Blame view
VARIATIONAL/vae.py
4.03 KB
b6d0165d1
Initial commit
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
'''This script demonstrates how to build a variational autoencoder with Keras.
Reference: "Auto-Encoding Variational Bayes" https://arxiv.org/abs/1312.6114
'''
import itertools
import sys
import json
import numpy as np
import matplotlib.pyplot as plt
from scipy import sparse
import scipy.io
from keras.layers import Input, Dense, Lambda
from keras.models import Model
from keras import backend as K
from keras import objectives
from keras.datasets import mnist
import pandas
import shelve
import pickle
from utils import *
#
sparse_model=shelve.open("{}.shelve".format(sys.argv[1]))
db=shelve.open("{}.shelve".format(sys.argv[2]),writeback=True)
ASR=sparse_model["ASR"]
TRS=sparse_model["TRS"]
LABEL=sparse_model["LABEL"]
db["LABEL"]=LABEL
label_bin={}
lb = preprocessing.LabelBinarizer(neg_label=0)
lb.fit(LABEL["TRAIN"].apply(select))
for i in ASR.keys():
label_bin=lb.transform(LABEL[i].apply(select))
batch_size = 16
original_dim = 784
latent_dim = 2
intermediate_dim = 128
epsilon_std = 0.01
nb_epoch = 40
hidden_size=50
input_activation="tanh"
out_activation="tanh"
loss="mse"
epochs=500
batch=1
patience=60
w1_size=3000
w2_size=500
sgd = Adam(lr=0.0001)#SGD(lr=0.00001,nesterov=False) #'rmsprop'# Adam(lr=0.00001)#SGD(lr=0.001, momentum=0.9, nesterov=True)
x = Input(batch_shape=(batch_size, original_dim))
h = Dense(intermediate_dim, activation='relu')(x)
z_mean = Dense(latent_dim)(h)
z_log_std = Dense(latent_dim)(h)
def sampling(args):
z_mean, z_log_std = args
epsilon = K.random_normal(shape=(batch_size, latent_dim),
mean=0., std=epsilon_std)
return z_mean + K.exp(z_log_std) * epsilon
# note that "output_shape" isn't necessary with the TensorFlow backend
# so you could write `Lambda(sampling)([z_mean, z_log_std])`
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_std])
# we instantiate these layers separately so as to reuse them later
decoder_h = Dense(intermediate_dim, activation='relu')
decoder_mean = Dense(original_dim, activation='sigmoid')
h_decoded = decoder_h(z)
x_decoded_mean = decoder_mean(h_decoded)
def vae_loss(x, x_decoded_mean):
xent_loss = objectives.binary_crossentropy(x, x_decoded_mean)
kl_loss = - 0.5 * K.mean(1 + z_log_std - K.square(z_mean) - K.exp(z_log_std), axis=-1)
return xent_loss + kl_loss
vae = Model(x, x_decoded_mean)
vae.compile(optimizer='rmsprop', loss=vae_loss)
# train the VAE on MNIST digits
(x_train, y_train), (x_test, y_test) = mnist.load_data()
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_test), np.prod(x_test.shape[1:])))
vae.fit(x_train, x_train,
shuffle=True,
nb_epoch=nb_epoch,
batch_size=batch_size,
validation_data=(x_test, x_test))
# build a model to project inputs on the latent space
encoder = Model(x, z_mean)
# display a 2D plot of the digit classes in the latent space
x_test_encoded = encoder.predict(x_test, batch_size=batch_size)
plt.figure(figsize=(6, 6))
plt.scatter(x_test_encoded[:, 0], x_test_encoded[:, 1], c=y_test)
plt.colorbar()
plt.show()
# build a digit generator that can sample from the learned distribution
decoder_input = Input(shape=(latent_dim,))
_h_decoded = decoder_h(decoder_input)
_x_decoded_mean = decoder_mean(_h_decoded)
generator = Model(decoder_input, _x_decoded_mean)
# display a 2D manifold of the digits
n = 15 # figure with 15x15 digits
digit_size = 28
figure = np.zeros((digit_size * n, digit_size * n))
# we will sample n points within [-15, 15] standard deviations
grid_x = np.linspace(-15, 15, n)
grid_y = np.linspace(-15, 15, n)
for i, yi in enumerate(grid_x):
for j, xi in enumerate(grid_y):
z_sample = np.array([[xi, yi]]) * epsilon_std
x_decoded = generator.predict(z_sample)
digit = x_decoded[0].reshape(digit_size, digit_size)
figure[i * digit_size: (i + 1) * digit_size,
j * digit_size: (j + 1) * digit_size] = digit
plt.figure(figsize=(10, 10))
plt.imshow(figure)
plt.show()
|