app.py

from flask import Flask, request, jsonify, render_template
from tensorflow.keras.models import model_from_json
from PIL import Image
import numpy as np

app = Flask(__name__)

# Load model architecture from JSON file
with open("model.json", "r") as json_file:
    loaded_model_json = json_file.read()

Model = model_from_json(loaded_model_json)

Model.load_weights("model.h5")

print("Loaded model from disk")


# predict
def preprocess_image(image):
    img = Image.open(image)
    img = img.resize((224, 224))
    img_array = np.expand_dims(img, axis=0)
    return img_array


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


@app.route('/predict', methods=['POST'])
def predict():
    if 'image' not in request.files:
        return jsonify({'error': 'No file part'})

    file = request.files['image']

    if file.filename == '':
        return jsonify({'error': 'No selected file'})

    if file:
        img = preprocess_image(file)
        predictions = Model.predict(img)
        predicted_class_index = int(np.argmax(predictions, axis=1)[0])  # Convert to int
        class_labels = ['pituitary', 'notumor', 'meningioma', 'glioma']
        predicted_class_label = class_labels[predicted_class_index]
        return jsonify({'class': predicted_class_label})


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