import streamlit as st
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.image import img_to_array
from PIL import Image

# Charger le modèle pré-entraîné
model = load_model('plant_diseases.h5')

# Classes de labels (remplacez par vos propres classes)
class_labels = ['Piment: Bacterial_spot', 
                'Piment: healthy', 
                'Pomme de terre: Early_blight', 
                'Pomme de terre: Late_blight', 
                'Pomme de terre: Healthy', 'Tomate: Bacterial Spot', 'Tomate: Early Blight', 'Tomate: Late Blight', 'Tomate: Leaf mold', 'Tomate: Septoria leaf spot', 'Tomate: Siper mites', 'Tomate: Spot', "Tomate: Yellow Leaf Curl", 'Tomate: Virus Mosaïque', 'Tomate: Healthy']


def preprocess_image(image, image_size=(224, 224)):
    # Convertir l'image en niveaux de gris
    image = np.array(image.convert('L'))
    # Redimensionner l'image
    image = cv2.resize(image, image_size)
 
    # Redimensionner pour le modèle
    image = img_to_array(image)
    image /= 255.0
    image = np.expand_dims(image, axis=0)
    return image

st.title("Classification des Maladies des Plantes")
st.write("Téléchargez une image de plante pour la classification")

uploaded_file = st.file_uploader("Choisissez une image...", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    # Afficher l'image téléchargée
    image = Image.open(uploaded_file)
    st.image(image, caption='Image téléchargée', use_column_width=True)
    
    st.write("Classification en cours...")
    
    # Prétraiter l'image
    processed_image = preprocess_image(image)
    
    # Faire la prédiction
    predictions = model.predict(processed_image)
    probabilities = predictions[0]
    
    # Afficher les probabilités de chaque classe
    for i, label in enumerate(class_labels):
        if probabilities[i] > 0:
            st.write(f"{label}: {probabilities[i]:.2f}")

    # Afficher le résultat de la classe prédite
    predicted_class = class_labels[np.argmax(probabilities)]
    st.write(f"Classe prédite: {predicted_class}")