app.py

import gradio as gr
import tensorflow as tf
from tensorflow.keras.preprocessing import image
import numpy as np
import pickle

# Load model and class indices
model = tf.keras.models.load_model("rice_disease_detector.h5")
with open("class_indices.pkl", "rb") as f:
    class_indices = pickle.load(f)
class_names = list(class_indices.keys())

def predict_rice_disease(img):
    img = img.resize((224, 224))
    img_array = image.img_to_array(img) / 255.0
    img_array = np.expand_dims(img_array, axis=0)
    predictions = model.predict(img_array)[0]  # shape: (num_classes,)
    
    # Map class names to confidence scores
    confidence_scores = {class_names[i]: float(f"{predictions[i]:.4f}") for i in range(len(class_names))}
    
    return confidence_scores

iface = gr.Interface(
    fn=predict_rice_disease,
    inputs=gr.Image(type="pil"),
    outputs=gr.Label(num_top_classes=len(class_names)),  # shows all class scores nicely
    title="Rice Disease Classifier"
)

iface.launch()