fix(deps): update dependency ultralytics ( 8.4.90 → 8.4.92 ) - #451

v8.4.92: - Fix RKNN INT8 multi-batch export (#​25094)

Compare Source

🌟 Summary

Ultralytics v8.4.92 improves RKNN INT8 multi-batch export reliability, strengthens inference and dataset validation, and expands YOLO26 documentation for web deployment. 🚀

📊 Key Changes

• 🔧 Fixed RKNN INT8 multi-batch export (PR #​25094, @​glenn-jocher)

  • RKNN calibration now uses a batch-1 ONNX graph, while the requested inference batch is passed to RKNN Toolkit through rknn_batch_size.
  • Resolves export failures when using configurations such as batch=8.
  • Adds regression coverage to verify that calibration and runtime batch handling remain correct.

• ⚡ Improved compiled model predictor reuse (PR #​25092, @​glenn-jocher)

  • Predictor initialization now explicitly checks whether the model is None.
  • Prevents torch.compile model wrappers from triggering unsupported truth-value checks during repeated inference.

• ✅ More accurate validation split handling (PR #​25093, @​glenn-jocher)

  • Dataset validation now checks the split requested by the user, such as val or test, instead of always checking val.
  • Missing or unavailable splits now produce a clear error rather than silently using another split.

• 📦 More reliable polygon-to-box conversion (PR #​25086, @​JESUSROYETH)

  • segment2box() now preserves the visible portion of polygons that cross image boundaries.
  • Improves bounding boxes after perspective and other augmentations, reducing shrunken or collapsed boxes.

• 🌐 Expanded LiteRT web deployment documentation (PR #​25087, @​onuralpszr)

  • Documents browser and Node.js inference with LiteRT.js and the official @ultralytics/yolo NPM package.
  • Includes WebGPU acceleration with CPU/WASM fallback and support for all six YOLO26 tasks.
  • Installation is documented with npm i @​ultralytics/yolo @​litertjs/core.

• 📚 Refreshed pose dataset documentation

  • Corrects dataset sizes, splits, keypoint details, and download requirements for COCO-Pose, COCO8-Pose, Dog-Pose, Hand Keypoints, and Tiger-Pose.
  • Adds clearer guidance for using Ultralytics Platform to annotate and train custom pose datasets.
  • Clarifies that COCO-Pose requires approximately 27 GB for its complete first download.

• 🔐 Simplified contributor license workflow

  • Replaces the third-party CLA action with the shared ultralytics/actions workflow.
  • Reduces duplicated configuration and limits workflow permissions.

🎯 Purpose & Impact

• Rockchip users can export INT8 models with larger inference batches more reliably, especially for edge deployments using RKNN hardware. 🧩
• Compiled models are safer to reuse across multiple predictions, improving stability for optimized inference workflows.
• Dataset validation errors are clearer and more trustworthy, helping users catch incorrect or missing test or val data earlier.
• Augmented segmentation data retains correct object extents, which can improve training labels and downstream detection quality near image borders.
• YOLO26 deployment is easier in browsers, enabling serverless webcam, image, and real-time inference through WebGPU or CPU/WASM fallback. 🌍
• Pose estimation documentation is more accurate and practical, making dataset selection, download planning, and training setup easier for both new and experienced users.

What's Changed

• Replace third-party CLA action by @​glenn-jocher in #​25084
• docs: 📝 Update LiteRT documentation to include Web deployment details and npm package installation by @​onuralpszr in #​25087
• Fix compiled model predictor reuse by @​glenn-jocher in #​25092
• Validate requested detection dataset split by @​glenn-jocher in #​25093
• Fix segment2box shrinking boxes when augmented polygons cross image bounds by @​JESUSROYETH in #​25086
• Refactor pose dataset docs by @​raimbekovm in #​25062
• Fix RKNN INT8 multi-batch export by @​glenn-jocher in #​25094

