Detr Resnet 50
> Carion et al., 2020 — End-to-End Object Detection with Transformers (arXiv:2005.12872)
Fonte do modelo
- Tipo
- Object detector
- Tamanho do arquivo
- 159 MB
- Versão
- vRevision e242bef
- Atualizado
- 3 de out. de 2026
- Publicador
- @lucid-dl
- Downloads
- 0
- Tarefas
- Detecção de objetos
- Fonte
- Hugging Face
Descrição da fonte
DETR (ResNet-50)
Carion et al., 2020 — End-to-End Object Detection with Transformers (arXiv:2005.12872)
Lucid port of facebookresearch/detr/detr_resnet50,
converted to Lucid-native safetensors.
Available weights
| Tag | box mAP | Params | GFLOPs | Size | Source |
|---|---|---|---|---|---|
COCO_2017 (default) | 42.0 | 41.5M | — | 158.86 MB | facebookresearch |
Usage
import lucid.models as models
from lucid.models.weights import DETRResNet50Weights
# default tag
model = models.detr_resnet50(pretrained=True)
# explicit tag (enum or string)
model = models.detr_resnet50(weights=DETRResNet50Weights.COCO_2017)
model = models.detr_resnet50(pretrained="COCO_2017")
# preprocessing travels with the weights
weights = DETRResNet50Weights.COCO_2017
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 facebookresearch/detr/detr_resnet50 via
python -m tools.convert_weights detr_resnet50 --tag COCO_2017.
Key mapping + numerical parity verified against the source.
License
apache-2.0 — inherited from the original weights.
Citation
@inproceedings{carion2020detr,
title={End-to-End Object Detection with Transformers},
author={Carion, Nicolas and Massa, Francisco and Synnaeve, Gabriel and Usunier, Nicolas and Kirillov, Alexander and Zagoruyko, Sergey},
booktitle={European Conference on Computer Vision (ECCV)},
year={2020}
}
Fontes
1 fonte
Fontes
1 fonteVerificado 3 de out.
Artefatos de modelo
1 artefato
Artefatos de modelo
1 artefatoTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- library_name: lucid license: apache-2.0 tags: - object-detection - detr - lucid datasets: - coco pipeline_tag: object-detection model-index: - name: detr-resnet50 results: - task: { type: object-detection } dataset: { name: COCO, type: coco } metrics: - { type: box mAP, value: 42.0 } --- # DETR (ResNet-50) > Carion et al., 2020 — *End-to-End Object Detection with Transformers* (arXiv:2005.12872) [Lucid](https://github.com/ChanLumerico/lucid) port of `facebookresearch/detr/detr_resnet50`, converted to Lucid-native safetensors. ## Available weights | Tag | box mAP | Params | GFLOPs | Size | Source | |---|---|---|---|---|---| | `COCO_2017` *(default)* | 42.0 | 41.5M | — | 158.86 MB | facebookresearch | ## Usage ```python import lucid.models as models from lucid.models.weights import DETRResNet50Weights # default tag model = models.detr_resnet50(pretrained=True) # explicit tag (enum or string) model = models.detr_resnet50(weights=DETRResNet50Weights.COCO_2017) model = models.detr_resnet50(pretrained="COCO_2017") # preprocessing travels with the weights weights = DETRResNet50Weights.COCO_2017 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 `facebookresearch/detr/detr_resnet50` via `python -m tools.convert_weights detr_resnet50 --tag COCO_2017`. Key mapping + numerical parity verified against the source. ## License `apache-2.0` — inherited from the original weights. ## Citation ``` @inproceedings{carion2020detr, title={End-to-End Object Detection with Transformers}, author={Carion, Nicolas and Massa, Francisco and Synnaeve, Gabriel and Usunier, Nicolas and Kirillov, Alexander and Zagoruyko, Sergey}, booktitle={European Conference on Computer Vision (ECCV)}, year={2020} } ```
Source context: 0 downloads · 0 likes · Pipeline object-detection · Library lucid · Repo lucid-dl/detr-resnet-50
Source context: 0 downloads · 0 likes · Pipeline object-detection · Library lucid · Repo lucid-dl/detr-resnet-50
