Skip to content
ModelListedExternal
Download

Faster Rcnn Resnet 50 Fpn

> Ren et al., 2015 — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497)

KindOtherVersionRevision 73a82eb

Model source

Kind
Other
File size
160 MB
Version
vRevision 73a82eb
Updated
Sep 16, 2026
Downloads
0
Tasks
Object detection
Source
Hugging Face

Source description

Faster R-CNN (ResNet-50-FPN)

Ren et al., 2015 — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497)

Lucid port of torchvision/FasterRCNN_ResNet50_FPN_Weights.COCO_V1, converted to Lucid-native safetensors.

Available weights

Tagbox mAPParamsGFLOPsSizeSource
COCO_V1 (default)37.041.8M134.38159.72 MBtorchvision

Usage

import lucid.models as models
from lucid.models.weights import FasterRCNNResNet50FPNWeights

# default tag
model = models.faster_rcnn_resnet50_fpn(pretrained=True)

# explicit tag (enum or string)
model = models.faster_rcnn_resnet50_fpn(weights=FasterRCNNResNet50FPNWeights.COCO_V1)
model = models.faster_rcnn_resnet50_fpn(pretrained="COCO_V1")

# preprocessing travels with the weights
weights = FasterRCNNResNet50FPNWeights.COCO_V1
preprocess = weights.transforms()
out = model(preprocess(image)[None])
# ObjectDetectionOutput: per-query/proposal class logits + boxes
logits, boxes = out.logits, out.pred_boxes

Conversion

Converted from torchvision/FasterRCNN_ResNet50_FPN_Weights.COCO_V1 via python -m tools.convert_weights faster_rcnn_resnet50_fpn --tag COCO_V1. Key mapping + numerical parity verified against the source.

License

bsd-3-clause — inherited from the original weights.

Citation

@inproceedings{ren2015faster,
  title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks},
  author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2015}
}

Sources

1 source
Hugging FacePrimaryVersion 73a82ebd8a933497cac0dca0c61fc321810677cb
huggingface.co/lucid-dl/faster-rcnn-resnet-50-fpn/tree/73a82ebd8a933497cac0dca0c61fc321810677cb

Verified Sep 16

Model artifacts

1 artifact

COCO_V1/model.safetensors

safetensors · 160 MB · SHA-256 cc8d2c79125d…3205 · Hugging Face

Download

Source excerpts

2 excerpts

--- library_name: lucid license: bsd-3-clause tags: - object-detection - faster - lucid datasets: - coco pipeline_tag: object-detection model-index: - name: faster-rcnn-resnet50-fpn results: - task: { type: object-detection } dataset: { name: COCO, type: coco } metrics: - { type: box mAP, value: 37.0 } --- # Faster R-CNN (ResNet-50-FPN) > Ren et al., 2015 — *Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks* (arXiv:1506.01497) [Lucid](https://github.com/ChanLumerico/lucid) port of `torchvision/FasterRCNN_ResNet50_FPN_Weights.COCO_V1`, converted to Lucid-native safetensors. ## Available weights | Tag | box mAP | Params | GFLOPs | Size | Source | |---|---|---|---|---|---| | `COCO_V1` *(default)* | 37.0 | 41.8M | 134.38 | 159.72 MB | torchvision | ## Usage ```python import lucid.models as models from lucid.models.weights import FasterRCNNResNet50FPNWeights # default tag model = models.faster_rcnn_resnet50_fpn(pretrained=True) # explicit tag (enum or string) model = models.faster_rcnn_resnet50_fpn(weights=FasterRCNNResNet50FPNWeights.COCO_V1) model = models.faster_rcnn_resnet50_fpn(pretrained="COCO_V1") # preprocessing travels with the weights weights = FasterRCNNResNet50FPNWeights.COCO_V1 preprocess = weights.transforms() out = model(preprocess(image)[None]) # ObjectDetectionOutput: per-query/proposal class logits + boxes logits, boxes = out.logits, out.pred_boxes ``` ## Conversion Converted from `torchvision/FasterRCNN_ResNet50_FPN_Weights.COCO_V1` via `python -m tools.convert_weights faster_rcnn_resnet50_fpn --tag COCO_V1`. Key mapping + numerical parity verified against the source. ## License `bsd-3-clause` — inherited from the original weights. ## Citation ``` @inproceedings{ren2015faster, title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks}, author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2015} } ```

Source context: 0 downloads · 0 likes · Pipeline object-detection · Library lucid · Repo lucid-dl/faster-rcnn-resnet-50-fpn