add support for custom augmentations

[vaskers5]

I add faced the same issue and support for custom torchvision.Transforms like augmentations

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhanced YOLOv5 image augmentation with torchvision transformations during inference.

📊 Key Changes

• Introduced torchvision.transforms as T to allow advanced image transformations.
• Modified the forward function signature to accept a transform composition (augment: T.Compose) instead of a boolean flag.
• Updated _forward_augment to apply the augment transformations to images before running inference.

🎯 Purpose & Impact

• Purpose: To enable more sophisticated and customizable image transformations during model inference, improving the versatility and accuracy of the model under various conditions.
• Impact: Users can now pass custom torchvision transform pipelines to the model during inference, potentially improving results and allowing for experiments with different augmentations. This change could lead to better performance in real-world applications by simulating various scenarios that the model may encounter.

[github-actions]

👋 Hello @vaskers5, 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 ultralytics/yolov5 master branch. If your PR is behind you can update your code by clicking the 'Update branch' button or by running git pull and git merge master locally.
• ✅ Verify all YOLOv5 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

[vaskers5]

now in can works like this:

`import torchvision.transforms as T

augment=T.Compose([
# T.ToTensor(),
# T.Normalize([0.5], [0.5]),
T.functional.rgb_to_grayscale,
lambda item: item.repeat(1, 3, 1, 1),
# T.ToPILImage()
])

model(img_path,
augment=augment
).show()`

[github-actions]

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions YOLOv5 🚀 and Vision AI ⭐.

[github-actions]

👋 Hello there! We wanted to let you know that we've decided to close this pull request due to inactivity. We appreciate the effort you put into contributing to our project, but unfortunately, not all contributions are suitable or aligned with our product roadmap.

We hope you understand our decision, and please don't let it discourage you from contributing to open source projects in the future. We value all of our community members and their contributions, and we encourage you to keep exploring new projects and ways to get involved.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[glenn-jocher]

@vaskers5 glad to know it's been working for you! YOLOv5 now supports custom augmentations with torchvision.transforms like this. If you have any other questions or need further assistance, feel free to ask!