[dependabot]

Bumps ultralytics from 8.4.137 to 8.4.164.

Release notes

Sourced from ultralytics's releases.

v8.4.164 - Delegate FLOPs counting to THOP 2.2.0 stride profiling (#26373)

🌟 Summary

v8.4.164 makes FLOPs reporting more efficient and improves export, video inference, dataset validation, and reliability—without changing model architectures or predictions.

📊 Key Changes

• Faster FLOPs counting (PR #26373): Delegates FLOPs estimation to THOP 2.2.0, which supports attention operations and profiles at smaller strides. This replaces full-size profiling for attention-based models such as YOLO11, YOLO12, and YOLO26, as well as RT-DETR. The PR depends on ultralytics-thop 2.2.0.
• More efficient exports: CoreML export skips redundant trace checking, with reported trace times around 2.8–3× faster. The exporter also removes a duplicate setup forward pass.
• Improved video prediction: CUDA prediction can prefetch video frames while the GPU processes the current batch. Batches now stay within one video, also fixing an FPS mix-up when processing videos with different frame rates.
• More reliable data handling: Dataset scans now catch malformed OBB labels and fractional class IDs earlier. They also accept pose datasets for detection training and correctly parse multi-row prediction CSV files.
• Bug fixes and stability: Fixes include memory growth in PIL-based annotation, cleanup when prediction streams end early, tracker callbacks affecting plain prediction, and YOLOv9 distillation across different head layouts.
• Clearer deployment guidance: Documentation adds and updates guidance for Core AI, Rust inference options, export formats, datasets, and deployment workflows.

🎯 Purpose & Impact

• Less overhead when checking model information or starting training: FLOPs reporting no longer needs a full-resolution forward pass for the affected models, which can make model.info() and training startup logging lighter.
• Faster and smoother deployment workflows: Export setup does less redundant work, and CUDA video prediction can overlap frame loading with GPU inference.
• Earlier, clearer feedback on dataset problems: Invalid labels are more likely to produce helpful errors during scanning rather than confusing failures later in training or validation.
• More dependable runs: Fixes reduce resource leaks, incorrect tracker behavior, and failures in distillation and prediction-source handling.

What's Changed

• Ride out PyPI outages when publishing and alert Slack once by @​glenn-jocher in ultralytics/ultralytics#26340
• Speed up CoreML export by disabling redundant trace checking by @​amanharshx in ultralytics/ultralytics#26337
• Update Platform docs to 21 export formats by @​glenn-jocher in ultralytics/ultralytics#26344
• Update ultralytics-inference version to 0.0.48 and add quantize in documentation by @​onuralpszr in ultralytics/ultralytics#26345
• Fix memory growth in Annotator(pil=True) from a font reference cycle by @​Y-T-G in ultralytics/ultralytics#26346
• Return early from segment2box for segments fully outside the image by @​raimbekovm in ultralytics/ultralytics#26331
• Document Core AI export on Linux and Platform, and 409 on duplicate resource names by @​raimbekovm in ultralytics/ultralytics#26343
• Reject box-only labels for OBB datasets at load time like segment datasets by @​Nicholas022400701 in ultralytics/ultralytics#26330
• Run the exporter dry-run forward pass once by @​amanharshx in ultralytics/ultralytics#26334
• Keep the checkpoint dataset on resume and omit host paths from the export validate hint by @​raimbekovm in ultralytics/ultralytics#26335
• Prefetch video frames during CUDA prediction by @​JESUSROYETH in ultralytics/ultralytics#26349
• Restore Conv.default_act after parse_model overrides it by @​cainiao33 in ultralytics/ultralytics#26347
• Release prediction writers and sources when stream runs end early by @​cainiao33 in ultralytics/ultralytics#26348
• Fix YOLOv9 distillation across teacher and student head layouts by @​Nikhi00718 in ultralytics/ultralytics#26338
• Fix multi-row CSV prediction sources by @​Nikhi00718 in ultralytics/ultralytics#26360
• Fix tracker callbacks running during plain prediction by @​aswanth-07 in ultralytics/ultralytics#26352
• Drop the keypoints in verify_image_label so a detect task can train on a pose dataset by @​Nicholas022400701 in ultralytics/ultralytics#26357
• Isolate Jetson CI settings per runner by @​glenn-jocher in ultralytics/ultralytics#26366
• Apply format-specific export options for mixed-case and alias formats by @​MohammadHijjawi97 in ultralytics/ultralytics#26358
• Join bracketed CLI values after '=' merging in merge_equals_args by @​MohammadHijjawi97 in ultralytics/ultralytics#26365
• Route tar-family dataset download URLs through safe_download by @​cainiao33 in ultralytics/ultralytics#26361
• Remove unused labels autolabel path from non_max_suppression by @​cainiao33 in ultralytics/ultralytics#26356
• Fix ObjectCropper crash with OBB models by @​MohammadHijjawi97 in ultralytics/ultralytics#26359
• 86% faster SAM batched_mask_to_box on CPU by @​Y-T-G in ultralytics/ultralytics#26364
• Fix valid .jp2 images dropped as corrupt in dataset scans by @​cainiao33 in ultralytics/ultralytics#26355
• Reduce Jetson CI time and cancel superseded hardware runs by @​glenn-jocher in ultralytics/ultralytics#26369
• Re-derive teacher feature indices when unpickling distillation checkpoints by @​cainiao33 in ultralytics/ultralytics#26362
• Reject fractional class IDs during dataset scans by @​Nikhi00718 in ultralytics/ultralytics#26367
• Fix docstrings, export docs/args, and bugs found in a full package audit by @​glenn-jocher in ultralytics/ultralytics#26370
• Fix stale TensorRT INT8 calibration cache reuse by @​amanharshx in ultralytics/ultralytics#26368
• Add lite, openapi, and skills to CI status table by @​glenn-jocher in ultralytics/ultralytics#26372

... (truncated)

Commits

• 9540b31 Delegate FLOPs counting to THOP 2.2.0 stride profiling (#26373)
• 0d90972 Auto-select idle GPUs at DDP launch in test_train (#26374)
• 48773b7 Add lite, openapi, and skills to CI status table (#26372)
• b5d3626 Fix stale TensorRT INT8 calibration cache reuse (#26368)
• 889b4fd Fix docstrings, export docs/args, and bugs found in a full package audit (#26...
• cb0be7c Reject fractional class IDs during dataset scans (#26367)
• d96475b Re-derive teacher feature indices when unpickling distillation checkpoints (#...
• 5eaa5ee Reduce Jetson CI time and cancel superseded hardware runs (#26369)
• cb8b5e6 Fix valid .jp2 images dropped as corrupt in dataset scans (#26355)
• 96ee3ef 86% faster SAM batched_mask_to_box on CPU (#26364)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)