def model(word_len, sent_len, nclass):
unicode_size = 1000
ch_embed_dim = 20
h, w = valid(ch_embed_dim,
word_len,
stride=(1, 1),
kernel_size=(ch_embed_dim, 5))
h, w = valid(h, w, stride=(1, 1), kernel_size=(1, 5))
h, w = valid(h, w, stride=(1, 2), kernel_size=(1, 5))
conv_out_dim = int(h * w * 60)
X_ph = tf.placeholder('int32', [None, sent_len, word_len])
input_sn = tg.StartNode(input_vars=[X_ph])
charcnn_hn = tg.HiddenNode(prev=[input_sn],
layers=[
Reshape(shape=(-1, word_len)),
Embedding(cat_dim=unicode_size,
encode_dim=ch_embed_dim,
zero_pad=True),
Reshape(shape=(-1, ch_embed_dim, word_len,
1)),
Conv2D(input_channels=1,
num_filters=20,
padding='VALID',
kernel_size=(ch_embed_dim, 5),
stride=(1, 1)),
RELU(),
Conv2D(input_channels=20,
num_filters=40,
padding='VALID',
kernel_size=(1, 5),
stride=(1, 1)),
RELU(),
Conv2D(input_channels=40,
num_filters=60,
padding='VALID',
kernel_size=(1, 5),
stride=(1, 2)),
RELU(),
Flatten(),
Linear(conv_out_dim, nclass),
Reshape((-1, sent_len, nclass)),
ReduceSum(1),
Softmax()
])
output_en = tg.EndNode(prev=[charcnn_hn])
graph = tg.Graph(start=[input_sn], end=[output_en])
y_train_sb = graph.train_fprop()[0]
y_test_sb = graph.test_fprop()[0]
return X_ph, y_train_sb, y_test_sb
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
real_ph = tf.placeholder('float32', [None, self.h, self.w, 1],
name='real')
real_sn = tg.StartNode(input_vars=[real_ph])
# fake_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='fake')
# fake_sn = tg.StartNode(input_vars=[fake_ph])
disc_hn = tg.HiddenNode(
prev=[real_sn, self.gen_hn],
layers=[
Conv2D(input_channels=1,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/c1'),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/c2'),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/c3'),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, self.bottleneck_dim),
TFBatchNormalization(name=scope + '/l1'),
LeakyRELU(),
# Dropout(0.5),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim, 1),
# Sigmoid()
])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
# dis_var_list = graph.variables
# for var in dis_var_list:
# print var.name
graph = tg.Graph(start=[self.noise_sn, self.y_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
# print('========')
# for var in graph.variables:
# print var.name
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
# for var in dis_var_list:
# print(var.name)
#
# print('=========')
# for var in tf.global_variables():
# print(var.name)
# import pdb; pdb.set_trace()
# print()
# graph = tg.Graph(start=[G_sn], end=[class_en, judge_en])
# class_train_sb, judge_train_sb = graph.train_fprop() # symbolic outputs
# class_test_sb, judge_test_sb = graph.test_fprop() # symbolic outputs
return real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
def generator(self):
self.generator_called = True
with self.tf_graph.as_default():
scope = 'Generator'
with tf.name_scope(scope):
# X_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='X')
# X_sn = tg.StartNode(input_vars=[X_ph])
noise_ph = tf.placeholder('float32',
[None, self.bottleneck_dim],
name='noise')
self.noise_sn = tg.StartNode(input_vars=[noise_ph])
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
print('h1:{}, w1:{}'.format(h1, w1))
print('h2:{}, w2:{}'.format(h2, w2))
print('h3:{}, w3:{}'.format(h3, w3))
print('flat dim:{}'.format(flat_dim))
# enc_hn = tg.HiddenNode(prev=[X_sn],
# layers=[Conv2D(input_channels=1, num_filters=32, kernel_size=(5,5), stride=(1,1), padding='VALID'),
# RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
# # Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# # RELU(),
# Flatten(),
# Linear(flat_dim, 300),
# RELU(),
# # seq.add(Dropout(0.5))
# Linear(300, self.bottleneck_dim),
# Tanh(),
# ])
y_ph = tf.placeholder('float32', [None, self.nclass], name='y')
self.y_sn = tg.StartNode(input_vars=[y_ph])
noise_hn = tg.HiddenNode(prev=[self.noise_sn, self.y_sn],
input_merge_mode=Concat(1))
self.gen_hn = tg.HiddenNode(
prev=[noise_hn],
layers=[
Linear(self.bottleneck_dim + 10, flat_dim),
