DeepLabV3+ Corm & Damage Semantic Segmentation Model

Model Summary

• Architecture Type: DeepLabV3+ (SMP wrapper)
• Backbone Encoder: resnet34
• Pretrained Weights: imagenet
• Input Channels: 3
• Number of Classes: 3 (0: background, 1: damage, 2: corm)
• Training Resolution: 640x640
• Loss Optimizer configuration: Hybrid_Focal_Tversky

Metrics Curves

Below are the training performance plots generated for this run: