New Release: Ultralytics v8.3.193

Ultralytics v8.3.193 Released :rocket:

Quick summary: v8.3.193 brings faster long-video and large-batch inference via automatic TorchVision NMS, a unified checkpoint loading API, and cleaner progress bars with smarter rate scaling. You’ll also see absolute save paths in logs, more stable exports, better PyTorch version handling, and improved segmentation validation. Perfect for day-to-day workflows across CLI and Ultralytics HUB. :bullseye:

Highlights

  • :high_voltage: Automatic TorchVision NMS for long-sequence inference (videos, streams, large image sets) — no action needed.
  • :counterclockwise_arrows_button: Unified load_checkpoint API used across the codebase for simpler, consistent model loading.
  • :chart_increasing: Cleaner, faster TQDM progress bars with human-friendly rate units and improved completion display.
  • :card_index_dividers: Absolute save paths in logs for unambiguous run tracking.
  • :locked: Stable exports with onnxslim==0.1.65 pin.
  • :toolbox: Robust PyTorch version handling.
  • :test_tube: More accurate segmentation validation.

Tip: If you parse exact progress bar strings, please update your tooling due to the new TQDM formatting. :writing_hand:

New Features

  • Long-sequence inference optimization in PR #21926 by @Laughing-q

    • Automatically preloads torchvision to trigger TorchVision-based NMS on streams, screenshots, >1000 images, or any video.
    • Warnings are now targeted and shown only when not in stream mode.
  • Unified checkpoint loading API in PR #21933 by @glenn-jocher

    • Replaces attempt_load_one_weight/attempt_load_weights with a single load_checkpoint function.
    • Docs updated to reference ultralytics.nn.tasks.load_checkpoint.

Minimal example:

from ultralytics.nn.tasks import load_checkpoint

model, ckpt = load_checkpoint("yolo11n.pt", device="cpu", fuse=False)

Improvements

Bug Fixes

Try It

  • Upgrade:
    • pip install -U ultralytics
  • Quick test with YOLO11:
    • CLI: yolo predict model=yolo11n.pt source=video.mp4
    • Python:
      from ultralytics import YOLO
      
      model = YOLO("yolo11n.pt")
      model.predict(source="video.mp4")
      

YOLO11 is the latest stable and recommended Ultralytics YOLO model for all use cases.

What’s Changed (PRs and Authors)

New Contributor

  • Big thanks to first-time contributor @samrere! :raising_hands:

Links

Feedback

We’d love your feedback and benchmarks—especially on long videos, streams, and large image batches. If you spot anything, please open a discussion or PR. Thanks to the YOLO community and the Ultralytics team for making this possible!