app.py

import gradio as gr
import tensorflow as tf
import numpy as np

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

# Define the class names
class_names = {
    0: 'Esophagitis',
    1: 'Dyed lifted polyps'
}


def classify_image(image):
    # Preprocess the image
    img_array = tf.image.resize(image, [256, 256])
    img_array = tf.expand_dims(img_array, 0) / 255.0

    # Make a prediction
    prediction = model.predict(img_array)
    predicted_class = tf.argmax(prediction[0], axis=-1)
    confidence = np.max(prediction[0])

    if confidence < 0.6:
        report = {
            'result': "Unable to detect",
            'confidence': confidence,
            'details': "The model was unable to confidently classify the image."
        }
    else:
        class_name = class_names[predicted_class.numpy()]
        report = {
            'result': class_name,
            'confidence': confidence,
            'details': f"The image is classified as {class_name} with a confidence of {confidence:.2f}."
        }

    return report


iface = gr.Interface(
    fn=classify_image,
    inputs=components.Image(shape=(256, 256)),
    outputs=[
        components.Textbox(label="Result"),
        components.Number(label="Confidence"),
        components.Textbox(label="Details")
    ],
    examples=[
        ['examples/0.jpg'],
        ['examples/1.jpg'],
        ['examples/2.jpg'],
        ['examples/3.jpg']
    ]
)

iface.launch()