import numpy as np
import gradio as gr
import tensorflow as tf #version 2.13.0
import keras #version 
import numpy as np
import cv2
import tensorflow as tf
import h5py
def analyse(img,plant_type):
    label_disease = {
        0 : 'Apple___Apple_scab',
        1 : 'Apple___Black_rot',
        2 : 'Apple___Cedar_apple_rust',
        3 : 'Apple___healthy',
        4 : 'Background_without_leaves',
        5 : 'Blueberry___healthy',
        6 : 'Cherry___Powdery_mildew',
        7 : 'Cherry___healthy',
        8 : 'Corn___Cercospora_leaf_spot_Gray_leaf_spot',
        9 : 'Corn___Common_rust',
        10: 'Corn___Northern_Leaf_Blight',
        11: 'Corn___healthy',
        12: 'Grape___Black_rot',
        13: 'Grape___Esca_(Black_Measles)',
        14: 'Grape___Leaf_blight_(Isariopsis_Leaf_Spot)',
        15: 'Grape___healthy',
        16: 'Orange___Haunglongbing_Citrus_greening',
        17: 'Peach___Bacterial_spot',
        18: 'Peach___healthy',
        19: 'Pepper_bell___Bacterial_spot',
        20: 'Pepper_bell___healthy',
        21: 'Potato___Early_blight',
        22: 'Potato___Late_blight',
        23: 'Potato___healthy',
        24: 'Raspberry___healthy',
        25: 'Soybean___healthy',
        26: 'Squash___Powdery_mildew',
        27: 'Strawberry___Leaf_scorch',
        28: 'Strawberry___healthy',
        29: 'Tomato___Bacterial_spot',
        30: 'Tomato___Early_blight',
        31: 'Tomato___Late_blight',
        32: 'Tomato___Leaf_Mold',
        33: 'Tomato___Septoria_leaf_spot',
        34: 'Tomato___Spider_mites_Two-,spotted_spider_mite',
        35: 'Tomato___Target_Spot',
        36: 'Tomato___Tomato_Yellow_Leaf_Curl_Virus',
        37: 'Tomato___Tomato_mosaic_virus',
        38: 'Tomato___healthy',
        }
    plant_label_disease={
            "apple":[0,1,2,3],
            "background_without_leaves":[4],
            "blueberry" : [5],
            "cherry" : [6,7],
            "corn" : [8,9,10,11],
            "grape" : [12,13,14,15],
            "orange" : [16] ,
            "peach" : [17,18],
            "pepper" : [19,20],
            "potato" : [21,22,23],
            "raspberry" : [24],
            "soybean" : [25],
            "squash" : [26],
            "strawberry" : [27,28],
            "tomato" : [29,30,31,32,33,34,35,36,37,38]
    }
    HEIGHT = 256
    WIDTH = 256
    dnn_model = keras.models.load_model('untrained_model.h5',compile=False)
    weights_path = 'keras_savedmodel_weights.h5'
    dnn_model.load_weights(weights_path)
    # dnn_model = tf.saved_model.load(model_path)
    
    process_img = cv2.resize(img, (HEIGHT, WIDTH),interpolation = cv2.INTER_LINEAR)
    process_img = process_img/(255)
    process_img = np.expand_dims(process_img, axis=0)
    
    
    y_pred = dnn_model.predict(process_img)
    print("y pred",y_pred)
    indx = np.argmax(y_pred)
    max_prob_indx = plant_label_disease[plant_type.lower()][0]
    for disease in plant_label_disease[plant_type.lower()]:
            print(disease,y_pred[0][disease],max_prob_indx,y_pred[0][max_prob_indx])
            if y_pred[0][disease]>y_pred[0][max_prob_indx]:
                max_prob_indx = disease
    print(label_disease[indx],y_pred[0][indx],label_disease[max_prob_indx],y_pred[0][max_prob_indx])
    return int(indx),max_prob_indx,label_disease[indx],y_pred[0][indx],label_disease[max_prob_indx],y_pred[0][max_prob_indx]

demo = gr.Interface(analyse, 
                    [gr.Image(),gr.Radio(["Apple","Blueberry","Cherry","Corn","Grape","Orange","Peach","Pepper","Potato","Raspberry","Soybean","Squash","Strawberry","Tomato"])],
                    ["number","number","text","number","text","number"],
                   )
demo.launch(share=True,show_error=True)