Add support for *.pfm images

[spacewalk01]

Solved the following issue:
#9222 (comment)

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Expanded image format support in YOLOv5 data loaders.

📊 Key Changes

• Added support for .pfm image format files.

🎯 Purpose & Impact

• Enhanced Flexibility: Users can now use .pfm (Portable Float Map) files for input, which is beneficial for depth maps or HDR images.
• Broader Applicability: The YOLOv5 model can be trained on a more diverse set of image data, potentially improving its utility in fields that use this format, like computer vision research or image processing.

[github-actions]

👋 Hello @spacewalk01, 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

[spacewalk01]

Tested 'pfm' extension with opencv imread:

[glenn-jocher]

@spacewalk01 thanks for the PR! Have you been able to train correctly with *.pfm images on this branch?

[glenn-jocher]

@spacewalk01 PR is merged. Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐

[spacewalk01]

Oh you merged, I was trying to test training model with pfm images. I will test it and fix if there is any problem.

[urbansound8K]

I could not train??

AssertionError: train: No labels found in D:\rty\yolov5\datasets\coco128\labels\train2017.cache, can not start training. See https://docs.ultralytics.com/yolov5/tutorials/train_custom_data

the labels are there when I change the images extension, it works well

I used MiDaS to get the depth.
please help?
thanks a lot

[glenn-jocher]

@urbansound8K it seems that the issue might be related to the labels for the pfm images. We recommend verifying the label files and ensuring they are correctly formatted and in the expected directory. 📝 You can find guidelines for training custom data in the YOLOv5 documentation at https://docs.ultralytics.com/yolov5/tutorials/train_custom_data. Let us know if you need further assistance.