- Регистрация
- 9 Май 2015
- Сообщения
- 1,483
- Баллы
- 155

? Sharing my end-to-end ML project: Krishi Rakshak — a crop disease classifier built with efficientnet_b0 for smallholder farmers.

90%+ accuracy on PlantVillage (38 classes)
Trained with AdamW, scheduler, early stopping
Used weighted loss to handle class imbalance
? Evaluation:
Manual metric validation + confusion matrix
Precision, recall, F1, per-class accuracy
? Deployment:
PyTorch + Gradio UI, multilingual support
Designed for light, modular inference
? GitHub:
? Demo:
Built independently from scratch — feedback welcome from ML/AgriTech community on optimization or scaling for noisy field data.
Источник: