model_predictor.py

import tensorflow as tf
import numpy as np

model = tf.keras.models.load_model("model/101_food_class_fine_tuned_model.keras")

class_names = [
    "apple_pie", "baby_back_ribs", "baklava", "beef_carpaccio", "beef_tartare", "beet_salad", "beignets", "bibimbap",
    "bread_pudding", "breakfast_burrito", "bruschetta", "caesar_salad", "cannoli", "caprese_salad", "carrot_cake",
    "ceviche", "cheesecake", "cheese_plate", "chicken_curry", "chicken_quesadilla", "chicken_wings", "chocolate_cake",
    "chocolate_mousse", "churros", "clam_chowder", "club_sandwich", "crab_cakes", "creme_brulee", "croque_madame",
    "cup_cakes", "deviled_eggs", "donuts", "dumplings", "edamame", "eggs_benedict", "escargots", "falafel",
    "filet_mignon", "fish_and_chips", "foie_gras", "french_fries", "french_onion_soup", "french_toast",
    "fried_calamari", "fried_rice", "frozen_yogurt", "garlic_bread", "gnocchi", "greek_salad", "grilled_cheese_sandwich",
    "grilled_salmon", "guacamole", "gyoza", "hamburger", "hot_and_sour_soup", "hot_dog", "huevos_rancheros", "hummus",
    "ice_cream", "lasagna", "lobster_bisque", "lobster_roll_sandwich", "macaroni_and_cheese", "macarons", "miso_soup",
    "mussels", "nachos", "omelette", "onion_rings", "oysters", "pad_thai", "paella", "pancakes", "panna_cotta",
    "peking_duck", "pho", "pizza", "pork_chop", "poutine", "prime_rib", "pulled_pork_sandwich", "ramen", "ravioli",
    "red_velvet_cake", "risotto", "samosa", "sashimi", "scallops", "seaweed_salad", "shrimp_and_grits",
    "spaghetti_bolognese", "spaghetti_carbonara", "spring_rolls", "steak", "strawberry_shortcake", "sushi", "tacos",
    "takoyaki", "tiramisu", "tuna_tartare", "waffles"
]

def prediction(img):
    img = tf.convert_to_tensor(img, dtype=tf.float32)
    img = tf.expand_dims(img, axis=0)
    pred = model.predict(img)
    
    # Get the top 10 predictions
    top_indices = np.argsort(pred[0])[::-1][:10]  # Sort probabilities in descending order
    top_probs = pred[0][top_indices]  # Get top probabilities
    top_classes = [class_names[i] for i in top_indices]  # Get corresponding class names

    predictions_list = [{"class": top_classes[i], "probability": float(top_probs[i])} for i in range(len(top_classes))]
    
    return predictions_list