Full Changelog: ultralytics/ultralytics@v8.4.91...v8.4.92

v8.4.91: - Exclude Sigmoid/Softmax from TensorRT INT8 quantization (#​25020)

Compare Source

🌟 Summary

Ultralytics v8.4.91 improves YOLO26 deployment quality—especially TensorRT INT8 confidence calibration—while adding stronger automated CLI fuzz testing, better export reliability, and many training/inference bug fixes 🚀

📊 Key Changes

• Improved TensorRT INT8 exports for YOLO26 confidence scores ⚡

  • Excludes the Sigmoid operation from INT8 quantization in TensorRT export paths.
  • Applies higher precision for Sigmoid across TensorRT 7 through TensorRT 11+ using the appropriate backend mechanisms.
  • Adds GPU export test coverage for static INT8 detection exports.

• Added daily YOLO CLI fuzz testing 🧪

  • Introduces a new Monte Carlo fuzzing workflow for the yolo CLI across train, export, predict, validation, and chaos-style command variations.
  • Automatically classifies failures, confirms reproducible issues, deduplicates findings, and can file GitHub issues for confirmed bugs.

• Improved ONNX INT8 export reliability 🔧

  • ONNX INT8 quantization now focuses only on weighted operations such as Conv, Gemm, and MatMul.
  • INT8 ONNX exports are capped to a compatible opset to avoid unsupported ONNX Runtime static quantization paths.

• Better pretrained fine-tuning behavior 🎯

  • Adds class-name-based remapping for pretrained detection heads when fine-tuning on datasets with reordered or partially matching class names.
  • Helps transfer learned weights more accurately instead of relying only on class index order.

• Multiple inference, validation, and tracking fixes ✅

  • Fixes track() crashes caused by CPU/GPU tensor mismatches when using exported models with the default tracker.
  • Fixes classes filtering being applied after max_det truncation for end-to-end NMS models, which could return too few or zero detections.
  • Fixes pose validation save_txt=True keypoint scaling so saved keypoints correctly align with original image coordinates.
  • Fixes several Ultralytics Solutions crashes with OBB models, including Heatmap and ObjectBlurrer.

• Improved support for non-RGB and custom-channel workflows 🌈

  • Fixes knowledge distillation warmup for grayscale and other non-3-channel datasets.
  • Fixes TensorBoard graph logging for multispectral or custom-channel training.
  • Fixes classification transforms so custom interpolation is respected for non-square image sizes.

• Export and platform reliability improvements 🧩

  • Edge TPU compiler failures now raise clear errors instead of returning corrupt stub files.
  • ExecuTorch and ARM export dependencies are pinned more safely to avoid upstream Torch compatibility breakage.
  • Version comparison logic now handles 4-part package versions like 4.13.0.90 correctly.
  • Windows OpenVINO CI coverage is kept while limiting CPU instruction dispatch for more stable tests.

• Documentation refreshes 📚

  • Large updates to classification, detection, and OBB dataset docs with verified image counts, split details, clearer usage examples, and better dataset descriptions.
  • Adds or updates YOLO26 tutorial videos, including semantic segmentation documentation.
  • Clarifies Ultralytics Platform data residency details and improves Hailo docs formatting.

• CI and Docker workflow hardening 🐳

  • Codecov uploads are now best-effort, so external reporting outages do not fail otherwise successful test jobs.
  • Docker validation containers are auto-removed and test assets are pre-cached before running tests.

🎯 Purpose & Impact

• More accurate TensorRT INT8 confidence calibration 📈

  • Keeping Sigmoid at higher precision helps prevent confidence-score compression in YOLO26 TensorRT INT8 exports.
  • This can improve F1 calibration and reduce deployment surprises for users relying on INT8 acceleration.

• More reliable production exports 🚀

  • ONNX, TensorRT, Edge TPU, ExecuTorch, OpenVINO, and ARM-related fixes reduce export failures and make deployment behavior clearer across platforms.

• Fewer silent or confusing failures 🛡️

  • Invalid CLI/config values, failed Edge TPU compilers, unsupported dependency combinations, and broken tracking/device paths are now handled more robustly.

