LibreDeformableDETRr50

LibreDeformableDETRr50

The official multi-scale ResNet-50 Deformable DETR checkpoint (44.5 AP on COCO val2017), converted for LibreYOLO.

from libreyolo import LibreYOLO

model = LibreYOLO("LibreDeformableDETRr50.pt")
results = model.predict("image.jpg")

LibreYOLO ships this museum family for inference only. Its portable deformable attention uses the upstream pure-PyTorch grid_sample reference path; the custom CUDA extension is not packaged. Native and ONNX inference use a fixed 800 x 800 PIL-bilinear stretch with ImageNet normalization. That deployment transform intentionally differs from upstream's short-side-800/max-1333 evaluation transform.

Source

Architecture derived from fundamentalvision/Deformable-DETR at commit 11169a60c33333af00a4849f1808023eba96a931. Copyright (c) 2020 SenseTime. All Rights Reserved. Modified from DETR, Copyright 2020 - present, Facebook, Inc. Licensed under Apache License 2.0.

The checkpoint comes from SenseTime/deformable-detr at revision 83ecd26945199939cb82806f988debdb71e6f43e. Source model.safetensors SHA-256: caf1e3e61283c6ce35cd2d9adaa7033cf40997d4dfe434003bcdb9085cc8cf9b.

Modifications

Checkpoint keys are remapped to the original module layout, decoder Q/K/V projections are concatenated, and serialization aliases for shared prediction heads are restored. Non-parameter BatchNorm tracking counters are omitted; learned tensor values are unchanged. The released 91-column COCO category-id head is retained and mapped to contiguous COCO-80 classes during postprocess.

The converted checkpoint SHA-256 is 1f8499d1ddf0e03e999ad4f821a68375144b814d765707df015a4373941b398b. LibreYOLO's output tensors are bit-exact against the pinned upstream pure-PyTorch path (max_abs_diff == 0.0); fixed-800 ONNX Runtime prediction parity is also verified.

See weights/convert_deformable_detr_weights.py and docs/provenance/deformable_detr.md in the LibreYOLO source repository.

License

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