PlantVillage Disease Detection Models

Multi-phase training pipeline for plant disease detection using the PlantVillage dataset.

Training Phases

  • Phase 1: Multiclass classification (38 classes) - full dataset
  • Phase 2: Balanced multiclass - class imbalance correction
  • Phase 3: Binary classification (healthy vs diseased)

Architectures Tested

50+ architectures including ViT, ResNet, EfficientNet, MobileNet, ConvNeXt, Swin, DeiT, and more.

Results

See individual phase directories for model weights, plots, and metrics.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support