app.py

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

#!pip install tensorflow tensorflow-datasets gradio pillow matplotlib

model_path = "Dogs-model_transferlearning_FT.keras"
model = tf.keras.models.load_model(model_path)

# Define the core prediction function
def predict_dogs(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)
    image = np.expand_dims(image, axis=0) # Add batch dimension
    
    # Predict
    prediction = model.predict(image)
    
    # Apply softmax to get probabilities for each class
    probabilities = tf.nn.softmax(prediction)
    
    # Map probabilities to Pokemon classes
    dogs_classes = ['beagle', 'goldie', 'husky']  
    probabilities_dict = {dogs_class: round(float(probability), 2) for dogs_class, probability in zip(dogs_classes, probabilities[0])}
    
    return probabilities_dict

# Create the Gradio interface
input_image = gr.Image()
iface = gr.Interface(
    fn=predict_dogs,
    inputs=input_image, 
    outputs=gr.Label(),
    examples=["images/01.jpg", "images/02.jpg", "images/03.jpg", "images/04.jpg", "images/05.jpg", "images/06.jpg"],   
    description="A simple mlp classification model for image classification using the mnist dataset.")
iface.launch()