ultralytics 8.4.96

v8.4.96 - Revert #25188 and secure NDJSON paths without a prepass (#25196)

on Python PyPI

🌟 Summary

Ultralytics v8.4.96 strengthens NDJSON dataset security and dramatically improves conversion speed, while adding YOLO26 depth deployment guidance, On Premise Platform documentation, and numerous reliability fixes. 🚀

📊 Key Changes

• 🔐 Faster and safer NDJSON conversion

  • Reverts the previous overbuilt validation approach and validates records during the existing hash scan.
  • Generates collision-free filenames from stable record indexes instead of trusting potentially unsafe source names.
  • Uses dense numeric class directories for classification datasets, while preserving original class names through a hidden metadata map.
  • Removes the extra full-dataset validation pass and avoids unnecessary path-object allocations.
  • Reported performance improves by approximately 7.8× for detection and 6.8× for classification compared with the reverted implementation.

• 📏 YOLO26 depth support in Rust inference

  • Adds depth estimation as a supported task with yolo26n-depth.onnx.
  • Supports depth visualization options such as --colormap and --depth-viz.
  • Adds Rust API examples for reading per-pixel depth maps, valid ranges, and center-pixel depth values.
  • Updates ultralytics-inference documentation to version 0.0.29.

• 🚀 New Intel deployment guide

  • Documents YOLO26 deployment with Intel DL Streamer, OpenVINO, GStreamer, and Docker.
  • Includes FP32, FP16, and INT8 export examples for Intel CPUs, GPUs, and NPUs.
  • Covers GPU/NPU inference, video output, and multi-stream processing.

• 🏢 Expanded Ultralytics Platform On Premise documentation

  • Explains how Enterprise users can connect Linux, macOS, or Windows workers.
  • Documents local dataset browsing, annotation, training, and model storage while keeping image and video pixels on the customer’s computer.
  • Adds plan metadata across Platform documentation and clarifies Enterprise capabilities.

• 🧩 Reliability and correctness fixes

  • Results.update(probs=...) now correctly wraps probabilities in Probs, restoring methods such as summary(), plot(), and exports.
  • RT-DETR standalone validation now honors single_cls and classes.
  • Keypoints and segmentation polygons remain aligned with boxes after letterbox resizing.
  • Classification confusion matrices no longer include an irrelevant background class.
  • FastSAM no longer overwrites the first detection when handling full-image boxes.
  • Segmentation loss no longer silently skips images when instances are fewer than the batch size.
  • save_one_box() now returns crops in the requested format regardless of whether the crop is saved.
  • End-to-end NMS now correctly returns original detection indexes when return_idxs=True.
  • Tracker motion compensation, trainer recovery logic, TensorBoard channel handling, YOLOE visual-prompt training, and configuration validation receive targeted fixes.

• 📚 Documentation improvements

  • Adds clearer semantic segmentation dataset guidance, including the masks/ folder fallback behavior.
  • Corrects augmentation and export argument tables and updates the tracker default to tracktrack.yaml.
  • Labels many documentation examples as text for improved rendering and readability.
  • Updates CoreML and LiteRT mobile benchmarks to include YOLO26 Depth results.

🎯 Purpose & Impact

• Safer dataset processing: Untrusted NDJSON filenames and class names can no longer control generated filesystem paths, reducing traversal and collision risks. 🛡️
• Faster large-dataset workflows: NDJSON conversion avoids redundant scans and scales much better for millions of records.
• Broader YOLO26 deployment: Users can now more easily run depth estimation on Rust, Apple, Android, and Intel hardware.
• Better production flexibility: Enterprise customers can train through the Ultralytics Platform while keeping sensitive data and compute on premise.
• More dependable APIs and results: Several fixes prevent confusing runtime errors, incorrect metrics, misaligned outputs, and silently dropped training data.
• Clearer documentation: Updated examples, defaults, benchmarks, and platform plan labels make setup and deployment easier for both new and experienced users. ✅

What's Changed

• Fix augmentation-args and export-args doc macro cells by @raimbekovm in #25163
• Document masks/-folder fallback in semantic task faq by @raimbekovm in #25161
• Fix Results.update(probs=...) to wrap probs in Probs like the other attributes by @JESUSROYETH in #25157
• Fix RT-DETR standalone val ignoring single_cls and classes by @JESUSROYETH in #25158
• Fix scale_coords letterbox pad so keypoints and mask polygons stay aligned with boxes by @JESUSROYETH in #25156
• Fix classify ConfusionMatrix gaining a phantom background class by @JESUSROYETH in #25155
• Fix stale tracker default and dropped row in object-blurring solutions table by @raimbekovm in #25170
• Document Enterprise On Premise workers by @glenn-jocher in #25167
• Use dataset channels for TensorBoard graph tracing by @Laughing-q in #25160
• Forward validation compile mode to attempt_compile by @Laughing-q in #25162
• Validate CopyPaste mode explicitly by @Laughing-q in #25168
• Add guide for deploying Ultralytics YOLO26 on Intel Core Ultra Series3 using DL Streamer and OpenVINO. by @tbujewsk in #25078
• Rewrite On Premise docs for customers by @glenn-jocher in #25174
• Fix v8SegmentationLoss silently dropping images when overlap_mask=False and instances < batch size by @JESUSROYETH in #25173
• Fix save_one_box to return the crop in the requested BGR format regardless of save by @JESUSROYETH in #25172
• Update CoreML and LiteRT mobile depth benchmarks by @glenn-jocher in #25177
• Improve Platform code example readability by @glenn-jocher in #25179
• Remove obsolete docs workflow badge by @glenn-jocher in #25180
• Fix FastSAM postprocess overwriting the first box by @JESUSROYETH in #25175
• Fix ECC camera-motion translation not rescaled after downscale in GMC by @JESUSROYETH in #25181
• Fix best_fitness falsy check and NaN recovery dead-code branches in trainer by @Zenka737 in #25176
• Fix YOLOESegModel.loss mixing text prompts into visual-prompt training by @JESUSROYETH in #25178
• Validate CLI choice arguments in config by @glenn-jocher in #25182
• Fix stale package imports in Python subprocesses by @raimbekovm in #24447
• Revert overbuilt subprocess import fix by @glenn-jocher in #25190
• Update ultralytics-inference version to 0.0.28 in rust docs by @onuralpszr in #25192
• Document the depth task in the Rust inference docs by @onuralpszr in #25193
• fix: validate NDJSON image and split output paths by @amanharshx in #25188
• Fix non_max_suppression dropping return_idxs for end-to-end models and remove dead ConfusionMatrix.matrix() method by @Zenka737 in #25187
• Fix uint8 overflow in polygons2masks_overlap dropping instances past 128 overlaps by @JESUSROYETH in #25185
• Update rust docs for the jet and disparity depth defaults and version 0.0.29 by @onuralpszr in #25195
• Revert #25188 and secure NDJSON paths without a prepass by @glenn-jocher in #25196

New Contributors

• @tbujewsk made their first contribution in #25078
• @Zenka737 made their first contribution in #25176

Full Changelog: v8.4.95...v8.4.96