Kvasir Unet Scratch
This is a custom U-Net built from scratch for polyp segmentation in endoscopic images.
Source du modèle
- Type
- Other
- Taille du fichier
- 1,86 MB
- Version
- vRevision f3cd397
- Mis à jour
- 27 sept. 2026
- Téléchargements
- 12
- Tâches
- Segmentation d'image
- Source
- Hugging Face
Description de la source
Kvasir-SEG Custom U-Net
This is a custom U-Net built from scratch for polyp segmentation in endoscopic images.
Model Details
- Architecture: 4-layer U-Net with BatchNorm and Dropout2d.
- Loss Function: Focal + Dice Loss (So the Network sees the small polyps)
- Resolution: Trained on 256x256 images.
- Data Augmentations: Spatial augmentations and color variation
Performance
- Validation IoU: 0.463803
Sources
1 source
Sources
1 sourceVérifié 27 sept.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: mit tags: - pytorch - image-segmentation - medical - kvasir-seg --- # Kvasir-SEG Custom U-Net This is a custom U-Net built from scratch for polyp segmentation in endoscopic images. ## Model Details * **Architecture:** 4-layer U-Net with BatchNorm and Dropout2d. * **Loss Function:** Focal + Dice Loss (So the Network sees the small polyps) * **Resolution:** Trained on 256x256 images. * **Data Augmentations:** Spatial augmentations and color variation ## Performance * **Validation IoU:** 0.463803
Source context: 12 downloads · 0 likes · Pipeline image-segmentation · Repo Shushunya/kvasir-unet-scratch
