# model_utils.py
import tensorflow as tf
from PIL import Image
import numpy as np

class ImageClassifier:
    def __init__(self, model_path):
        self.model = tf.keras.models.load_model(model_path)
        # Update these based on your model's requirements
        self.input_size = (224, 224)  # Example size, change as needed
        self.class_names = ['class1', 'class2', 'class3']  # Replace with your class names
    
    def preprocess_image(self, image):
        """Preprocess the image for your model"""
        image = image.resize(self.input_size)
        image_array = np.array(image)
        image_array = image_array / 255.0  # Normalize if your model expects this
        image_array = np.expand_dims(image_array, axis=0)
        return image_array
    
    def predict(self, image):
        """Make a prediction on the image"""
        processed_image = self.preprocess_image(image)
        predictions = self.model.predict(processed_image)
        predicted_class = np.argmax(predictions[0])
        confidence = np.max(predictions[0])
        return {
            'class': self.class_names[predicted_class],
            'confidence': float(confidence),
            'all_predictions': predictions.tolist()
        }