app.py

from flask import Flask, render_template, request, redirect, url_for
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
import numpy as np
import os
from PIL import Image

# Initialize the Flask app
app = Flask(__name__)

# Load trained model
MODEL_PATH = 'my_model.h5'
model = load_model(MODEL_PATH)

# List of class names (from LabelEncoder's `classes_`)
class_names = ['Acacia', 'Acer', 'Alnus', 'Anadenanthera', 'Betula', 'Celtis', 'Chamaerops', 
               'Corylus', 'Eucalyptus', 'Fagus', 'Fraxinus', 'Juglans', 'Laurus', 'Morus',
               'Pinus', 'Platanus', 'Populus', 'Quercus', 'Salix', 'Tamarix', 'Tilia', 
               'Ulmus', 'Zea']

# Home route
@app.route('/')
def index():
    return render_template('index.html')

# Predict route
@app.route('/predict', methods=['POST'])
def predict():
    if 'file' not in request.files:
        return redirect(request.url)

    file = request.files['file']
    if file.filename == '':
        return redirect(request.url)

    if file:
        # Save the uploaded file
        filepath = os.path.join('static', file.filename)
        file.save(filepath)

        # Load image
        img = Image.open(filepath).convert("RGB")
        img = img.resize((128, 128))
        img_array = np.array(img) / 255.0
        img_array = np.expand_dims(img_array, axis=0)

        # Predict
        predictions = model.predict(img_array)
        class_index = np.argmax(predictions)
        predicted_label = class_names[class_index]
        confidence = round(100 * np.max(predictions), 2)

        return render_template('result.html', label=predicted_label, confidence=confidence, image_path=filepath)

    return redirect(url_for('index'))

# Run the app
if __name__ == '__main__':
    app.run(debug=True)