from __future__ import print_function


import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Input, Conv2D, MaxPooling2D


import tensorflow as tf
from keras.utils import multi_gpu_model
from keras.callbacks import TensorBoard

import os
import time

from datetime import date

start = time.time()
today = date.today()

num_gpus = int(os.environ.get('CIFAR10_NUM_GPUS'))
num_cores = int(os.environ.get('CIFAR10_NUM_CORES'))
batch_size = int(os.environ.get('CIFAR10_BATCHSIZE'))
num_classes = 10
epochs = 200
num_predictions = 20
save_dir = os.environ.get('CIFAR10_PATH_SAVED_MODELS')
log_dir = os.path.join(os.environ.get('CIFAR10_PATH_TENSORBOARD_LOGS'), "".join(['gpus',str(num_gpus),'_cores', str(num_cores),'_batchsize',str(batch_size),'_',str(today.year),'_',str(today.month),'_',str(today.day)]))
model_name = 'keras_cifar10_trained_model_gpus'+str(num_gpus)+'_cores'+str(num_cores)+'_batchsize'+str(batch_size)+'_'+str(today.year)+'_'+str(today.month)+'_'+str(today.day)+'.h5'

if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
if not os.path.isdir(log_dir):
    os.makedirs(log_dir)


# The data, shuffled and split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print('y_train shape:', y_train.shape)

num_train, height, width, depth = x_train.shape
print (x_train.shape)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255


# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)


model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop

model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])


parallel_model = multi_gpu_model(model, gpus=num_gpus)
parallel_model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

tensorboard = TensorBoard(log_dir=log_dir, histogram_freq=0, write_graph=True, write_grads=False, write_images=False)

parallel_model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          validation_data=(x_test, y_test),
          shuffle=True,
          callbacks=[tensorboard])

print('###############################\n')

# Save model and weights
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model: %s \n' % model_path)
print('Tensorboard log: %s \n' % log_dir)

# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('GPUS:', num_gpus, '\n')
print('Batch size:', batch_size, '\n')

print('Test loss:', scores[0], '\n')
print('Test accuracy:', scores[1], '\n')

end = time.time()
print('Total duration:', ((end - start)/60), 'minutes')