Ultralytics v8.3.237 is live!
TL;DR: v8.3.237 brings full SAM 3 image + video segmentation support (including text + exemplar prompts and tracking), improves export reliability (notably ONNX FP16 on CPU plus cleaner Edge TPU/IMX dependencies), and adds several training/validation + docs quality-of-life upgrades. ![]()
![]()
![]()
Upgrade any time with pip install -U ultralytics and let us know what you build!
New Features: SAM 3 (Image + Video) Integration
Ultralytics now supports SAM 3 end-to-end across interactive + semantic (concept) segmentation, plus video tracking:
-
New SAM 3 model builder stack- New
build_sam3.pyand SAM 3 modules (ViT backbone, encoder/decoder, text + geometry encoders, video tracker). - The SAM entrypoint now detects
sam3.ptand routes builds viabuild_interactive_sam3.
- New
-
New SAM 3 predictors & public APIsSAM3Predictor– interactive segmentationSAM3SemanticPredictor– text + exemplar concept segmentation on imagesSAM3VideoPredictor– video tracking with box promptsSAM3VideoSemanticPredictor– video concept tracking (text + boxes + masklets)- Integrated into SAM’s
task_map, soSAM("sam3.pt")routes automatically to the correct predictor.
-
Docs upgraded from preview → real usage- SAM 3 reference docs added for modules under
docs/en/reference/models/sam/sam3/*. docs/en/models/sam-3.mdrewritten with concrete examples and important setup notes:- SAM 3 weights are not auto-downloaded (you must fetch
sam3.ptfrom the official repo). - Text prompts require the BPE vocab file (
bpe_simple_vocab_16e6.txt.gz).
- SAM 3 weights are not auto-downloaded (you must fetch
- SAM 3 reference docs added for modules under
For more, see the SAM 3 integration PR by @Laughing-q in PR #22897.
Improvements: Export & Device Tooling
ONNX FP16 export on CPU
ONNX export now supports half=True on CPU, converting weights to FP16 and gracefully warning/falling back if conversion fails (instead of aborting).
Implemented by @glenn-jocher in PR #22927.
Edge TPU & IMX export dependency management
Export tooling is now more robust on Debian/Ubuntu-based systems:
- Edge TPU export now uses centralized
check_apt_requirements(["edgetpu-compiler"]) - IMX export uses
check_apt_requirements()for appropriate Java packages check_apt_requirements()now runsapt updatewithcheck=Trueso failures surface clearly
Implemented by @lakshanthad in PR #22925.
Training & Experiment Quality-of-Life
More flexible resume-training overrides
Resuming training now allows overriding more runtime/logging options without restarting:
save_period, workers, cache, patience, time, freeze, val, plots.
Data augmentation docs: scale range clarified
Docs updated to clarify scale should be 0.0 - 1.0, avoiding unstable configs.
Updated by @Y-T-G in PR #22907.
Validation & Visualization Fixes
RT-DETR validation scaling fix
Validation transforms simplified and scaling behavior made explicit/safe via a no-op scale_preds() override.
OBB plotting robustness
OBBValidator.plot_predictions() is now more robust (handles empty predictions cleanly, avoids redundant conversions, uses plot_images() directly).
Fixed by @onuralpszr in PR #22765.
Quick Try
pip install -U ultralytics
from ultralytics import SAM
model = SAM("sam3.pt") # ensure you've downloaded sam3.pt manually
results = model("image.jpg")
Release + Changelog
Dive into the release details in the v8.3.237 release page, or browse all commits in the full changelog comparison.
Feedback welcome!
If you try SAM 3 (especially text prompts or video concept tracking) or the updated export paths, please share:
- your platform (OS / CPU / GPU)
- the command or snippet you used
- any logs or minimal repro steps if something looks off
Your feedback helps keep Ultralytics YOLO and the broader community ecosystem moving fast.