RELU(),
######[ Method 0 ]######
# Reshape((-1, h3, w3, 32)),
# Conv2D_Transpose(input_channels=32, num_filters=100, output_shape=(h2,w2),
# kernel_size=(5,5), stride=(2,2), padding='VALID'),
######[ End Method 0 ]######
######[ Method 1 ]######
Reshape((-1, 1, 1, flat_dim)),
Conv2D_Transpose(input_channels=flat_dim,
num_filters=200,
output_shape=(2, 2),
kernel_size=(2, 2),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/dc1'),
RELU(),
Conv2D_Transpose(input_channels=200,
num_filters=100,
output_shape=(h2, w2),
kernel_size=(9, 9),
stride=(1, 1),
padding='VALID'),
######[ End Method 1 ]######
TFBatchNormalization(name=scope + '/dc2'),
RELU(),
Conv2D_Transpose(input_channels=100,
num_filters=50,
output_shape=(h1, w1),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/dc3'),
RELU(),
Conv2D_Transpose(input_channels=50,
num_filters=1,
output_shape=(self.h, self.w),
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
SetShape((-1, self.h, self.w, 1)),
Sigmoid()
])
y_en = tg.EndNode(prev=[self.gen_hn])
graph = tg.Graph(start=[self.noise_sn, self.y_sn], end=[y_en])
G_train_sb = graph.train_fprop()[0]
G_test_sb = graph.test_fprop()[0]
# import pdb; pdb.set_trace()
gen_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return y_ph, noise_ph, G_train_sb, G_test_sb, gen_var_list
def generator(self):
self.generator_called = True
with self.tf_graph.as_default():
scope = 'Generator'
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
print('h1:{}, w1:{}'.format(h1, w1))
print('h2:{}, w2:{}'.format(h2, w2))
print('h3:{}, w3:{}'.format(h3, w3))
print('flat dim:{}'.format(flat_dim))
self.gen_real_sn = tg.StartNode(input_vars=[self.real_ph])
enc_hn = tg.HiddenNode(
prev=[self.gen_real_sn],
layers=[
Conv2D(input_channels=self.c,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc1'),
RELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc2'),
RELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/genc3'),
RELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, 300),
TFBatchNormalization(name=scope + '/genc4'),
RELU(),
Linear(300, self.bottleneck_dim),
Tanh(),
])
self.noise_sn = tg.StartNode(input_vars=[self.noise_ph])
self.gen_hn = tg.HiddenNode(
prev=[self.noise_sn, enc_hn],
input_merge_mode=Sum(),
layers=[
Linear(self.bottleneck_dim, flat_dim),
RELU(),
######[ Method 0 ]######
# Reshape((-1, h3, w3, 32)),
# Conv2D_Transpose(input_channels=32, num_filters=100, output_shape=(h2,w2),
# kernel_size=(5,5), stride=(2,2), padding='VALID'),
######[ End Method 0 ]######
######[ Method 1 ]######
Reshape((-1, 1, 1, flat_dim)),
# Reshape((-1, h))
Conv2D_Transpose(input_channels=flat_dim,
num_filters=200,
output_shape=(h3, w3),
kernel_size=(h3, w3),
stride=(1, 1),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=200, short_memory=0.01),
TFBatchNormalization(name=scope + '/g1'),
RELU(),
Conv2D_Transpose(input_channels=200,
num_filters=100,
output_shape=(h2, w2),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=100, short_memory=0.01),
######[ End Method 1 ]######
TFBatchNormalization(name=scope + '/g2'),
RELU(),
Conv2D_Transpose(input_channels=100,
num_filters=50,
output_shape=(h1, w1),
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
# BatchNormalization(layer_type='conv', dim=50, short_memory=0.01),
TFBatchNormalization(name=scope + '/g3'),
RELU(),
Conv2D_Transpose(input_channels=50,
num_filters=self.c,
output_shape=(self.h, self.w),
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
SetShape((-1, self.h, self.w, self.c)),
Sigmoid()
])
h, w = valid(self.h, self.w, kernel_size=(5, 5), stride=(1, 1))
h, w = valid(h, w, kernel_size=(5, 5), stride=(2, 2))
h, w = valid(h, w, kernel_size=(5, 5), stride=(2, 2))
h, w = valid(h, w, kernel_size=(h3, w3), stride=(1, 1))
y_en = tg.EndNode(prev=[self.gen_hn])
graph = tg.Graph(start=[self.noise_sn, self.gen_real_sn],
end=[y_en])
G_train_sb = graph.train_fprop()[0]
G_test_sb = graph.test_fprop()[0]
gen_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.y_ph, self.noise_ph, G_train_sb, G_test_sb, gen_var_list
