UNet Root & Nematode Semantic Segmentation Model
This repository contains weights, performance curves, and hyperparameter logs for experiment unet-nematode-256_run_2026-06-27_18-49.
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: root)
- Training Resolution:
256x256 - 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-reported0.865
- Best Val Damage-Class IoUself-reported0.721
- Best Val Root-Class IoUself-reported0.878