Images in MPO Format are considered corrupted

[maxupp]

I am using images taken by a DJI drone. These images are deemed corrupted by the dataset loader, and are thus not used.
This happens because in datasets.py the im.format is checked against a list of formats that doesn't contain "mpo".
If I add that entry manually everything works as expected.

MPO is a container format, that can contain any of the valid formats.

🐛 Bug

Images that report "MPO" as PIL.Image.format are deemed corrupted.

To Reproduce (REQUIRED)

Try to load MPO images.

I'm not sure whether Github tempers with the image. If necessary I can upload somewhere else.

Expected behavior

Images should be considered valid.

[github-actions]

👋 Hello @maxupp, 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://www.ultralytics.com or email Glenn Jocher at [email protected].

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@maxupp ah interesting, thanks for the bug report!

If *.mpo suffixes work then we should add them to the list. We recently added *.webp as well based on user feedback. Can you add the format to the approved formats list here, and verify correct operation for your training set, and submit a PR if everything goes well please? Thanks!

yolov5/utils/datasets.py

Lines 27 to 30 in 886f1c0

	# Parameters
	help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
	img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp'] # acceptable image suffixes
	vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes

[glenn-jocher]

Removed TODO as *.mpo now added to YOLOv5 supported image formats.