ultralytics 8.4.94

v8.4.94 - Remove TorchScript mobile optimization (#25140)

on Python PyPI

🌟 Summary

🚀 Ultralytics 8.4.94 modernizes deployment, improves validation and tracking reliability, and expands edge-device and dataset documentation.

📊 Key Changes

• TorchScript mobile optimization removed 🛠️

  • Removed the deprecated PyTorch Mobile/XNNPACK optimization path and the TorchScript optimize argument.
  • Regular TorchScript export remains available for legacy C++ and LibTorch applications.
  • Mobile deployments are now directed to ExecuTorch, PyTorch’s supported successor for mobile and edge inference.
  • The optimize argument is retained for DEEPX exports only.

• New Ambarella CVflow deployment guide 📷

  • Added a preview workflow for deploying YOLO models on Ambarella SoCs such as CV72 and CV75.
  • Documents SpongeTorch compression-aware training, ONNX export, offline CVflow compilation, AmbaPB inference, and host-side validation.
  • The guide is clearly marked as an early preview and requires Ambarella’s proprietary SDK and toolchain.

• Improved semantic segmentation dataset support 🧩

  • Expanded and corrected documentation for ADE20K, Cityscapes, and Cityscapes8.
  • Clarified manual download requirements, dataset sizes, test-set limitations, licensing, class mappings, and benchmark usage.
  • Semantic segmentation can now automatically detect a root-level masks/ directory when selecting PNG-mask data.
  • Added guidance for using polygon labels and Smart annotation through Ultralytics Platform.

• Dataset configuration validation strengthened ✅

  • Dataset fraction must now be greater than zero, preventing empty training datasets caused by fraction=0.
  • Other fractional settings, such as dropout and scale, continue to allow zero.

• Pose26 training loss corrected 🎯

  • Fixed loss selection when Pose26 models run with end-to-end mode disabled.
  • This ensures keypoint decoding and training loss remain aligned across Pose and Pose26 model heads.

• ReID tracking made more robust 🔍

  • Invalid or empty detection crops are now skipped instead of causing crashes.
  • Original detection ordering is preserved, with missing appearance features represented as None so trackers can fall back to motion or IoU association.

• LVIS downloads reduced 💾

  • Removed the unused 7 GB test2017.zip download because LVIS does not define a test split.
  • Updated the documented total download size to 20.7 GB.

• Documentation and CI cleanup 📚

  • Added an Ambarella integration entry and refreshed deployment guidance.
  • Removed outdated CI table entries and redundant YAML terminology.
  • Added more dataset provenance, annotation, licensing, and usage notes.

🎯 Purpose & Impact

• 📱 More future-proof mobile deployment: Users targeting new mobile or edge applications should migrate from TorchScript Mobile to ExecuTorch. Existing C++ TorchScript workflows continue to work, but mobile optimization through optimize=True is no longer supported.
• ⚙️ Cleaner export behavior: Removing obsolete mobile branches and guards reduces maintenance complexity and avoids relying on deprecated PyTorch APIs.
• 🚀 Broader edge hardware coverage: Ambarella users now have a documented path from YOLO training to compressed, compiled CVflow models, although the integration remains experimental and vendor verification is pending.
• 🛡️ Fewer runtime failures: Invalid dataset fractions, incorrect Pose26 loss selection, and empty ReID crops are detected or handled more safely.
• 📉 Lower setup overhead for LVIS: Fresh LVIS users avoid downloading an unnecessary 7 GB archive.
• 📖 Clearer, more accurate documentation: Dataset limitations, licensing requirements, manual downloads, and semantic segmentation behavior are now easier to understand and less likely to cause setup or evaluation mistakes.

What's Changed

• Add Ambarella export guide by @lakshanthad in #25077
• Remove stale CI table entries by @glenn-jocher in #25137
• Reject zero dataset fractions by @glenn-jocher in #25141
• Refactor semantic dataset docs by @raimbekovm in #25134
• Fix Pose26 loss selection when end2end=False by @synml in #25132
• Fix ReID crash for invalid custom detection crops by @anshulll19 in #25135
• Add additional notes to dog-pose, hand keypoints, and tiger-pose entries in pose dataset index by @raimbekovm in #25144
• Stop lvis.yaml from downloading the unused test2017.zip archive by @raimbekovm in #25143
• Drop incorrect YAML expansion from dataset docs by @raimbekovm in #25142
• Remove TorchScript mobile optimization by @glenn-jocher in #25140

New Contributors

• @anshulll19 made their first contribution in #25135
• @synml made their first contribution in #25132

Full Changelog: v8.4.93...v8.4.94