Kvasir Unet Scratch
This is a custom U-Net built from scratch for polyp segmentation in endoscopic images.
Model source
- Kind
- Other
- File size
- 1.86 MB
- Version
- vRevision f3cd397
- Updated
- Sep 27, 2026
- Downloads
- 12
- Tasks
- Image segmentation
- Source
- Hugging Face
Source description
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 sourceVerified Sep 27
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- 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
