You can deploy this model and start earning money today!

LibreYOLO/
LibreRTMDetm-seg

Name: LibreRTMDetm-seg
Availability: InStock

libreyolo

object-detection

instance-segmentation

rtmdet

mmdetection

apache-2.0

Views

No views yet

LibreRTMDetm-seg

RTMDet-Ins-m COCO instance segmenter, repackaged for the LibreYOLO framework.

Source

Derived from https://github.com/open-mmlab/mmdetection at commit cfd5d3a985b0249de009b67d04f37263e11cdf3d and upstream checkpoint:

https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet-ins_m_8xb32-300e_coco/rtmdet-ins_m_8xb32-300e_coco_20221123_001039-6eba602e.pth

(SHA-256 6eba602e5fb98ee993cffb1724bd6d51d2e86a69f261147f405e5582ad0098c1).

Modifications

EMA weights were selected from the upstream checkpoint. data_preprocessor.* and batch-tracking buffers were omitted, bbox_head. keys were renamed to head., and the loaded state dict was saved with LibreYOLO checkpoint metadata schema v1.0 (task=segment). Learned model parameters are otherwise preserved.

Validation

Evaluated with LibreYOLO on full COCO val2017 (5000 images) at imgsz=640, conf=0.001, next to the official mmdetection references:

Metric	LibreYOLO	Official
COCO val2017 mask mAP50-95	0.4208	42.1
COCO val2017 box mAP50-95	0.4881	48.8
SHA256	`bd0c615739c58a3fcbfb783c927ecfae57f0aa55c0d5ecded1e4b0fa996acb7f`

Usage

python

from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTMDetm-seg.pt")
res = model.predict("image.jpg")
res.masks      # instance masks
res.boxes      # boxes, scores, classes

License

Apache License 2.0. See the LICENSE and NOTICE files in this repository.

LibreYOLO/LibreRTMDetm-seg