YOLOv3 (Darknet-53)
Redmon & Farhadi, 2018 — YOLOv3: An Incremental Improvement (arXiv:1804.02767)
Lucid port of darknet/yolov3.weights,
converted to Lucid-native safetensors.
Available weights
| Tag | mAP@0.5 | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|
COCO_2014 (default) | 55.3 | 61.9M | — | 236.57 MB | darknet |
Usage
import lucid.models as models
from lucid.models.weights import YOLOV3Weights
# default tag
model = models.yolo_v3(pretrained=True)
# explicit tag (enum or string)
model = models.yolo_v3(weights=YOLOV3Weights.COCO_2014)
model = models.yolo_v3(pretrained="COCO_2014")
# preprocessing travels with the weights
weights = YOLOV3Weights.COCO_2014
preprocess = weights.transforms()
out = model(preprocess(image)[None])
# ObjectDetectionOutput: per-query/proposal class logits + boxes
logits, boxes = out.logits, out.pred_boxes
Conversion
Converted from darknet/yolov3.weights via
python -m tools.convert_weights yolo_v3 --tag COCO_2014.
Key mapping + numerical parity verified against the source.
License
other — inherited from the original weights.
Citation
@article{redmon2018yolov3,
title={YOLOv3: An Incremental Improvement},
author={Redmon, Joseph and Farhadi, Ali},
journal={arXiv preprint arXiv:1804.02767},
year={2018}
}