111682241+0zppd@users.noreply.github.com

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Upgraded logging to use zero-initialized tensor for improved stability during TensorBoard graph generation.

📊 Key Changes

• Changed input image initialization from torch.empty() to torch.zeros().

🎯 Purpose & Impact

• Ensures more consistent initialization by using zero-filled tensors, which can help avoid any potential issues caused by uninitialized memory.
• The change could lead to more reliable model graph visualization in TensorBoard, benefiting users who analyze model architectures and debug them.

[github-actions]

👋 Hello @0zppd, thank you for submitting a YOLOv5 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to:

• ✅ Verify your PR is up-to-date with upstream/master. If your PR is behind upstream/master an automatic GitHub Actions merge may be attempted by writing /rebase in a new comment, or by running the following code, replacing 'feature' with the name of your local branch:

git remote add upstream https://github.com/ultralytics/yolov5.git
git fetch upstream
# git checkout feature  # <--- replace 'feature' with local branch name
git merge upstream/master
git push -u origin -f

• ✅ Verify all Continuous Integration (CI) checks are passing.
• ✅ Reduce changes to the absolute minimum required for your bug fix or feature addition. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." -Bruce Lee

[AyushExel]

I think #9067 includes these changes

[glenn-jocher]

@0zppd thanks for the PR! Are you sure this is the only place that torch.empty() is causing problems? See #9067

[glenn-jocher]

@AyushExel if this is the only source of error then this PR is preferred as #9067 introduces some slight speed improvements, torch.empty() profiles faster than torch.zeros(), which was the original purpose behind #9067, but it seems the danger is when the model BN layers are in train mode and they are updating based on the inputs.

EDIT: testing this now x10 in Colab

[0zppd]

I have extensively tested this, and making only this change consistently removes the issue (and reverting the change brings it back ) in the same Colab session.

[glenn-jocher]

Confirmed on 10x colab training all good

[glenn-jocher]

@0zppd PR is merged. Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐

[robotaiguy]

Great work! You guys handled the business!

[pourmand1376]

I tested this PR on colab 30 times and I found no problem. I think this is finally resolved.

[glenn-jocher]

@pourmand1376 that's fantastic news! I'm glad to hear that the changes have been thoroughly tested and are proving effective. Your input and testing are invaluable to the YOLOv5 community. Thank you for your dedication to improving the project!