def __init__(self, args):
self.input_shape = 28
self.num_classes = 2
self.latent_dim = 100
optimizer = Adam(0.0002, 0.5)
# Build and compile the discriminator
self.discriminator = self.build_discriminator()
self.discriminator.compile(
loss=['binary_crossentropy', 'categorical_crossentropy'],
loss_weights=[0.5, 0.5],
optimizer=optimizer,
metrics=['accuracy'])
# Build the generator
self.generator = self.build_generator()
# The generator takes noise as input and generates imgs
noise = Input(shape=(64, ))
img = self.generator(noise)
# For the combined model we will only train the generator
self.discriminator.trainable = False
# The valid takes generated images as input and determines validity
valid, _ = self.discriminator(img)
# The combined model (stacked generator and discriminator)
# Trains generator to fool discriminator
self.combined = Model(noise, valid)
self.combined.compile(loss=['binary_crossentropy'],
optimizer=optimizer)
def __init__(self,Name,LearningRate = 0.0001,img_shape,latent_dim):
self.Name = Name
self.LearningRate = LearningRate
self.img_shape = img_shape
self.latent_dim = latent_dims
self.trained = 0
#self.source_img = tf.Variable()
#self.target_img = tf.Variable()
self.g_optimizer = Adam(learning_rate=self.LearningRate)
self.d_optimizer = Adam(learning_rate=self.LearningRate)
self.optimizer = Adam(learning_rate = self.LearningRate)
# compile the IR Disciminator model - Target
self.IR_discriminator = self.discriminator_network()
self.IR_discriminator.compile(optimizer=self.optimizer,loss='binary_crossentropy',metric=['accuracy'])
# compile the IR Generator model - Target
self.IR_f_net = self.feature_extractor_network()
self.IR_g_net = self.generator_network()(self.IR_f_net)
self.IR_generator = Model(inputs = in_image_IR, outputs = self.IR_g_net)
self.IR_generator.compile(optimizer=self.optimizer,loss='binary_crossentropy',metric=['accuracy'])
# compile the Visual Disciminator model - Source
self.Visual_discriminator = self.discriminator_network()
self.Visual_discriminator.compile(optimizer=self.optimizer,loss='binary_crossentropy',metric=['accuracy'])
# compile the Visual Generator model - Visual
self.Visual_f_net = self.feature_extractor_network()
self.Visual_g_net = self.generator_network()(self.Visual_f_net)
self.Visual_generator = Model(inputs = in_image_Vis, outputs = self.Visual_g_net)
self.Visual_generator.compile(optimizer=self.optimizer,loss='binary_crossentropy',metric=['accuracy'])
def feature_extractor_network(self):
# input
in_image = Input(shape = in_shape)
# C1 Layer
nett = Conv2D(32,(5,5))(in_image)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# M2 Layer
nett = MaxPooling2D(pool_size = (3,3))(nett)
# C3 Layer
nett = Conv2D(64,(3,3))
nett = BatchNormalization(pool_size = (3,3))(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# L4 Layer
nett = LocallyConnected2D(128,(3,3))(nett)
# L5 Layer
nett = LocallyConnected2D(256,(3,3))(nett)
# F6 Layer
nett = Dense(512,activation='relu')(nett)
nett = Dropout(0.2)(nett)
# F7 Layer
out_features = Dense(activation='tanh')(nett)
# output
model = Model(inputs = in_image, outputs = out_features)
return model
def build_discriminator(self):
model = Sequential()
model.add(Dense(78, activation="relu", input_dim=self.input_shape))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(56, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(32, activation="relu"))
model.add(Dropout(rate=0.3))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(28, activation="relu"))
model.add(Dropuout(rate=0.3))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(10, activation="relu"))
model.summary()
img = Input(shape=self.img_shape)
features = model(img)
valid = Dense(1, activation="sigmoid")(features)
label = Dense(self.num_classes + 1, activation="softmax")(features)
return Model(img, [valid, label])
def build_model(self):
gyr_x, gyr_y, gyr_z, lacc_x, lacc_y, lacc_z, mag_x, mag_y, mag_z = self.input_layer()
gyr_x_cnn, gyr_y_cnn, gyr_z_cnn, lacc_x_cnn, lacc_y_cnn, lacc_z_cnn, mag_x_cnn, mag_y_cnn, mag_z_cnn = self.residual_layer(
gyr_x, gyr_y, gyr_z, lacc_x, lacc_y, lacc_z, mag_x, mag_y, mag_z)
all_resnet = self.cnn_layer(gyr_x_cnn, gyr_y_cnn, gyr_z_cnn, lacc_x_cnn, lacc_y_cnn, lacc_z_cnn, mag_x_cnn,
mag_y_cnn, mag_z_cnn)
lstm = self.lstm_layer(all_resnet)
