import gradio as gr 
import tensorflow as tf
from tensorflow.keras.models import model_from_json,Sequential
from tensorflow.keras.preprocessing import image
import numpy as np
from tensorflow.keras.layers import Layer
from tensorflow.keras.utils import register_keras_serializable
import json

class AccidentDetectionModel(object):

    class_nums = ['Accident', "No Accident"]

    def __init__(self, model_json_file, model_weights_file):
        # load model from JSON file
        with open(model_json_file, "r") as json_file:
            loaded_model_json = json_file.read()
            self.loaded_model = model_from_json(loaded_model_json)

        # load weights into the new model
        self.loaded_model.load_weights(model_weights_file)
        self.loaded_model.make_predict_function()

    def predict_accident(self, img):
        self.preds = self.loaded_model.predict(img)
        return AccidentDetectionModel.class_nums[np.argmax(self.preds)], self.preds


# Initialize the model with the weights file
model_ = AccidentDetectionModel("modified_model.json","modified_model_weights.h5")

    # from keras.preprocessing import image
def predict(image):
    test_image = tf.keras.utils.load_img(image, target_size = (250,250,3)) 
    test_image = tf.keras.utils.img_to_array(test_image)
    test_image = np.expand_dims(test_image, axis = 0)
# print(test_image[:1])
#predict the result
    pred,probab = model_.predict_accident(test_image)
    return dict(zip(pred, {model_.class_nums[i]: float(probab[0][i]) for i in range(len(model_.class_nums))}))

image = gr.Image()
label = gr.Label(num_top_classes=2)

demo = gr.Interface(fn=predict , inputs=image, outputs=label, title="Accident Detection")
demo.launch()