# -*- coding: utf-8 -*-

"""Inception V3 model for Keras.

Note that the input image format for this model is different than for

the VGG16 and ResNet models (299x299 instead of 224x224),

and that the input preprocessing function is also different (same as Xception).

# Reference

- [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)

"""

from __future__ import print_function

from __future__ import absolute_import

import warnings

import numpy as np

from keras.models import Model

from keras import layers

from keras.layers import Activation

from keras.layers import Dense

from keras.layers import Input

from keras.layers import BatchNormalization

from keras.layers import Conv2D

from keras.layers import MaxPooling2D

from keras.layers import AveragePooling2D

from keras.layers import GlobalAveragePooling2D

from keras.layers import GlobalMaxPooling2D

from keras.engine.topology import get_source_inputs

from keras.utils.layer_utils import convert_all_kernels_in_model

from keras.utils.data_utils import get_file

from keras import backend as K

from keras.applications.imagenet_utils import decode_predictions

from keras.applications.imagenet_utils import _obtain_input_shape

from keras.preprocessing import image

import subprocess

import json

WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels.h5'

WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5'

def jtalk(t):

wr = subprocess.Popen(aplay)

def conv2d_bn(x,

return x

def InceptionV3(include_top=True,

return model

def preprocess_input(x):

return x

import cv2

import socket

import subprocess

import xml.etree.ElementTree as ET

import time

HOST = "127.0.1.1"

PORT = 10500

if __name__ == '__main__':

model = InceptionV3(include_top=True, weights='imagenet')

cam = cv2.VideoCapture(0)

print("start")

# julius起動スクリプトを実行

p = subprocess.Popen(["bash /home/pi/start_julius.sh"], stdout=subprocess.PIPE, shell=True)

print(p)

pid = p.stdout.read() # juliusのプロセスIDを取得

pid = p.pid

print(pid)

#time.sleep(5)

# TCPクライアントを作成し接続

client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

client.connect(('localhost', 10500))

#client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

#client.connect((HOST, PORT))

print("start2")

# サーバからのデータ受信と

data = ""

#while 1:

while(True):

#ret, frame = cam.read()

#cv2.imshow("Show FLAME Image", frame)

#time.sleep(1)

if "</RECOGOUT>\n." in data:

# RECOGOUT要素以下をXMLとしてパース

root = ET.fromstring('<?xml version="1.0"?>\n' + data[data.find("<RECOGOUT>"):].replace("\n.", ""))

ret, frame = cam.read()

cv2.imshow("Show FLAME Image", frame)

#time.sleep(1)

# 言葉を判別

for whypo in root.findall("./SHYPO/WHYPO"):

word = whypo.get("WORD")

#ret, frame = cam.read()

#cv2.imshow("Show FLAME Image", frame)

if u"何ですか" in word:

cv2.imwrite("output.png", frame)

img_path = "output.png"

img = image.load_img(img_path, target_size=(299, 299))

x = image.img_to_array(img)

x = np.expand_dims(x, axis=0)

x = preprocess_input(x)

preds = model.predict(x)

recognize = decode_predictions(preds)

speak = recognize[0][0][1]

if speak == "nematode":

jtalk("わかりません")

data = ""

continue

#subprocess.check_output(["espeak", "-k5", "-s150", speak])

print('Label:', speak)

with open('imagenet_class_index.json', 'r') as f:

obj = json.load(f)

for i in obj:

if i['en'] == speak:

jp_speak = i['ja']

jp_speak = jp_speak.encode('utf-8')

print(jp_speak)

#jtalk(jp_speak)

jtalk("これは" + jp_speak + "だよ")

#jtalk("英語では")

#subprocess.check_output(["espeak", "-k5", "-s150", speak])

#jtalk("です")

if u"終了" in word:

jtalk("ばいばい")

break

else:

print("Unknown:" + word.encode('utf-8'))

#print("Unknown:")

data = ""

else:

data = data + client.recv(1024)

# CTRL+Cで終了

print("KeyboardInterrupt occured.")

p.kill() #

subprocess.call(["kill " + str(pid)], shell=True) # juliusのプロセスを終了

client.close()

cam.release()

cv2.destroyAllWindows()

#while(True):

# ret, frame = cam.read()

# cv2.imshow("Show FLAME Image", frame)

# k = cv2.waitKey(1)

# if k == ord('s'):

# cv2.imwrite("output.png", frame)

# img_path = "output.png"

# img = image.load_img(img_path, target_size=(299, 299))

# x = image.img_to_array(img)

# x = np.expand_dims(x, axis=0)

# x = preprocess_input(x)

# preds = model.predict(x)

# recognize = decode_predictions(preds)

# speak = recognize[0][0][1]

# subprocess.check_output(["espeak", "-k5", "-s150", speak])

# print('Label:', speak)

# with open('imagenet_class_index.json', 'r') as f:

# obj = json.load(f)

# for i in obj:

# if i['en'] == speak:

# jp_speak = i['ja']

# jp_speak = jp_speak.encode('utf-8')

# print(jp_speak)

# jtalk(jp_speak)

#

#

# elif k == ord('q'):

# break

#model = InceptionV3(include_top=True, weights='imagenet')

#img_path = 'elephant.jpg'

#img = image.load_img(img_path, target_size=(299, 299))

#x = image.img_to_array(img)

#x = np.expand_dims(x, axis=0)

#x = preprocess_input(x)

#preds = model.predict(x)

##print('Predicted:', decode_predictions(preds))

#recognize = decode_predictions(preds)

#print('Label:', recognize[0][0][1])