AI-Food-Detector

AI Food Detector

Model Description

This is a deep learning model trained on the Food-101 dataset to classify food images into 101 categories. The model can recognize a wide range of dishes with high accuracy, making it useful for food recognition applications in restaurants, nutrition tracking, and more. Users can input an image, and the model will predict the corresponding food category.

Model Details

Dataset: Food-101

Input Size: 224x224 pixels

Normalization: Pixel values are scaled between [0, 1]

Framework: TensorFlow/Keras

Training Hardware: (Specify if trained on GPU, TPU, etc.)

Load model

model = tf.keras.models.load_model("your_model_path.h5")

Preprocess Image

def preprocess_image(image_path):
    image = Image.open(image_path).resize((224, 224))
    image = np.array(image) / 255.0
    return np.expand_dims(image, axis=0)

Predict

image_path = "example.jpg"
image = preprocess_image(image_path)
prediction = model.predict(image)
predicted_class = class_names[np.argmax(prediction)]
print(f"Predicted Food Item: {predicted_class}")

Example Predictions

Model Performance