app.py

from PIL import Image
import tensorflow as tf
import numpy as np
import gradio as gr
import io
import json

# Load the model
model_path = 'final_teath_classifier.h5'
model = tf.keras.models.load_model(model_path)

# Define preprocessing function


# Define prediction function
def predict_image(image):
    # Save the image to a file-like object
    image_bytes = io.BytesIO()
    image.save(image_bytes, format="JPEG")

    # Load the image from the file-like object
    image = tf.keras.preprocessing.image.load_img(image_bytes, target_size=(256, 256))
    image = tf.keras.preprocessing.image.img_to_array(image)
    image = np.expand_dims(image, axis=0)

    # Make a prediction
    prediction = model.predict(image)

    # Get the probability of being 'Good'
    probability_good = prediction[0][0]  # Assuming it's a binary classification

    # Define the prediction result
    result = {
        "prediction": "Your Teeth are Good & You Don't Need To Visit Doctor" if probability_good > 0.5 else "Your Teeth are Bad & You Need To Visit Doctor"
    }

    return result
    #predictions = tf.nn.softmax(outputs.logits, axis=-1)
    #predicted_class = np.argmax(predictions)
    #if predicted_class == 0:
        #predict_label = "Clean"
    #else:
        #predict_label = "Carries"
    #confidence = float(np.max(predictions))
    #prediction_dict = {"prediction": predict_label, "confidence": confidence}
    #return prediction_dict
   


# Create the interface
input_interface = gr.Image(type = "pil")
output_interface = "json"

iface = gr.Interface(
    fn=predict_image,
    inputs=input_interface,
    outputs=gr.Textbox("output"))

# Launch the interface
iface.launch(share=True)