import gradio as gr
import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from tensorflow.keras.applications import ResNet50V2
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Dense
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.applications.resnet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import load_img, img_to_array

image_folders = ['King_Crab', 'Wind_Lion_God', 'pavo_cristatus', 'otter', 'Upupa_epops']
labels = ["鱟", "金門風獅爺", "金門藍孔雀", "歐亞水獺", "金門戴勝鳥"]

base_dir = './'

thedir = base_dir + image_folders[0]
os.listdir(thedir)

data = []
target = []
for i in range(5):
    thedir = base_dir + image_folders[i]
    image_fnames = os.listdir(thedir)
    for theimage in image_fnames:
        if theimage == ".git" or theimage == ".ipynb_checkpoints":
          continue
        img_path = thedir + '/' + theimage
        img = load_img(img_path , target_size = (256,256))
        x = img_to_array(img)
        data.append(x)
        target.append(i)

model = load_model('my_cnn_model.pb') # Loading the Tensorflow Saved Model (PB)
print(model.summary())

def classify_image(inp):
    inp = inp.reshape((-1, 256, 256, 3))
    inp = preprocess_input(inp)
    prediction = model.predict(inp).flatten()
    return {labels[i]: float(prediction[i]) for i in range(5)}

image = gr.Image(shape=(256, 256), label="金門藍孔雀、歐亞水獺、戴勝鳥照片")
label = gr.Label(num_top_classes=5, label="AI辨識結果")
some_text="我能辨識金門藍孔雀、歐亞水獺、戴勝鳥。找張金門藍孔雀、歐亞水獺、戴勝鳥照片來考我吧!"

sample_images = []
for i in range(5):
    thedir = base_dir + image_folders[i]
    for file in os.listdir(thedir):
        if file == ".git" or file == ".ipynb_checkpoints":
          continue
        sample_images.append(image_folders[i] + '/' + file)

iface = gr.Interface(fn=classify_image,
             inputs=image,
             outputs=label,
             title="AI 金門藍孔雀、歐亞水獺、戴勝鳥辨識機",
             description=some_text,
             examples=sample_images, live=True)

# def greet(name):

#     model = load_model('my_cnn_model.h5') # Loading the Tensorflow Saved Model (PB)    

    
#     return "Hello " + name + "!!" + model.summary()


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

# .launch(share=True)
iface.launch()