app_model2.py

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

# Load the model
model_path = "model_2_familyguy.keras"
model = tf.keras.models.load_model(model_path)

# Define the core prediction function
def predict_familyguy(image):
    # Preprocess image
    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
    image = image.resize((150, 150))  # Resize the image to 150x150
    image = np.array(image) / 255.0  # Normalize the image
    image = np.expand_dims(image, axis=0)  # Add batch dimension
    
    # Predict
    prediction = model.predict(image)
    
    # Convert the probabilities to rounded values
    prediction = np.round(prediction, 2)
    
    # Separate the probabilities for each class
    p_brian = prediction[0][0]  # Probability for class 'Brain Griffin'
    p_lois = prediction[0][1]   # Probability for class 'Lois Griffin'
    p_peter = prediction[0][2]  # Probability for class 'Peter Griffin'
    p_stewie = prediction[0][3] # Probability for class 'Stewie Griffin'
    
    return {'brian': p_brian, 'lois': p_lois, 'peter': p_peter, 'stewie': p_stewie}

# Create the Gradio interface
input_image = gr.Image()
iface = gr.Interface(
    fn=predict_familyguy,
    inputs=input_image,
    outputs=gr.Label(num_top_classes=4),  # This will display the top 4 class labels
    examples=["images/Brain1.png", "images/Brain2.jpg", "images/Brain3.jpg", 
              "images/Lois1.png", "images/Lois2.png", "images/Lois3.png", 
              "images/Peter1.jpg", "images/Peter2.jpg", "images/Peter3.jpg",  
              "images/Stewie1.jpg", "images/Stewie2.jpg", "images/Stewie3.jpg"],
    description="Upload an image to classify it as Brian, Lois, Peter, or Stewie."
)

iface.launch()