LibreRTMDett Seg

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:

Usage

from libreyolo import LibreYOLO

model = LibreYOLO("LibreRTMDett-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.

--- license: apache-2.0 library_name: libreyolo tags: - object-detection - instance-segmentation - rtmdet - mmdetection --- # LibreRTMDett-seg RTMDet-Ins-tiny COCO instance segmenter, repackaged for the [LibreYOLO](https://github.com/LibreYOLO/libreyolo) framework. ## Source Derived from [https://github.com/open-mmlab/mmdetection](https://github.com/open-mmlab/mmdetection) at commit `cfd5d3a985b0249de009b67d04f37263e11cdf3d` and upstream checkpoint: `https://download.openmmlab.com/mmdetection/v3.0/rtmdet/rtmdet-ins_tiny_8xb32-300e_coco/rtmdet-ins_tiny_8xb32-300e_coco_20221130_151727-ec670f7e.pth` (SHA-256 `ec670f7ee9e20bd7931e15f15b7016f7fe531baaab81f2e6153382d046111885`). 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 | 0.3538 | 35.4 | | COCO val2017 box mAP50-95 | 0.4049 | 40.5 | | SHA256 | `55c387ce50424e9bf1816b59f6eff7ec1ea9455db35049be46f946670c18d775` | | ## Usage ```python from libreyolo import LibreYOLO model = LibreYOLO("LibreRTMDett-seg.pt") res = model.predict("image.jpg") res.masks # instance masks res.boxes # boxes, scores, classes ``` ## License Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files in this repository.