U-Net for Gastrointestinal Polyp Segmentation

Binary segmentation model trained on the Kvasir-SEG dataset for polyp detection in gastrointestinal endoscopy images.

Also available: 3-class multi-class variant — 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

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.safetensors"))
model.eval()

# input: (B, 3, 256, 256) float tensor in [0, 1]
# output: (B, 1, 256, 256) logits — apply sigmoid + threshold for mask

Or download from Hub:

from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from model import UNet

weights = hf_hub_download(
    repo_id="sebastiao-teixeira/week04-polyp-segmentation-unet",
    filename="model.safetensors",
)
model = UNet(in_channels=3, num_classes=1)
model.load_state_dict(load_file(weights))
model.eval()
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
31.1M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support