RetinaNet (ResNet-50 FPN v2 with GroupNorm heads), repackaged for LibreYOLO. This is an
inference-only model with 38,198,935 parameters.
1from libreyolo import LibreYOLO
2
3model = LibreYOLO("LibreRetinaNetr50v2.pt")
4results = model.predict("image.jpg")
Derived from
pytorch/vision at commit
336d36e8db990a905498c73933e35231876e28bc.
Copyright (c) Soumith Chintala 2016 and torchvision contributors. The source
implementation is BSD-3-Clause.
Checkpoint metadata was added for LibreYOLO's v1.0 schema. Learned tensors and
state-dict keys are unchanged. The native LibreYOLO graph strictly loads the
official state dict and has exact eager parity at every FPN feature, raw head,
and final detection. See
weights/convert_retinanet_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.
