Mask R-CNN with a ResNet-50-FPN v2 backbone, repackaged for LibreYOLO. The
checkpoint supports instance segmentation by default and box-only detection
with task="detect".
1from libreyolo import LibreYOLO
2
3model = LibreYOLO("LibreMaskRCNNr50.pt")
4result = model.predict("image.jpg")
5print(result.boxes.xyxy, result.masks.data)
Derived from
pytorch/vision at commit
336d36e8db990a905498c73933e35231876e28bc.
Copyright (c) Soumith Chintala 2016 and torchvision contributors. The source
implementation is BSD-3-Clause.
LibreYOLO checkpoint metadata was added. Learned tensors and state-dict keys
are unchanged. The native graph loads the official state dict strictly and has
exact eager parity at the RPN head, box head, final boxes, raw mask logits, and
full-image masks. The batch-1 opset-18 ONNX graph is also covered by ONNX
Runtime parity. See
weights/convert_mask_rcnn_weights.py in the
LibreYOLO source repository.
The checkpoint publisher did not attach a separate per-object license file.
This mirror applies the releasing project's BSD-3-Clause license on an
implied, not publisher-confirmed, basis. Torchvision warns that pretrained
models may have their own licenses or terms derived from training data and
that users must determine whether they have permission for their use case.
COCO annotations are CC BY 4.0; source images retain their individual Flickr
terms. See
LICENSE and
NOTICE.
