---
license: bsd-3-clause
library_name: libreyolo
pipeline_tag: object-detection
datasets:
  - detection-datasets/coco
tags:
  - object-detection
  - retinanet
  - torchvision
  - libreyolo
---

# LibreRetinaNetr50

RetinaNet (ResNet-50 FPN v1 with FrozenBatchNorm), repackaged for LibreYOLO. This is an
inference-only model with 34,014,999 parameters.

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreRetinaNetr50.pt")
results = model.predict("image.jpg")
```

## Source

Derived from [pytorch/vision](https://github.com/pytorch/vision) at commit
[`336d36e8db990a905498c73933e35231876e28bc`](https://github.com/pytorch/vision/commit/336d36e8db990a905498c73933e35231876e28bc).
Copyright (c) Soumith Chintala 2016 and torchvision contributors. The source
implementation is BSD-3-Clause.

Official checkpoint: [retinanet_resnet50_fpn_coco-eeacb38b.pth](https://download.pytorch.org/models/retinanet_resnet50_fpn_coco-eeacb38b.pth)

- Official file bytes: 136595076
- Official SHA-256: `eeacb38b7cec8cf93c57867e05eaab621047f19b0d2ec5accaa405f690da15b7`
- Converted file bytes: 136594812
- Converted SHA-256: `a2b9d711f531bbee88eff659d11ca263792491060fa6fe0ab957541b63f12051`
- Published COCO val2017 box mAP: 36.4

## Model contract

- Input: RGB image, normalized with ImageNet mean/std.
- Resize: short side 800, long side capped at 1333, then bottom/right padding
  to a multiple of 32.
- Output: contiguous COCO-80 boxes, scores, and class ids after per-level
  candidate selection and class-aware NMS.
- Training: not implemented in LibreYOLO; `train()` raises.
- Export: dynamic-spatial, batch-one ONNX is validated.

## Modifications

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](https://github.com/LibreYOLO/libreyolo).

## License

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`](./LICENSE) and [`NOTICE`](./NOTICE).