Original DETR with a ResNet-50 backbone (41.5M parameters, 42.0 box AP on
COCO val2017 in the upstream model zoo), repackaged for
LibreYOLO.
1from libreyolo import LibreYOLO
2
3model = LibreYOLO("LibreDETRr50.pt")
4results = model.predict("image.jpg")
LibreYOLO ships this family for inference and validation, plus ONNX and
TorchScript export. Training is not implemented. The deployment contract uses
a fixed 800x800 canvas; upstream COCO evaluation instead preserves aspect ratio
with a short side of 800 and a long side capped at 1333.
Derived from the official
facebookresearch/detr checkpoint
detr-r50-e632da11.pth
at commit
29901c51d7fe8712168b8d0d64351170bc0f83e0.
Copyright (c) Facebook, Inc. and its affiliates. Licensed under the Apache
License 2.0.
Checkpoint metadata wrap only. Learned parameter names and tensors are
unchanged. See
weights/convert_detr_weights.py in the
LibreYOLO source repository.
Strict state-dict loading succeeds with no missing or unexpected keys. Against
the pinned upstream implementation, identical input tensors produce exact
FP32 outputs (max_abs_diff == 0.0) for both pred_logits and pred_boxes.
LibreYOLO maps the sparse COCO category ids to its contiguous 80-class public
interface and does not apply NMS.
Apache License 2.0. See the
LICENSE and
NOTICE
files in this repository.