lstm = self.attention_layer(lstm)
output = self.mlp_layer(lstm)
model = Model(inputs=[
gyr_x, gyr_y, gyr_z,
lacc_x, lacc_y, lacc_z,
mag_x, mag_y, mag_z
],
outputs=[output])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
return model
def main1():
# Load the data
train_data, train_label, validation_data, validation_label, test_data, test_label = data_preparation_moe(
)
num_features = train_data.shape[1]
print('Training data shape = {}'.format(train_data.shape))
print('Validation data shape = {}'.format(validation_data.shape))
print('Test data shape = {}'.format(test_data.shape))
#print('Training laebl shape = {}'.format(len(train_label)))
# Set up the input layer
input_layer = Input(shape=(num_features, ))
# Set up MMoE layer
mmoe_layers = MMoE(units=16, num_experts=8, num_tasks=2)(input_layer)
output_layers = []
output_info = ['y0', 'y1']
# Build tower layer from MMoE layer
for index, task_layer in enumerate(mmoe_layers):
tower_layer = Dense(units=8,
activation='relu',
kernel_initializer=VarianceScaling())(task_layer)
output_layer = Dense(units=1,
name=output_info[index],
activation='linear',
kernel_initializer=VarianceScaling())(tower_layer)
output_layers.append(output_layer)
# Compile model
model = Model(inputs=[input_layer], outputs=output_layers)
learning_rates = [1e-4, 1e-3, 1e-2]
adam_optimizer = Adam(lr=learning_rates[0])
model.compile(loss={
'y0': 'mean_squared_error',
'y1': 'mean_squared_error'
},
optimizer=adam_optimizer,
metrics=[metrics.mae])
# Print out model architecture summary
model.summary()
# Train the model
model.fit(x=train_data,
y=train_label,
validation_data=(validation_data, validation_label),
epochs=100)
return model
def create_autoencoder(input_dim, encoding_dim):
"""
Args:
input_dim: dimension of one-hot encoded categorical features
encoding_dim: dimension of encoded data(hidden layer representation)
Return:
model
"""
one_hot_in = Input(shape=(input_dim, ), name='input', sparse=True)
X = Dense(HIDDEN_UNITS, activation='selu')(one_hot_in)
encoding = Dense(encoding_dim, activation='selu', name='enco')(X)
X = Dense(HIDDEN_UNITS, activation='selu')(encoding)
output = Dense(input_dim, activation='sigmoid')(X)
model = Model(inputs=one_hot_in, outputs=output)
return model
def build_generator(self):
model = Sequential()
model.add(Dense(78, activation="relu", input_dim=self.latent_dim))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(56, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(32, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(28, activation="tanh"))
model.summary()
noise = Input(shape=(self.latent_dim, ))
img = model(noise)
return Model(noise, img)
def generator_network(self):
# input
in_latents = Input(shape = (self.latent_dim,))
#DC1
nett = Conv2DTranspose(512,(3,3))(in_latents)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
#DC2
nett = Conv2DTranspose(128,(3,3))(nett)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
#DC3
nett = Conv2DTranspose(64,(3,3))
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
#DC4
nett = Conv2DTranspose(32,(5,5))(nett)
nett = BatchNormalization()(nett)
out_image = Dense(alpha = 0.2)(nett)
#output
model = Model(inputs = in_latents, outputs = out_image)
return model
def discriminator_network(self):
# input
in_image = Input(shape=self.img_shape)
# C1 layer
nett = Conv2D(64,(5,5))(in_image)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
# C2 layer
nett = Conv2D(128,(5,5))(nett)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
nett = Dropout(0.2)(nett)
# C3 layer
nett = Conv2D(256,(5,5))(nett)
nett = BatchNormalization()(nett)
nett = LeakyReLU(alpha = 0.2)(nett)
nett = Dropout(0.2)(nett)
# F4 layer
nett = Flatten()(nett)
validity = Dense(1,alpha = 0.2)(nett)
#output
model = Model(inputs = in_image, outputs = validity)
return model
def compiled_tcn(num_feat, # type: int
num_classes, # type: int
nb_filters, # type: int
kernel_size, # type: int
dilations, # type: List[int]
nb_stacks, # type: int
max_len, # type: int
padding='causal', # type: str
use_skip_connections=True, # type: bool
return_sequences=True,
regression=False, # type: bool
dropout_rate=0.05, # type: float
name='tcn', # type: str,
opt='adam',
lr=0.002):
# type: (...) -> keras.Model
"""Creates a compiled TCN model for a given task (i.e. regression or classification).
