UNet Corm & Damage Semantic Segmentation Model
This repository contains weights, performance curves, and hyperparameter logs for experiment unet_run_2026-06-26_20-47.
Model Summary
- Architecture Type: UNet (SMP wrapper)
- Backbone Encoder:
resnet34 - Pretrained Weights:
imagenet - Input Channels: 3
- Number of Classes: 3 (0: background, 1: damage, 2: corm)
- Training Resolution:
1024x1024 - Loss Optimizer configuration:
CrossEntropy
Metrics Curves
Below are the training performance plots generated for this run:
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Evaluation results
- Best Val Mean IoUself-reported0.940
- Best Val Damage-Class IoUself-reported0.854
- Best Val Corm-Class IoUself-reported0.967