# -*- coding: utf-8 -*-
"""Untitled0.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1wQK5xSDWkNehxDpQ5sdbyfYsOS-5u62i
"""

from google.colab import files
files.upload()

import os
import tensorflow as tf
from tensorflow.keras.applications.inception_v3 import InceptionV3
from tensorflow.keras.preprocessing import image
from tensorflow.keras.models import Model, load_model, save_model
from tensorflow.keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout
from tensorflow.keras.layers import BatchNormalization, Activation
from tensorflow.python.keras.optimizers import Adam, RMSprop
from tensorflow.python.keras.preprocessing.image import ImageDataGenerator
import numpy as np
import matplotlib as mplib
import matplotlib.pyplot as plt

!unzip Cyrillic.zip -d /content/test_dir

image_size = 278
batch_size = 32
base_dir = "/content/"
train_dir = base_dir+'train_dir/Cyrillic/'
test_dir = base_dir+'test_dir/Cyrillic/'

input_shape = (image_size, image_size, 3)
train_datagen = ImageDataGenerator(rescale=1./255, rotation_range=10,
                                  width_shift_range=0.1,
                                  height_shift_range=0.1,
                                  zoom_range=0.1,
                                  fill_mode='nearest')

alphabet = ['А', 'Б', 'В','Г','Д','Е','Ё','Ж','З','И','Й','К','Л',
            'М','Н','О','П','Р','С','Т','У','Ф','Х','Ц','Ч','Ш',
            'Щ','Ъ','Ы','Ь','Э','Ю','Я']

train_generator = train_datagen.flow_from_directory(train_dir, target_size=(image_size, image_size), batch_size=batch_size)
test_datagen = ImageDataGenerator(rescale=1./255)
test_generator = train_datagen.flow_from_directory(test_dir, target_size=(image_size, image_size), batch_size=batch_size)
train_generator.class_indices

pretrained_model = InceptionV3(weights='imagenet', include_top=False)

pretrained_model.trainable = False
x = pretrained_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(512)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
predictions = Dense(1, activation='sigmoid')(x)
model = Model(inputs=pretrained_model.input, outputs=predictions)

model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

filepath="/content/inceptionv3_best.h5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, 
                             save_best_only=True, mode='max')
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', 
                                            patience=3, 
                                            verbose=1, 
                                            factor=0.5, 
                                            min_lr=0.00001)
callbacks_list = [checkpoint, learning_rate_reduction]

steps_per_epoch = 40
history = model.fit_generator(
    train_generator,
    steps_per_epoch=steps_per_epoch,
    validation_data=test_generator,
    validation_steps=5,
    callbacks=callbacks_list,
    epochs=20,
    verbose=2)

save_model(model, "/content/inceptionv3_best.h5")

model = load_model("inceptionv3_best.h5")
img1 = '/content/train_dir/Cyrillic/Я/58bed180e322e.png'
img = image.load_img(img1, target_size=(image_size, image_size))

x = image.img_to_array(img)
x /= 255
x = np.expand_dims(x, axis=0)

prediction = model.predict(x)
prediction