Classification uses a sparse categorical loss. Please input class ids and not one-hot encodings.
Args:
num_feat: The number of features of your input, i.e. the last dimension of: (batch_size, timesteps, input_dim).
num_classes: The size of the final dense layer, how many classes we are predicting.
nb_filters: The number of filters to use in the convolutional layers.
kernel_size: The size of the kernel to use in each convolutional layer.
dilations: The list of the dilations. Example is: [1, 2, 4, 8, 16, 32, 64].
nb_stacks : The number of stacks of residual blocks to use.
max_len: The maximum sequence length, use None if the sequence length is dynamic.
padding: The padding to use in the convolutional layers.
use_skip_connections: Boolean. If we want to add skip connections from input to each residual block.
return_sequences: Boolean. Whether to return the last output in the output sequence, or the full sequence.
regression: Whether the output should be continuous or discrete.
use_separable_convolutions: whether to use these instead of normal conv layers for optimizing parameter count
dropout_rate: Float between 0 and 1. Fraction of the input units to drop.
name: Name of the model. Useful when having multiple TCN.
opt: Optimizer name.
lr: Learning rate.
Returns:
A compiled keras TCN.
"""
dilations = process_dilations(dilations)
input_layer = Input(shape=(max_len, num_feat))
x = TCN(nb_filters, kernel_size, nb_stacks, dilations, padding,
use_skip_connections, dropout_rate, return_sequences, name)(input_layer)
print('x.shape=', x.shape)
def get_opt():
return tf.train.AdamOptimizer(learning_rate=1e-3, )
if not regression:
# classification
x = Dense(num_classes)(x)
x = Activation('softmax')(x)
output_layer = x
model = Model(input_layer, output_layer)
model.compile(get_opt(), loss='sparse_categorical_crossentropy', metrics=[accuracy])
else:
# regression
x = Dense(1)(x)
x = Activation('linear')(x)
output_layer = x
model = Model(input_layer, output_layer)
model.compile(get_opt(), loss='mean_squared_error')
print(f'model.x = {input_layer.shape}')
print(f'model.y = {output_layer.shape}')
return model
def createModel(patchSize, numClasses, usingClassification=False):
if K.image_data_format() == 'channels_last':
bn_axis = -1
else:
bn_axis = 1
input_tensor = Input(shape=(patchSize[0], patchSize[1], patchSize[2], 1))
# first stage
x = Conv3D(filters=16,
kernel_size=(5, 5, 5),
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal')(input_tensor)
x = BatchNormalization(axis=bn_axis)(x)
x_after_stage_1 = LeakyReLU(alpha=0.01)(x)
#x_after_stage_1 = Add()([input_tensor, x])
# first down convolution
x_down_conv_1 = projection_block_3D(x_after_stage_1,
filters=(32, 32),
kernel_size=(2, 2, 2),
stage=1,
block=1,
se_enabled=True,
se_ratio=4)
# second stage
x = identity_block_3D(x_down_conv_1,
filters=(32, 32),
kernel_size=(3, 3, 3),
stage=2,
block=1,
se_enabled=True,
se_ratio=4)
x_after_stage_2 = identity_block_3D(x,
filters=(32, 32),
kernel_size=(3, 3, 3),
stage=2,
block=2,
se_enabled=True,
se_ratio=4)
# second down convolution
x_down_conv_2 = projection_block_3D(x_after_stage_2,
filters=(64, 64),
kernel_size=(2, 2, 2),
stage=2,
block=3,
se_enabled=True,
se_ratio=8)
# third stage
x = identity_block_3D(x_down_conv_2,
filters=(64, 64),
kernel_size=(3, 3, 3),
stage=3,
block=1,
se_enabled=True,
se_ratio=8)
x_after_stage_3 = identity_block_3D(x,
filters=(64, 64),
kernel_size=(3, 3, 3),
stage=3,
block=2,
se_enabled=True,
se_ratio=8)
#x = identity_block_3D(x, filters=(64, 64), kernel_size=(3, 3, 3), stage=3, block=3, se_enabled=False, se_ratio=16)
# third down convolution
x_down_conv_3 = projection_block_3D(x_after_stage_3,
