Week04 Polyp Segmentation Unet

--- license: mit tags: - image-segmentation - medical-imaging - polyp-segmentation - unet - pytorch datasets: - Angelou0516/kvasir-seg pipeline_tag: image-segmentation --- # U-Net for Gastrointestinal Polyp Segmentation Binary segmentation model trained on the [Kvasir-SEG](https://huggingface.co/datasets/Angelou0516/kvasir-seg) dataset for polyp detection in gastrointestinal endoscopy images. > Also available: [3-class multi-class variant](https://huggingface.co/sebastiao-teixeira/week04-polyp-segmentation-unet-multiclass) — same architecture with 3 output classes (val_dice=0.9036, test_dice=0.9169) ## Architecture Standard U-Net encoder-decoder with skip connections: - **Encoder**: 4 stages of double 3×3 conv blocks (64 → 128 → 256 → 512) with MaxPool2d downsampling, followed by a 1024-channel bottleneck. - **Decoder**: 4 stages of transposed convolution upsampling with skip concatenation and double conv blocks (512 → 256 → 128 → 64). - **Reduction head**: extra Conv2d(64→32) + BatchNorm + ReLU before the final 1×1 convolution to reduce capacity and mitigate overfitting. - **Output**: 1-channel logits (binary segmentation). - All conv blocks use BatchNorm2d + ReLU activation. - Input: 3-channel RGB, 256×256. ## Loss Function **CombinedLoss** = 0.5 × BCE + 0.5 × Dice Loss - **BCE (Binary Cross-Entropy with Logits)**: provides stable pixel-level gradients and handles class imbalance through its log-based formulation. - **Dice Loss**: directly optimizes the overlap metric (Dice coefficient), which is the standard evaluation metric for medical segmentation. BCE alone tends to underperform on imbalanced masks where background dominates. - The equal weighting balances pixel-wise accuracy (BCE) with region-level overlap (Dice). ## Training Setup | Parameter | Value | |---|---| | Epochs | 20 | | Optimizer | Adam | | Learning rate | 1e-4 | | LR scheduler | ReduceLROnPlateau (factor=0.5, patience=3, min_lr=1e-6) | | Batch size | 8 | | Image size | 256×256 | | GPU | NVIDIA GeForce RTX 3080 Ti | | Dataset splits | train=800, val=100, test=100 | ## Metrics | Split | Dice Coefficient | Loss | |---|---|---| | Validation (best) | 0.7747 | — | | Test | 0.8114 | 0.2661 | ## Usage ```python import torch from model import UNet from safetensors.torch import load_file model = UNet(in_channels=3, num_classes=1) model.load_state_dict(load_file("model.safet...