LibreRTMDetx-seg

RTMDet-Ins-x 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_x_8xb16-300e_coco/rtmdet-ins_x_8xb16-300e_coco_20221124_111313-33d4595b.pth (SHA-256 33d4595b3be83358b5187c0e9473aac6fb5d441f523fc2bdccb955121b77cfd7).

Copyright (c) 2018-2023 OpenMMLab. Licensed under the Apache License, Version 2.0.

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 0.4461 44.6
COCO val2017 box mAP50-95 0.5243 52.4
SHA256 2870367a886c344de867e7c8f885b76aece9911bace8c1997f34947d5f43e592

Usage

from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTMDetx-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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support