[6기] 프로그래머스 인공지능 데브코스 116일차 TIL

1225

[17주차 - Day3] Recommendation system

케라스 오토인코더 실습

# 케라스 이용한 오토인코더 실습

import numpy as np
import matplotlib.pyplot as plt
from keras.layers import Input, Dense
from keras.models import Model
from keras.datasets import mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.astype('float32') / 256
x_test = x_test.astype('float32') / 256

print(x_train.shape)

 

x_train = x_train.reshape(len(x_train), 28*28)
x_test = x_test.reshape(len(x_test), 28*28)

print(x_train.shape)
print(x_test.shape)

input_layer = Input(shape=(784,))
encoded = Dense(64, activation='relu')(input_layer)
decoded = Dense(784, activation='sigmoid')(encoded)

autoencoder = Model(input_layer, decoded)

encoder = Model(input_layer, encoded)

input_layer_decoder = Input(shape=(64,))
decoder_layer = autoencoder.layers[-1](input_layer_decoder)
decoder = Model(input_layer_decoder, decoder_layer)

autoencoder.summary()

 

autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
autoencoder.fit(x_train, x_train, epochs=50, batch_size=256, shuffle=True, validation_data=(x_test, x_test))

 

def visualize(data, size):
  n = 8
  plt.figure(figsize=(20,4))
  plt.gray()
  for i in range(n):
    ax = plt.subplot(2, n, i+1)
    plt.imshow(data[i].reshape(size, size))
    ax.get_xaxis().set_visible(False)
    ax.get_yaxis().set_visible(False)
  plt.show()
  
visualize(x_test, 28)
visualize(encoded_images, 8)
visualize(decoded_images, 28)