fidoptFCBFormer
FCBFormer, a PVTv2 transformer branch fused with a fully convolutional branch, with its authors' Kvasir-SEG model, run as their predict.py runs it: 352 x 352, the logits kept above 0.
SegmentationCPUversion FCBFormer c353199, FCBFormer_Kvasir.pt (sha256 e0ef52cc), PVTv2-B3 (sha256 48b51a06)ENDOSCOPYApache-2.0 (code); weights: no licence stated
Run it
With its KonfAI app, at the benchmark's settings (the fidopt app repositories are private for now: a Hugging Face token with access opens them):
pip install konfai-apps konfai-apps infer fideus-labs/fidopt-segmentation:FCBFormer -i image.nii.gz -o out
The app on Hugging Face: its model, its settings and how it is scored.
Results
| Dataset | # | Read by | Score | Failed | Time s |
|---|---|---|---|---|---|
| Kvasir-SEG, colonoscopy polyps outlined by hand | Dice | 0.935 | 0 | 16 |
- Reference
- Sanderson and Matuszewski, MIUA 2022