ultralytics 8.4.109

v8.4.109 - Log GFLOPs at the training `imgsz` (#25483)

on Python PyPI

🌟 Summary

📊 v8.4.109 improves profiling accuracy, export reliability, inference efficiency, tracking stability, and Ultralytics Platform integrations—led by correctly reporting GFLOPs for the actual training image size.

📊 Key Changes

• Accurate GFLOPs logging at training resolution 🎯

  • model_info_for_loggers() now passes the trainer’s actual imgsz to FLOPs profiling.
  • Logging integrations—including W&B, Comet, ClearML, DVC, Neptune, HUB, and Platform—no longer report the default 640-pixel GFLOPs for every run.
  • Classification and other models with size-independent operations also receive more accurate measurements through the updated ultralytics-thop dependency.

• Improved model fusion and profiling ⚙️

  • model.fuse() now accepts an imgsz argument so reported model information matches the intended input resolution.
  • Export workflows pass the export image size during fusion and profiling.

• More reliable INT8 calibration 📦

  • Classification exports now honor the fraction setting when selecting calibration images.
  • OpenVINO INT8 calibration uses the complete requested calibration dataset instead of silently limiting calibration to NNCF’s default 300 batches.

• Faster and more efficient mask plotting 🖼️

  • Removed an unused GPU image construction and unnecessary tensor allocations.
  • Mask rendering now avoids redundant resizing and host-to-device transfers, reducing memory use and plotting overhead.

• Inference warmup now uses the real input shape 🔥

  • Predictors warm up using the first preprocessed input rather than a fixed square dummy image.
  • This better supports rectangular images, tensor sources, dynamic shapes, and shape-specialized backends.

• Training recovery behavior made safer 🛡️

  • Healthy runs are no longer stopped simply because an early validation fitness value rounds to zero.
  • Recovery remains enabled for genuine NaN or infinite loss and fitness values.

• Tracking and numerical stability improvements 🚦

  • ReID embeddings are consistently processed as float32 for more dependable association decisions.
  • Embedding-distance calculations use the appropriate dtype precision.
  • macOS tracking workflows avoid spurious NumPy warnings and can run faster during covariance updates.

• Heatmap and validation performance improvements 📈

  • Heatmap regions are drawn once per frame, preventing flicker when no objects are tracked and avoiding repeated work.
  • Confusion-matrix matching replaces repeated array scans with direct lookups.

• Expanded Ultralytics Platform documentation and integrations 🌐

  • Added Labelbox import documentation, including direct NDJSON upload workflows.
  • Added coming-soon documentation for CVAT and Label Studio integrations, with supported YOLO export paths available today.
  • Updated Cityscapes guidance and removed broken Platform dataset links.
  • For dataset annotation, training, and deployment, users can use Ultralytics Platform.

• System and CI maintenance 🧰

  • Removed stale persistent CPU-name caching and the macOS subprocess probe.
  • CI now tests newer OpenVINO Conda packages and uses actions/stale@v11.
  • Cleaned up augmentation documentation image sizing for consistent rendering.

🎯 Purpose & Impact

• ✅ More trustworthy experiment tracking: GFLOPs now reflect the resolution actually used for training or export, making model comparisons and resource estimates more meaningful.
• 🚀 Better deployment preparation: INT8 calibration respects user-selected data limits and OpenVINO can use the full requested calibration set, potentially improving quantization quality.
• ⚡ Lower inference and visualization overhead: Real-shape warmup and optimized mask plotting can reduce first-inference delays, memory use, and unnecessary computation.
• 🛡️ Fewer unexpected failures: Valid early-stage training runs are less likely to be incorrectly treated as corrupted, while real numerical failures still trigger recovery.
• 🎥 More stable tracking outputs: ReID precision and macOS matrix-operation fixes improve consistency and reduce distracting runtime warnings.
• 🌍 Simpler dataset workflows: New Platform integration guidance helps users move data from labeling tools into annotation, training, and deployment workflows with fewer conversion steps.

What's Changed

• Remove discarded im_gpu build and reduce mask plotting allocations by @onuralpszr in #25454
• Bump actions/stale from 10 to 11 in /.github/workflows by @dependabot[bot] in #25471
• Remove OpenVINO version constraint in conda CI environment by @onuralpszr in #24366
• Add Labelbox, CVAT, and Label Studio Platform integration docs by @glenn-jocher in #25464
• Fix stale cached CPU name and remove the subprocess probe by @glenn-jocher in #25478
• Remove broken Platform links by @raimbekovm in #25479
• Fit the size-independent term in get_flops by @JESUSROYETH in #25468
• Draw the Heatmap counting region once per frame instead of once per object by @JESUSROYETH in #25467
• Replace the per-object array scans in ConfusionMatrix.process_batch with a lookup by @JESUSROYETH in #25466
• Fix INT8 export calibration ignoring fraction for classify models by @synml in #25469
• Calibrate OpenVINO INT8 on the full dataset instead of nncf's 300-batch default by @synml in #25470
• Preserve embedding distance dtype by @raimbekovm in #25482
• Pin float32 when stacking TrackTrack ReID embeddings by @raimbekovm in #25475
• Keep the gmc covariance warp operand c-contiguous by @raimbekovm in #25473
• Drop hand-tuned image widths from the augmentation guide tables by @raimbekovm in #25472
• Warm up the predictor on the real input shape by @glenn-jocher in #25477
• Stop killing healthy runs on fitness collapse; stop orphaned console capture by @glenn-jocher in #25486
• Log GFLOPs at the training imgsz by @JESUSROYETH in #25483

Full Changelog: v8.4.108...v8.4.109