app.py

import gradio as gr
import tensorflow as tf
print(tf.__version__)
import numpy as np
from PIL import Image

import os

model_path = "pokemon-model_transferlearning.keras"
model = tf.keras.models.load_model(model_path)

def predict_pokemon(image):
    # Preprocess image
    print(type(image))
    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
    image = image.resize((150, 150))  # Resize the image to 150x150 pixels
    image = np.array(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)

    # Make sure the indices are correct according to your model's training
    p_dratini = prediction[0][0]  # Probability for class 'dratini'
    p_eevee = prediction[0][1]    # Probability for class 'eevee'
    p_jolteon = prediction[0][2]  # Probability for class 'jolteon'

    return {'dratini': p_dratini, 'eevee': p_eevee, 'jolteon': p_jolteon}
 
 
# Create the Gradio interface
input_image = gr.Image()
iface = gr.Interface(
    fn=predict_pokemon,
    inputs=input_image,
    outputs=gr.Label(),
    examples=["images/Dratini1.jpg", 
              "images/Dratini2.jpg", 
              "images/Dratini3.jpg", 
              "images/Eevee1.jpg",
              "images/Eevee2.jpg",
              "images/Eevee3.jpg",
              "images/Jolteon1.jpg",
              "images/Jolteon2.jpg",
              "images/Jolteon3.jpg"], 
    description="POKEMON MODEL")
 
iface.launch()