• Better results when fine-tuning custom datasets 🎓

  • Class-name-aware head remapping helps users reuse pretrained models more effectively when dataset class order differs from the original model.

• Stronger support for specialized vision data 🛰️

  • Grayscale, multispectral, OBB, pose, and custom-channel workflows receive important fixes, helping users working beyond standard RGB detection.

• Higher long-term stability through fuzzing 🧪

  • The new scheduled CLI fuzz workflow should uncover edge-case bugs that normal test matrices miss, improving future release quality for both developers and end users.

• Clearer learning and dataset guidance 📖

  • Refreshed docs make it easier to choose datasets, understand dataset structure, train YOLO26 models, and use Ultralytics Platform for annotation, training, and deployment.

What's Changed

• Use text fence for hailortcli device output in Hailo docs by @​glenn-jocher in #​25041
• Fix track() device mismatch with exported models under the default tracktrack tracker by @​JESUSROYETH in #​25042
• Add https://youtu.be/_fvGA9LPXzs to docs by @​raimbekovm in #​25048
• Fix classify_transforms ignoring interpolation for non-square sizes by @​ahmet-f-gumustas in #​25047
• Fix crashes on invalid copy_paste_mode and optimizer values by @​glenn-jocher in #​25052
• Update data region warning with additional details by @​sokrisba in #​25050
• Fix classes filter applied after max_det truncation in end-to-end NMS by @​JESUSROYETH in #​25043
• Remap pretrained cls head by class name when fine-tuning by @​Y-T-G in #​25051
• Quantize only weighted ops for ONNX INT8 by @​Y-T-G in #​25046
• Fix Heatmap, ObjectBlurrer and other solutions crash with OBB models by @​JESUSROYETH in #​25058
• Fix save_txt keypoint scaling in PoseValidator by @​JESUSROYETH in #​25053
• Fix incorrect bin indexing in plt_color_scatter by @​dorianboille in #​25064
• Refactor OBB dataset documentation by @​raimbekovm in #​25061
• Refactor classification dataset documentation by @​raimbekovm in #​25003
• Refactor detect dataset documentation by @​raimbekovm in #​25013
• Fix ExecuTorch ARM torch compatibility by @​glenn-jocher in #​25069
• Reject None for typed CLI defaults by @​glenn-jocher in #​25070
• Raise Edge TPU compiler failures instead of returning corrupt stub by @​glenn-jocher in #​25068
• Bump onnx from 1.21.0 to 1.22.0 in /examples/RTDETR-ONNXRuntime-Python in the pip group across 1 directory by @​dependabot[bot] in #​25071
• Skip OpenVINO inference on Windows CI by @​glenn-jocher in #​25072
• Keep Windows OpenVINO inference tests by @​glenn-jocher in #​25073
• Make Codecov uploads best effort by @​glenn-jocher in #​25075
• Fix DistillationModel warmup for single-channel datasets by @​JESUSROYETH in #​25067
• Pre-cache Docker test assets by @​glenn-jocher in #​25074
• Fix Tensorboard logging with multi-spectral training by @​Y-T-G in #​25076
• Fix version comparisons for 4-segment pins like opencv-python!=4.13.0.90 by @​glenn-jocher in #​25079
• Pin ARM export torch below 2.13 by @​glenn-jocher in #​25080
• Add Fuzz workflow: daily Monte Carlo fuzzing of the yolo CLI by @​glenn-jocher in #​25049
• Handle v-prefixed versions in check_version by @​glenn-jocher in #​25083
• Exclude Sigmoid/Softmax from TensorRT INT8 quantization by @​davidnichols-ops in #​25020

New Contributors

• @​sokrisba made their first contribution in #​25050
• @​davidnichols-ops made their first contribution in #​25020
• @​dorianboille made their first contribution in #​25064

Full Changelog: ultralytics/ultralytics@v8.4.90...v8.4.91