TTA COCO FasterRCNN R50
Faster R-CNN ResNet-50-FPN trained on COCO (91-class id space), re-hosted for the TTA-Evaluation-Harness as the two-stage detection source model (sibling of WNJXYK/TTA-COCO-DETR-R50).
Model source
- Kind
- Other
- File size
- 160 MB
- Version
- vRevision 9c0297a
- Updated
- Sep 16, 2026
- Downloads
- 0
- Source
- Hugging Face
Source description
TTA-COCO-FasterRCNN-R50
Faster R-CNN ResNet-50-FPN trained on COCO (91-class id space), re-hosted for the
TTA-Evaluation-Harness as the two-stage detection source model (sibling of
WNJXYK/TTA-COCO-DETR-R50).
model.safetensors is the torchvision fasterrcnn_resnet50_fpn COCO state_dict
(FasterRCNN_ResNet50_FPN_Weights.DEFAULT, Apache-2.0). The harness loads it into
a real-BatchNorm2d backbone (weights_backbone=None, strict=False) so BN-based
test-time adaptation has a genuine adaptation surface. Pinned by revision: v1.0.
Sources
1 source
Sources
1 sourceVerified Sep 2
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: apache-2.0 tags: - object-detection - test-time-adaptation - faster-rcnn - coco --- # TTA-COCO-FasterRCNN-R50 Faster R-CNN ResNet-50-FPN trained on COCO (91-class id space), re-hosted for the TTA-Evaluation-Harness as the two-stage detection source model (sibling of `WNJXYK/TTA-COCO-DETR-R50`). `model.safetensors` is the torchvision `fasterrcnn_resnet50_fpn` COCO `state_dict` (`FasterRCNN_ResNet50_FPN_Weights.DEFAULT`, Apache-2.0). The harness loads it into a real-`BatchNorm2d` backbone (`weights_backbone=None`, `strict=False`) so BN-based test-time adaptation has a genuine adaptation surface. Pinned by `revision: v1.0`.
Source context: 0 downloads · 0 likes · Pipeline object-detection · Repo WNJXYK/TTA-COCO-FasterRCNN-R50
