ultralytics 8.4.42

v8.4.42 - `ultralytics 8.4.42` Free tensors before OOM batch retry (#24360)

on Python PyPI

🌟 Summary

Ultralytics v8.4.42 focuses on more reliable training under GPU memory pressure 🧠💪, plus several stability, security, export, and documentation improvements that make YOLO workflows smoother for both developers and end users.

📊 Key Changes

• Top priority (current PR #24360 by @glenn-jocher): Better OOM recovery during training 🚀

  • When CUDA runs out of memory in early training, temporary tensors (batch, loss, preds) and trainer loss state are now explicitly cleared before retry.
  • Existing auto-batch retry behavior is preserved (no workflow changes for users).

• Security hardening in downloads and path handling 🔐

  • Safer archive extraction now blocks unsafe zip/tar paths and risky members.
  • Safer URL/URI-derived file handling to prevent unsafe path traversal patterns.
  • Replaced unsafe parsing behavior in CUDA test logic and improved related safeguards.

• Export pipeline refactor + reliability fixes 📦

  • Export dependency setup moved from central exporter into per-format modules (cleaner architecture, easier maintenance).
  • CoreML export now skips unnecessary proxy model loading to avoid export crashes on some Apple Silicon setups.
  • Added a new guide for exporting non-YOLO PyTorch models (timm/torchvision/custom) to multiple targets.

• Backend usability improvement ✨

  • Backends can now be called directly like model(x) instead of only model.forward(x).

• Bug fixes affecting real workflows 🛠️

  • Fixed dataset/image loading when folder names contain square brackets (e.g. ./[data]/).
  • Fixed hyperparameter tuning checkpoint copying for multi-dataset runs.
  • Fixed plot_results() crash path when CSV plotting fails.
  • Added safety check for YOLOE head fusion when one2many branches are absent.

• Platform and docs improvements 📚

  • Platform API docs now clearly document segmentation label payloads using segments (not polygon).
  • Jetson guide adds practical memory optimization tips (headless mode, service trimming, show=False, profiling).
  • Updated Axelera integration to stable SDK 1.6.0.
  • Broader docs cleanup: onboarding/order fixes, activity feed path fixes, updated tutorial videos, annotation links, and removed outdated API endpoints.

🎯 Purpose & Impact

• Fewer failed training runs on limited VRAM 🎯
  The main v8.4.42 change helps training recover more reliably from first-epoch OOM events, reducing frustrating restarts.

• Safer defaults for file and dataset handling 🛡️
  Security-focused path and extraction checks reduce risk when working with external files and archives.

• More dependable exports across formats 🌍
  Export refactors and CoreML fixes improve cross-platform conversion stability, especially for deployment-heavy teams.

• Better developer ergonomics 👩‍💻
  Callable backends, cleaner export internals, and bug fixes in tuning/plotting/path-loading improve everyday productivity.

• Clearer onboarding and learning resources for all users 🙌
  Improved docs (including Ultralytics Platform guidance and Jetson memory tips) make setup and adoption easier for newcomers while still useful for advanced users.

What's Changed

• Add https://youtu.be/m-Lc5MXbydg to docs by @RizwanMunawar in #24294
• Document Platform segment label payloads by @glenn-jocher in #24296
• Update Axelera SDK to 1.6.0 with YOLO classifier fix by @tamrobb in #24278
• docs: 📝 Add memory optimization tips for NVIDIA Jetson devices by @onuralpszr in #24299
• Bump slackapi/slack-github-action from v3.0.1 to v3.0.2 in /.github/workflows by @UltralyticsAssistant in #24309
• Add guide for exporting non-YOLO PyTorch models by @raimbekovm in #24277
• Add https://youtu.be/hsimB10D6Y0 & https://youtu.be/BpSuXSUzEYY to docs by @RizwanMunawar in #24308
• fix(coreml): skip proxy load during export by @amanharshx in #24312
• Remove drifting GPU heuristic table from platform quickstart by @raimbekovm in #24303
• Added banner to licensing section by @matt-ultralytics in #24295
• Correct activity feed access paths on platform by @raimbekovm in #24288
• Correct platform onboarding step order and final step by @raimbekovm in #24289
• Remove ghost API endpoints from platform docs by @mykolaxboiko in #24111
• Fix missing weights copy in hyperparameter tuning iterations by @Laughing-q in #24196
• Bump conda-incubator/setup-miniconda from 3 to 4 in /.github/workflows by @dependabot[bot] in #24319
• Add __call__ wrapper for BaseBackend.forward method by @Laughing-q in #24311
• Set conda workflow permissions by @glenn-jocher in #24317
• add ultralytics.com/annotate link to docs pages by @raimbekovm in #24340
• Remove redundant .keys() call in dict membership test by @tempoo04 in #24339
• Fix Snyk code security findings by @glenn-jocher in #24342
• Fix undefined ax variable in plot_results by @Y-T-G in #24345
• Fix lychee install workflow by @glenn-jocher in #24347
• Fix: FileNotFoundError when loading datasets from paths containing square brackets by @prashansapkota in #24353
• YOLOE: check one2many head exists while fusing prompt embeddings by @Y-T-G in #24359
• Refactor: move export package requirements from exporter.py into per-format utility modules by @lakshanthad in #24245
• ultralytics 8.4.42 Free tensors before OOM batch retry by @glenn-jocher in #24360

New Contributors

• @prashansapkota made their first contribution in #24353
• @tempoo04 made their first contribution in #24339
• @tamrobb made their first contribution in #24278

Full Changelog: v8.4.41...v8.4.42