import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm
import cPickle
from keras.layers import Input, Dense, Lambda, Flatten, Reshape, Layer
from keras.layers import Conv2D, Conv2DTranspose
from keras.models import Model
from keras import backend as K
from keras import metrics
from keras import optimizers
from full_params_conv_101 import *
if K.image_data_format() == 'channels_first':
original_img_size = (img_chns, img_rows, img_cols)
else:
original_img_size = (img_rows, img_cols, img_chns)
x = Input(shape=original_img_size)
conv_1 = Conv2D(32,
kernel_size=(4, 4),
strides=(2, 2),
padding='same', activation='relu')(x)
conv_2 = Conv2D(64,
kernel_size=(4, 4),
padding='same', activation='relu',
strides=(2, 2))(conv_1)
conv_3 = Conv2D(128,
kernel_size=(4, 4),
padding='same', activation='relu',
strides=(2, 2))(conv_2)
conv_4 = Conv2D(256,
kernel_size=(4, 4),
padding='same', activation='relu',
strides=(2, 2))(conv_3)
flat = Flatten()(conv_4)
hidden = Dense(intermediate_dim, activation='relu')(flat)
z_mean = Dense(latent_dim)(hidden)
z_log_var = Dense(latent_dim)(hidden)
def sampling(args):
z_mean, z_log_var = args
epsilon = K.random_normal(shape=(K.shape(z_mean)[0], latent_dim),
mean=0., stddev=epsilon_std)
return z_mean + K.exp(z_log_var) * epsilon
# note that "output_shape" isn't necessary with the TensorFlow backend
# so you could write `Lambda(sampling)([z_mean, z_log_var])`
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])
# we instantiate these layers separately so as to reuse them later
decoder_hid = Dense(intermediate_dim, activation='relu')
decoder_upsample = Dense(16384, activation='relu')
if K.image_data_format() == 'channels_first':
output_shape = (batch_size, 256, 8, 8)
else:
output_shape = (batch_size, 8, 8, 256)
decoder_reshape = Reshape(output_shape[1:])
decoder_deconv_1 = Conv2DTranspose(128,
kernel_size=(4, 4),
padding='same',
strides=(2, 2),
activation='relu')
decoder_deconv_2 = Conv2DTranspose(64,
kernel_size=(4, 4),
padding='same',
strides=(2, 2),
activation='relu')
decoder_deconv_3_upsamp = Conv2DTranspose(32,
kernel_size=(4, 4),
strides=(2, 2),
padding='same',
activation='relu')
decoder_mean_squash = Conv2DTranspose(3,
kernel_size=(4, 4),
strides=(2, 2),
padding='same',
activation='relu')
hid_decoded = decoder_hid(z)
up_decoded = decoder_upsample(hid_decoded)
reshape_decoded = decoder_reshape(up_decoded)
deconv_1_decoded = decoder_deconv_1(reshape_decoded)
deconv_2_decoded = decoder_deconv_2(deconv_1_decoded)
x_decoded_relu = decoder_deconv_3_upsamp(deconv_2_decoded)
x_decoded_mean_squash = decoder_mean_squash(x_decoded_relu)
# Custom loss layer
class CustomVariationalLayer(Layer):
def __init__(self, **kwargs):
self.is_placeholder = True
super(CustomVariationalLayer, self).__init__(**kwargs)
def vae_loss(self, x, x_decoded_mean_squash):
x = K.flatten(x)
x_decoded_mean_squash = K.flatten(x_decoded_mean_squash)
xent_loss = img_rows * img_cols * metrics.binary_crossentropy(x, x_decoded_mean_squash)
kl_loss = - 0.5 * K.mean(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
return K.mean(xent_loss + kl_loss)
def call(self, inputs):
x = inputs[0]
x_decoded_mean_squash = inputs[1]
loss = self.vae_loss(x, x_decoded_mean_squash)
self.add_loss(loss, inputs=inputs)
# We don't use this output.
return x
y = CustomVariationalLayer()([x, x_decoded_mean_squash])
vae = Model(x, y)
sgd = optimizers.SGD(lr=0.01)
vae.compile(optimizer=sgd, loss=None)
vae.summary()
"""
with open('../datasets/101_ObjectCategories.pkl') as f:
dic = cPickle.load(f)
x_train = dic['all_images']
"""
x_train = np.load('../datasets/full_x.npy')
print "dataset loaded"
history = vae.fit(x_train,
shuffle=True,
epochs=epochs,
batch_size=batch_size,
)
# 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,))
_hid_decoded = decoder_hid(decoder_input)
_up_decoded = decoder_upsample(_hid_decoded)
_reshape_decoded = decoder_reshape(_up_decoded)
_deconv_1_decoded = decoder_deconv_1(_reshape_decoded)
_deconv_2_decoded = decoder_deconv_2(_deconv_1_decoded)
_x_decoded_relu = decoder_deconv_3_upsamp(_deconv_2_decoded)
_x_decoded_mean_squash = decoder_mean_squash(_x_decoded_relu)
generator = Model(decoder_input, _x_decoded_mean_squash)
vae.save('../models/object101_ld_%d_conv_%d_id_%d_e_%d_vae.h5' % (latent_dim, num_conv, intermediate_dim, epochs))
encoder.save('../models/object101_ld_%d_conv_%d_id_%d_e_%d_encoder.h5' % (latent_dim, num_conv, intermediate_dim, epochs))
generator.save('../models/object101_ld_%d_conv_%d_id_%d_e_%d_generator.h5' % (latent_dim, num_conv, intermediate_dim, epochs))
fname = '../models/object101_ld_%d_conv_%d_id_%d_e_%d_history.pkl' % (latent_dim, num_conv, intermediate_dim, epochs)
with open(fname, 'wb') as file_pi:
cPickle.dump(history.history, file_pi)
"""
# 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))
# linearly spaced coordinates on the unit square were transformed through the inverse CDF (ppf) of the Gaussian
# to produce values of the latent variables z, since the prior of the latent space is Gaussian
grid_x = norm.ppf(np.linspace(0.05, 0.95, n))
grid_y = norm.ppf(np.linspace(0.05, 0.95, n))
for i, yi in enumerate(grid_x):
for j, xi in enumerate(grid_y):
z_sample = np.array([[xi, yi]])
z_sample = np.tile(z_sample, batch_size).reshape(batch_size, 2)
x_decoded = generator.predict(z_sample, batch_size=batch_size)
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, cmap='Greys_r')
plt.show()
"""