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
dis_real_sn = tg.StartNode(input_vars=[self.real_ph])
# fake_ph = tf.placeholder('float32', [None, self.h, self.w, 1], name='fake')
# fake_sn = tg.StartNode(input_vars=[fake_ph])
disc_hn = tg.HiddenNode(
prev=[dis_real_sn, self.gen_hn],
layers=[
Conv2D(input_channels=self.c,
num_filters=32,
kernel_size=(5, 5),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d1'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/d2'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
Conv2D(input_channels=32,
num_filters=32,
kernel_size=(5, 5),
stride=(2, 2),
padding='VALID'),
TFBatchNormalization(name=scope + '/d3'),
# BatchNormalization(layer_type='conv', dim=32, short_memory=0.01),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=32, kernel_size=(5,5), stride=(2,2), padding='VALID'),
# RELU(),
Flatten(),
Linear(flat_dim, self.bottleneck_dim),
# BatchNormalization(layer_type='fc', dim=self.bottleneck_dim, short_memory=0.01),
TFBatchNormalization(name=scope + '/d4'),
LeakyRELU(),
# Dropout(0.5),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[Linear(self.bottleneck_dim, 1),
Sigmoid()])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[dis_real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
graph = tg.Graph(start=[self.noise_sn, self.gen_real_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list
def discriminator(self):
if not self.generator_called:
raise Exception(
'self.generator() has to be called first before self.discriminator()'
)
scope = 'Discriminator'
with self.tf_graph.as_default():
with tf.name_scope(scope):
h1, w1 = valid(self.h,
self.w,
kernel_size=(5, 5),
stride=(1, 1))
h2, w2 = valid(h1, w1, kernel_size=(5, 5), stride=(2, 2))
h3, w3 = valid(h2, w2, kernel_size=(5, 5), stride=(2, 2))
flat_dim = int(h3 * w3 * 32)
h1, w1 = valid(self.char_embed_dim,
self.word_len,
kernel_size=(self.char_embed_dim, 3),
stride=(1, 1))
print('h1:{}, w1:{}'.format(h1, w1))
h2, w2 = valid(h1, w1, kernel_size=(1, 3), stride=(1, 1))
print('h2:{}, w2:{}'.format(h2, w2))
h3, w3 = valid(h2, w2, kernel_size=(1, 3), stride=(1, 1))
print('h3:{}, w3:{}'.format(h3, w3))
# h4, w4 = valid(h3, w3, kernel_size=(1,6), stride=(1,1))
# print('h4:{}, w4:{}'.format(h4, w4))
# hf, wf = h4, w4
hf, wf = h3, w3
n_filters = 100
real_sn = tg.StartNode(input_vars=[self.real_ph])
real_hn = tg.HiddenNode(prev=[real_sn],
layers=[
OneHot(self.char_embed_dim),
Transpose(perm=[0, 3, 2, 1])
])
disc_hn = tg.HiddenNode(
prev=[real_hn, self.gen_hn],
layers=[
Conv2D(input_channels=self.sent_len,
num_filters=100,
kernel_size=(self.char_embed_dim, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d1'),
LeakyRELU(),
Conv2D(input_channels=100,
num_filters=100,
kernel_size=(1, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d2'),
LeakyRELU(),
Conv2D(input_channels=100,
num_filters=100,
kernel_size=(1, 3),
stride=(1, 1),
padding='VALID'),
TFBatchNormalization(name=scope + '/d3'),
LeakyRELU(),
# Conv2D(input_channels=32, num_filters=128, kernel_size=(1,6), stride=(1,1), padding='VALID'),
# RELU(),
Flatten(),
Linear(int(hf * wf * n_filters), self.bottleneck_dim),
TFBatchNormalization(name=scope + '/d4'),
LeakyRELU(),
])
class_hn = tg.HiddenNode(prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim,
self.nclass),
Softmax()
])
judge_hn = tg.HiddenNode(
prev=[disc_hn],
layers=[
Linear(self.bottleneck_dim, 1),
# Sigmoid()
])
real_class_en = tg.EndNode(prev=[class_hn])
real_judge_en = tg.EndNode(prev=[judge_hn])
fake_class_en = tg.EndNode(prev=[class_hn])
fake_judge_en = tg.EndNode(prev=[judge_hn])
graph = tg.Graph(start=[real_sn],
end=[real_class_en, real_judge_en])
real_train = graph.train_fprop()
real_valid = graph.test_fprop()
graph = tg.Graph(start=[self.noise_sn],
end=[fake_class_en, fake_judge_en])
fake_train = graph.train_fprop()
fake_valid = graph.test_fprop()
dis_var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=scope)
return self.real_ph, real_train, real_valid, fake_train, fake_valid, dis_var_list