FireViewer YOLO11-M strict v1
Reproducible two-class visible smoke/flame baseline trained on the strict-clean FireViewer detection corpus.
Status
Reference baseline. Retained independent benchmark results:
| Metric |
Result |
| COCO mAP50-95 |
0.1491 |
| COCO mAP50 |
0.2784 |
| Smoke AP50-95 |
0.2790 |
| Flame AP50-95 |
0.0193 |
| Holdout precision / recall / F1 |
0.4274 / 0.2488 / 0.3145 |
| Negative-image false-alarm rate |
0.3391 |
Its weak flame AP and recall are explicitly documented; this checkpoint is retained as a reproducible iteration artifact with documented use as a local preannotation helper. It is not a qualified pointing model.
Rights
Ultralytics code and models are distributed under AGPL-3.0 unless covered by a separate Ultralytics enterprise licence. Do not add the FireViewer non-redistribution checkpoint licence to this repository unless an upstream commercial licence and rights analysis expressly support it.
Training-source rights and attribution remain separately applicable.
Reproducibility and artifact access
from huggingface_hub import hf_hub_download
path = hf_hub_download(
repo_id="fireviewer/fire-smoke-yolo11m-strict-v1",
repo_type="model",
revision="065979cd2300c27eeb355ab1e1524d8223d0b276",
filename="model.pt",
)
Hub artifact SHA-256 for model.pt: 4428ee4c17980d8f1995bbe624a593f63326ead85ec76f2f0cd480195bab2a4d. This identity was read from Hub metadata; the weights were not downloaded or rehashed during the documentation review.
The example downloads a pinned artifact; it does not execute or qualify inference. Preserve the matching configuration, labels, preprocessing and runtime dependencies from that revision. Keep raw outputs, scores, model revision and source provenance when integrating with fireviewer-vision-runtime.
Training corpus: fireviewer/fire-smoke-detection-corpus-v1 at 8e3cb52e86e15debdff7d37a3ce9eac39fbe1835 (see run receipt and source manifest). Base recipe and implementation are recorded with the training artifacts; a family name alone is not an immutable upstream revision.
The included inference helper consumes an RGB image and returns class ID/name, confidence and xyxy image boxes; its documented image size is 960. --confidence 0.25 is the helper default, not a calibrated deployment threshold.
Independent evaluation protocol and limits
Published independent report: 512 images from Hajorda/flameye-wildfire-detection, test, revision 361a3dea8b877482af9f4ed80eff77ffd39926ef. The retained common protocol uses 129 calibration images and 383 holdout images; its selection is dominated by D-Fire (508/512). Zero exact training overlap is a reported hash-based check, not proof of no semantic or domain overlap.
Evaluated model revision: a75aa44716658f02eb85b4e7bba6a358040e6f86. The report-calibrated score threshold is 0.1; it is specific to this protocol and is not an operational threshold. COCO AP over the 512-image selection and F1 on the calibrated holdout are different measurements. Do not compare them with RF-DETR training-validation scores or DINOv3 pointing metrics.
The report does not contain an explicit execution timestamp. Its original revision is the evidence reference; a documentation review date is not a new evaluation date. Multi-event and multi-camera external validation remains necessary.
Sensitive results require human validation. No image detection establishes geographic coordinates, a measured perimeter, absence of fire or future propagation.
Documentation and revision
Card updated in English on 5 October 2026, from the public repository at
065979cd2300c27eeb355ab1e1524d8223d0b276 and its retained reports.
This update checks documentation, repository metadata and small evidence files;
it does not rerun training, inference, dataset payload verification or device qualification.
Historical receipts keep their original dates, revisions and scope. Earlier README
hashes in artifact manifests refer to those earlier releases.
The association FIRE-VIEWER provides administrative and financial stewardship for
resources under its control. Technical governance is maintainer-led. Upstream,
source-specific and pre-association rights remain separate; repository placement
does not transfer ownership or grant additional rights.
Project documentation
· Institutional website. Contact: [email protected].
