import gradio as gr

label_dict = {}

f = open('baseline_keras_model_labels.txt', 'r')

lines = f.readlines()
for line in lines:
    index, label_name = line.split(',')
    label_dict[int(index)] = label_name.strip()
f.close()
 
import tensorflow as tf
from tensorflow import keras
from keras.models import load_model
from PIL import Image, ImageOps
import numpy as np
import os

# Load the model
model = load_model('baseline_keras_model.h5')

# Create the array of the right shape to feed into the keras model
# The 'length' or number of images you can put into the array is
# determined by the first position in the shape tuple, in this case 1.
data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32)
# Replace this with the path to your image

folder_path = 'x_test'

y_pred = []

def predict(image):

    size = (224, 224)
    image = ImageOps.fit(image, size, Image.ANTIALIAS)

    #turn the image into a numpy array
    image_array = np.asarray(image)
    # Normalize the image
    normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
    # Load the image into the array
    data[0] = normalized_image_array

    # run the inference
    prediction = model.predict(data)[0]
    confidences = {label_dict[i]: float(prediction[i]) for i in range(4)}    
    
    return confidences

gr.Interface(fn=predict, 
             inputs=gr.Image(type="pil"),
             outputs=gr.Label(num_top_classes=5),
             examples=["12122.jpg", "23482.jpg", "32321.jpg", "43413.jpg", "59394.jpg", "77923.jpg", "83823.jpg"]).launch()