ultralytics 8.4.15

v8.4.15 - `ultralytics 8.4.15` HEIC/HEIF image support (#23714)

on Python PyPI

🌟 Summary (single-line synopsis)

Ultralytics v8.4.15 improves real-world image ingestion (adds HEIC/HEIF + HEIF support with lazy decoding + better EXIF handling) and includes several quality fixes for metrics, exports, and docs 🖼️⚙️✅

📊 Key Changes

• HEIC/HEIF image support (priority change) 🖼️📱
  • Added ultralytics.utils.patches.image_open and monkey-patched PIL.Image.open to lazily enable HEIC/HEIF decoding via pi-heif only when needed (i.e., on first decode failure) ⏱️
  • Expanded supported extensions to include .heif (in addition to .heic) ✅
  • Removed HEIC-specific loading code from dataset loaders (now unified through the standard image reading pathway) 🧹
• Better plotting for non‑Latin text 🈶🖋️
  • Improves matplotlib defaults by prioritizing Arial Unicode MS and auto-registering .ttf fonts from the Ultralytics user config directory for stronger multilingual rendering.
• EXIF auto-rotation fix for list-of-path sources 🔄🖼️
  • Applies ImageOps.exif_transpose() when loading images from lists of paths/URLs, reducing “sideways phone photo” issues.
• Validation/metrics correctness fix (important for accuracy reporting) 🎯📈
  • Fixes SciPy-based matching (match_predictions) to maximize IoU during assignment (previously could choose the worst matches), which can affect TP/FP classification and mAP when use_scipy=True.
• IMX (Sony IMX500) export improvements 📦🤖
  • Enables IMX export on Linux ARM64 (removes an ARM64 block), adds dependency support, and improves test gating.
  • Adds segmentation as a supported IMX export/benchmark task ✅
• Usability improvement: Results.save() 💾📁
  • Adds create_dir parameter (default True) to control auto-creation of parent directories when saving annotated outputs.
• Dev/CI reliability updates 🧪🏗️
  • CI now tests newer PyTorch versions (2.8/2.9) and makes export tests less flaky by skipping TFLite export tests unless torch>=1.13 on Linux.

🎯 Purpose & Impact

• More “it just works” image input 🖼️✅
  • HEIC/HEIF (common on iPhones) can be used directly for training/inference with fewer manual conversions, while lazy loading avoids paying the dependency cost unless you actually need it.
• Fewer confusing orientation bugs 📱➡️🖥️
  • EXIF transpose handling reduces rotated/sideways images that can break visualization, training data review, and inference outputs.
• More trustworthy evaluation metrics 📈🧠
  • The IoU matching fix ensures SciPy-based evaluation behaves as intended, preventing artificially worse results or incorrect TP/FP assignment when that path is enabled.
• Better edge/export support on ARM 🧩🚀
  • IMX export on ARM64 + segmentation support expands deployment options for embedded and edge workflows.
• Smoother workflows & sharing outputs 💾✨
  • Results.save(create_dir=True) makes saving predictions into new folders simpler (fewer “directory not found” errors).
• Improved global documentation and plots 🈶📚
  • Better multilingual font defaults help teams with non‑Latin labels produce clearer charts/figures.

If you’re deploying/training with mixed photo sources (phones, HEIC libraries, multilingual labels), 8.4.15 is a practical upgrade 🛠️🚀

What's Changed

• Add guide on customizing the YOLO trainer by @raimbekovm in #23579
• Add YOLO26 vs YOLO11 performance charts for Raspberry Pi 5 by @lakshanthad in #23625
• test: 🧪 Add TFLite export requirement for Torch version 1.13 by @onuralpszr in #23618
• Fix typos and grammar errors in documentation by @him2him2 in #23617
• feat: improve Results.save() with pathlib and optional directory creation by @ShuaiLYU in #23592
• fix: 🐞 add ExecuTorch version during model export into logging by @onuralpszr in #23620
• ci: 👷 move Conda Builds CI to monitor from conda-forge/ultralytics-feedstock to ultralytics repo by @onuralpszr in #23600
• Add https://youtu.be/GAFlmuk0fZI to docs by @RizwanMunawar in #23624
• Apply EXIF transpose when list of paths is used as source by @Y-T-G in #23631
• Fix scipy matching in match_predictions to maximize IoU by @Mr-Neutr0n in #23634
• Enable IMX export for ARM64 by @lakshanthad in #23636
• Enable segmentation models in IMX benchmarks by @lakshanthad in #23635
• Fix: get the correct package name for metadata.distribution by @Laughing-q in #23641
• docs: 📝 update hyperlink for hyperparameter tuning in custom trainer guide by @onuralpszr in #23644
• Fix broken YOLO26 documentation link in vision-eye guide by @raimbekovm in #23646
• Fix docstrings by @glenn-jocher in #23648
• docs: 📝 fix conda badge link in CI documentation by @onuralpszr in #23661
• docs: 📝 remove unneeded tokenizer_ve documentation file by @onuralpszr in #23662
• Delete orphan markdown files in build_reference.py by @glenn-jocher in #23666
• docs: 📝 remove non-existed dataset generation section from COCO12-Formats documentation by @onuralpszr in #23667
• Simplify CustomSaveTrainer example in custom trainer guide by @raimbekovm in #23668
• Add custom trainer guide cross-reference in train.md by @raimbekovm in #23649
• Add PyTorch 2.8 and 2.9 tests to slow CI by @Y-T-G in #23683
• Update platform docs by @glenn-jocher in #23688
• Update Platform docs by @glenn-jocher in #23692
• Added max concurrency 16 to link checker workflow for the HTTP/2 error by @banica-ultralytics in #23690
• Add https://youtu.be/pJLXmhyuHzA to docs by @RizwanMunawar in #23658
• Platform Docs screenshots by @sergiuwaxmann in #23697
• Add https://youtu.be/cxU5E2SkivU to docs by @RizwanMunawar in #23701
• Update platform API docs by @glenn-jocher in #23704
• Platform Rate Limit docs by @glenn-jocher in #23706
• Fix uv conflicts between export and solutions extras by @fcakyon in #23686
• Add YOLOE agnostic_nms default behavior note by @raimbekovm in #23707
• Document CUDA OOM auto-retry in batch-size settings by @raimbekovm in #23708
• Document Results.save() automatic directory creation by @raimbekovm in #23709
• Banica ultralytics http2 changes undone by @banica-ultralytics in #23712
• ultralytics 8.4.15 HEIC/HEIF image support by @glenn-jocher in #23714

New Contributors

• @him2him2 made their first contribution in #23617
• @banica-ultralytics made their first contribution in #23690

Full Changelog: v8.4.14...v8.4.15