from keras.layers import Input, Dense, Conv2D, Conv3D, LSTM, Flatten, Conv2DTranspose, MaxPooling2D, UpSampling2D, Conv3DTranspose, UpSampling3D, MaxPooling3D
from keras.models import Model, Sequential
from keras.datasets import mnist
import numpy as np
from sklearn.model_selection import train_test_split
from keras.utils import to_categorical
# use Matplotlib (don't ask)
import matplotlib.pyplot as plt




# this is the size of our encoded representations
encoding_dim = 64  # 32 floats -> compression of factor 24.5, assuming the input is 784 floats
'''
# this is our input placeholder
input_img = Input(shape=(1440000,))
# "encoded" is the encoded representation of the input
encoded = Dense(encoding_dim, activation='relu')(input_img)
# "decoded" is the lossy reconstruction of the input
decoded = Dense(1440000, activation='sigmoid')(encoded)

# this model maps an input to its reconstruction
autoencoder = Model(input_img, decoded)

# this model maps an input to its encoded representation
encoder = Model(input_img, encoded)

# create a placeholder for an encoded (32-dimensional) input
encoded_input = Input(shape=(encoding_dim,))
# retrieve the last layer of the autoencoder model
decoder_layer = autoencoder.layers[-1]
# create the decoder model
decoder = Model(encoded_input, decoder_layer(encoded_input))
'''



autoencoder = Sequential()
autoencoder.add(Conv3D(64, kernel_size=3, activation='relu', input_shape=(99,75,120,160)))
autoencoder.add(MaxPooling3D(pool_size=2))
autoencoder.add(Conv3D(32, kernel_size=3, activation='relu'))
autoencoder.add(MaxPooling3D(pool_size=2))
autoencoder.add(Conv3D(16, kernel_size=3, activation='relu'))
autoencoder.add(MaxPooling3D(pool_size=2))
'''
autoencoder.add(Flatten())
autoencoder.add(Dense(encoding_dim))
'''
autoencoder.add(Conv3DTranspose(16, kernel_size=3, activation='relu', data_format="channels_last"))
autoencoder.add(UpSampling3D(size=2))
autoencoder.add(Conv3DTranspose(32, kernel_size=3, activation='relu'))
autoencoder.add(UpSampling3D(size=2))
autoencoder.add(Conv3DTranspose(64, kernel_size=3, activation='relu'))

autoencoder.compile(optimizer='adagrad', loss='mse')
#split data to test and train
data = np.load(r"C:Usersshj_kDesktopProjecthandclapping.npy")

data = to_categorical(data)
print (data.shape)
(x_train,x_test) = train_test_split(data)
#print("Xtrain",x_train)
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.


x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
x_test = x_test.reshape((len(x_train), np.prod(x_train.shape[1:])))
print (x_train.shape)
print (x_test.shape)

autoencoder.fit(x_train, x_train,
                epochs=100,
                batch_size=25,
                shuffle=False,
                validation_data=(x_test, x_test))