import gradio as gr

from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input, decode_predictions
import numpy as np
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from glob import glob
# loading the directories 
# importing the libraries
import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Flatten, Dense
from tensorflow.keras.applications import VGG16
#from keras.preprocessing import image
num_classes=10
IMAGE_SHAPE = [224, 224]

class_labels = ['exterior_building','icons','interior_building','landscapes','layouts','others','people','scanned_documents','signatures','under_construction']


def greet(name):
    return "Hello " + name + "!!"


model = tf.keras.models.load_model("./classification_model.h5")
class_labels = ['exterior_building','icons','interior_building','landscapes','layouts','others','people','scanned_documents','signatures','under_construction']

def predict_image(image):

    
    # img_path = '/Users/balamuruga/Desktop/Screenshot 2023-11-08 at 9.22.52 PM.png'
    # img = image.load_img(img_path, target_size=(224, 224))
    # x = image.img_to_array(img)
    # x = np.expand_dims(x, axis=0)
    # x = preprocess_input(x)
    image = image.reshape((-1, 224, 224, 3))


    # preds=model.predict(image)
    prediction = model.predict(image).flatten()
    print(prediction)
    return {class_labels[i]: float(prediction[i]) for i in range(10)}

    # create a list containing the class labels
    
    # # find the index of the class with maximum score
    # pred = np.argmax(preds, axis=-1)
    
    # # print the label of the class with maximum score
    # print(class_labels[pred[0]])
    # return {class_labels[i]: float(pred[i]) for i in range(10)}
    
  # img_4d=img.reshape(-1,256,256,3)
  # prediction=model.predict(img_4d)[0]
  # return {class_names[i]: float(prediction[i]) for i in range(5)}

# iface = gr.Interface(fn=predict_image, inputs="text", outputs="text")
# iface.launch()


image = gr.inputs.Image(shape = (224, 224)) 
label = gr.outputs.Label(num_top_classes = 10)
gr.Interface(fn=predict_image, inputs=image, outputs=label,interpretation='default').launch(debug='True')