FireViewer RF-DETR Medium 1.10 strict v1
Research release of an RF-DETR Medium detector trained for smoke_visible and flame_visible.
Status
Serious validation candidate; independent frozen benchmark pending. The selected epoch-18 EMA checkpoint reports training-validation mAP50-95 0.468331, mAP50 0.734626, precision 0.755401, recall 0.649472 and F1 0.697713. These are not directly rankable against D-FINE/RT-DETR/YOLO independent scores.
Default inference candidate: checkpoint_best_total.pth. Resume checkpoint checkpoint_23.ckpt is retained for exact training continuation, not preferred serving.
Rights
RF-DETR Medium is in Roboflow's Apache-2.0 core model family. Before applying FireViewer custom checkpoint terms remotely, verify that the repository's exact upstream revision and all included files are the Apache-designated core components. Training-source rights remain separate.
Safety
This model is not a certified warning system and has not yet passed the current frozen independent FireViewer benchmark.
Reproducibility and artifact access
from huggingface_hub import hf_hub_download
path = hf_hub_download(
repo_id="fireviewer/fire-smoke-rfdetr-medium-v110-strict-v1",
repo_type="model",
revision="443ea24a73004558b288eb3b7d78d7b04cdd5cd4",
filename="checkpoint_best_total.pth",
)
Hub artifact SHA-256 for checkpoint_best_total.pth: 47f6d478baa44622ec9075dbbfd98f04a80471f808536fa7b343615f3020ca46. 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.
RF-DETR version 1.10.0, resolution 576, selected EMA at epoch 18. See training configuration, validation metrics, artifact roles and metrics.csv. The exact training-source revision must be recovered from the retained run provenance before any reproduction; this card does not invent one. The visibility: private field in the original artifact manifest is historical; current Hub metadata is public.
Evaluation boundary
The independent detector benchmark remains pending. Training-validation mAP, precision, recall and F1 are checkpoint-selection measurements, not an external ranking. An inference threshold shown in an example is not an operationally calibrated threshold. No new evaluation date or result is established by this update. Preserve the exact checkpoint, training split, grouping and source rights for the independent comparison. Human review remains required for sensitive results.
Documentation, revision and stewardship
Documentation reviewed on 19 September 2026, using the FireViewer documentation pack and the repository at 443ea24a73004558b288eb3b7d78d7b04cdd5cd4. This is a documentation and metadata check, not a new model evaluation, training run, data acquisition or full artifact verification. Historical receipts keep their original dates and identifiers; manifest hashes of earlier README versions describe those earlier releases.
The association FIRE-VIEWER provides administrative and financial stewardship for resources under its control. Technical governance is maintainer-led. Pre-association rights, UWD components, upstream licences and source-specific rights remain separate; repository placement does not transfer ownership or grant new rights.
Canonical documentation · Status vocabulary · Institutional website. Contact: contact@fire-viewer.fr.