metadata
language: en
license: mit
tags:
- semantic-segmentation
- pytorch
- unet
- resnet34
- agricultural-cv
model-index:
- name: unet_run_2026-06-25_17-20
results:
- task:
type: semantic-segmentation
name: Corm Segmentation
metrics:
- type: mean_iou
value: 0.9353266318454168
name: Best Val Mean IoU
- type: mean_accuracy
value: 0.9690303641731419
name: Best Val Mean Accuracy
UNet Corm & Damage Semantic Segmentation Model
This repository contains the weights, performance logs, and hyperparameters for experiment unet_run_2026-06-25_17-20.
Model Hyperparameters
- 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:
{image_size}{image_size}
Training Configurations
- Batch Size: 8
- Optimizers / Lr: AdamW / 0.0001
- Maximum Epochs: 60
- Seed Configuration: 42
Metrics Curves
Below are the training performance plots generated for this run:
