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

# LibreFasterRCNNs

Modernized Faster R-CNN (MobileNetV3-Large FPN variant), repackaged for LibreYOLO.
This is a torchvision COCO recipe, not the original 2015 VGG16 architecture.

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreFasterRCNNs.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: [fasterrcnn_mobilenet_v3_large_fpn-fb6a3cc7.pth](https://download.pytorch.org/models/fasterrcnn_mobilenet_v3_large_fpn-fb6a3cc7.pth)
SHA-256: `fb6a3cc702b1df54c18a44b26708cd083614211062d0c36d2ca7bf9270df3533`
Published COCO val2017 box mAP: 32.8.

## Modifications

Checkpoint metadata was added for LibreYOLO's v1.0 schema. Learned tensors and
state-dict keys are unchanged. The native LibreYOLO graph loads the official
state dict strictly and has exact eager parity at the RPN head, RoI predictor,
and final detections. See `weights/convert_faster_rcnn_weights.py` in the
[LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo).

## Benchmarks

Independent accuracy and speed benchmarks:
[visionanalysis.org/model/faster_rcnn-s](https://www.visionanalysis.org/model/faster_rcnn-s)

## 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).