ultralytics 8.4.7

v8.4.7 - `ultralytics 8.4.7` AVIF training and new COCO12-Formats dataset (#23358)

on Python PyPI

🌟 Summary

Ultralytics v8.4.7 adds AVIF training support and a new COCO12-Formats mini-dataset to continuously verify that all supported image types load correctly end-to-end (especially in CI) 🧪🖼️

📊 Key Changes

• AVIF is now a supported training image format ✅📷
  • IMG_FORMATS expanded to include avif
• More robust image decoding for modern formats 🛡️
  • Adds a Pillow-based fallback image reader (_imread_pil) for cases where OpenCV can’t decode AVIF/HEIC
• New “COCO12-Formats” dataset + generator script 🧰
  • A tiny 12-image dataset covering all supported extensions (AVIF, BMP, DNG, HEIC, JP2, JPEG, JPG, MPO, PNG, TIF, TIFF, WebP)
  • Includes a dataset YAML and a generator (generate_coco12_formats.py) to build the set for testing/validation
  • Adds a dedicated docs page and links it in the dataset index 📚
• Training and tooling reliability improvements 🔧
  • Fixes loss image-size calculation for OBB and Pose26 multi-scale training 📐
  • Fixes semantic segmentation masking/indexing for overlapping instances 🧩
  • More accurate optimizer parameter-group logging 🧾
  • Adds retry + validation for dataset image downloads (NDSON) 🔁📥
• Install/export stability & experiment tracking 📦📈
  • Pins torch < 2.10 to prevent ExecuTorch export incompatibilities 🧷
  • Saves runs under runs/ by default for relative projects + improves W&B traceability 🗂️
• Docs updates (large) 📝⚡
  • Docs images migrated to a CDN and improved alt text for accessibility/SEO

🎯 Purpose & Impact

• Train directly on AVIF images without manual conversion 🎉
  • Useful for modern web/phone pipelines where AVIF is common
• Fewer “it works on my machine” image-loading failures 🧯
  • The new COCO12-Formats dataset is designed to catch format-specific decoding issues early, especially in CI/CD
• Better resilience across environments 🌍
  • Pillow fallback reduces dependence on how OpenCV was built (many prebuilt OpenCV wheels lack AVIF support)
• More reliable training & clearer debugging 🔍
  • Fixes reduce subtle scaling bugs (Pose/OBB), segmentation masking issues, and misleading optimizer logs
• Smoother installs/exports and cleaner run management 🚀
  • Dependency pin helps prevent breakage; run folder changes improve organization and experiment tracking

What's Changed

• Fix docs images content disposition by @glenn-jocher in #23322
• Docs images cleanup by @glenn-jocher in #23323
• Fix the length of optimizer params group print by @Laughing-q in #23314
• Platform docs by @glenn-jocher in #23338
• Route outputs to runs/ by default and improve W&B run traceability by @artest08 in #23026
• fix image size calculation in OBB and Pose26 loss for multi-scale training by @lmycross in #23342
• fix: 🐞 pin torch version to <2.10 for executorch export by @onuralpszr in #23353
• fix semantic segmentation loss indexing error by @lmycross in #23330
• Retry NDSON download failures by @glenn-jocher in #23354
• Fix multi_scale range sampling and clarify docs by @artest08 in #23284
• ultralytics 8.4.7 AVIF training and new COCO12-Formats dataset by @glenn-jocher in #23358

New Contributors

• @artest08 made their first contribution in #23026

Full Changelog: v8.4.6...v8.4.7