AgriMali-EfficientNetV2

AgriMali is an AI-powered agricultural assistant designed to help farmers in Mali 🇲🇱 by providing instant diagnosis for plant diseases.

Overview

This model is based on the EfficientNetV2-S architecture. It has been fine-tuned to classify plant diseases with high accuracy, ensuring robustness and efficiency for mobile-based field applications.

Performance Metrics

The model has been validated on a high-quality dataset, achieving the following results:

Metric	Value
Validation Accuracy	98.48%
Macro F1-Score	97.99%
Macro AUC	99.98%

How to use

You can easily load this model in your Python application using the huggingface_hub library:

from huggingface_hub import hf_hub_download
import torch

# Download the model weights
model_path = hf_hub_download(repo_id="Abouba1810/AgriMali-EfficientNetV2", filename="agrimali_best.pth")

# Initialize the model architecture (AgriMaliNet)
model = AgriMaliNet(num_classes=38) 

# Load the weights
model.load_state_dict(torch.load(model_path, map_location='cpu'))
model.eval()