filters=(128, 128),
kernel_size=(2, 2, 2),
stage=3,
block=4,
se_enabled=True,
se_ratio=16)
# fourth stage
x = identity_block_3D(x_down_conv_3,
filters=(128, 128),
kernel_size=(3, 3, 3),
stage=4,
block=1,
se_enabled=True,
se_ratio=16)
x_after_stage_4 = identity_block_3D(x,
filters=(128, 128),
kernel_size=(3, 3, 3),
stage=4,
block=2,
se_enabled=True,
se_ratio=16)
#x = identity_block_3D(x, filters=(128, 128), kernel_size=(3, 3, 3), stage=4, block=3, se_enabled=False, se_ratio=16)
### end of encoder path
if usingClassification:
# use x_after_stage_4 as quantification output
# global average pooling
x_class = GlobalAveragePooling3D(
data_format=K.image_data_format())(x_after_stage_4)
# fully-connected layer
classification_output = Dense(units=numClasses,
activation='softmax',
kernel_initializer='he_normal',
name='classification_output')(x_class)
### decoder path
# first 3D upsampling
x = UpSampling3D(size=(2, 2, 2),
data_format=K.image_data_format())(x_after_stage_4)
x = Conv3D(filters=64,
kernel_size=(3, 3, 3),
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal')(x)
x = BatchNormalization(axis=bn_axis)(x)
x = LeakyReLU(alpha=0.01)(x)
x = concatenate([x, x_after_stage_3], axis=bn_axis)
# first decoder stage
x = identity_block_3D(x,
filters=(128, 128),
kernel_size=(3, 3, 3),
stage=6,
block=1,
se_enabled=True,
se_ratio=16)
x = identity_block_3D(x,
filters=(128, 128),
kernel_size=(3, 3, 3),
stage=6,
block=2,
se_enabled=True,
se_ratio=16)
# second 3D upsampling
x = UpSampling3D(size=(2, 2, 2), data_format=K.image_data_format())(x)
x = Conv3D(filters=32,
kernel_size=(3, 3, 3),
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal')(x)
x = BatchNormalization(axis=bn_axis)(x)
x = LeakyReLU(alpha=0.01)(x)
x = concatenate([x, x_after_stage_2], axis=bn_axis)
# second decoder stage
x = identity_block_3D(x,
filters=(64, 64),
kernel_size=(3, 3, 3),
stage=7,
block=1,
se_enabled=True,
se_ratio=8)
x = identity_block_3D(x,
filters=(64, 64),
kernel_size=(3, 3, 3),
stage=7,
block=2,
se_enabled=True,
se_ratio=8)
# third 3D upsampling
x = UpSampling3D(size=(2, 2, 2), data_format=K.image_data_format())(x)
x = Conv3D(filters=16,
kernel_size=(3, 3, 3),
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal')(x)
x = BatchNormalization(axis=bn_axis)(x)
x = LeakyReLU(alpha=0.01)(x)
x = concatenate([x, x_after_stage_1], axis=bn_axis)
# third decoder stage
x = identity_block_3D(x,
filters=(32, 32),
kernel_size=(3, 3, 3),
stage=9,
block=1,
se_enabled=True,
se_ratio=4)
#x = identity_block_3D(x, filters=(32, 32), kernel_size=(3, 3, 3), stage=9, block=2, se_enabled=True, se_ratio=4)
### End of decoder
### last segmentation segments
# 1x1x1-Conv3 produces 2 featuremaps for probabilistic segmentations of the foreground and background
x = Conv3D(filters=2,
kernel_size=(1, 1, 1),
strides=(1, 1, 1),
padding='same',
kernel_initializer='he_normal',
name='conv_veryEnd')(x)
#x = BatchNormalization(axis=bn_axis)(x) # warum leakyrelu vor softmax?
#x = LeakyReLU(alpha=0.01)(x)
segmentation_output = Softmax(axis=bn_axis, name='segmentation_output')(x)
#segmentation_output = keras.layers.activations.sigmoid(x)
# create model
if usingClassification:
cnn = Model(inputs=[input_tensor],
outputs=[segmentation_output, classification_output],
name='3D-VResFCN-Classification')
sModelName = cnn.name
else:
cnn = Model(inputs=[input_tensor],
outputs=[segmentation_output],
name='3D-VResFCN')
sModelName = cnn.name
return cnn, sModelName
def perceptual_loss(y_true, y_pred):
vgg = VGG16(include=False, weights="imagenet", input_shape=image_shape)
loss_model = Model(inputs=vgg.input, outputs=vgg.get_layer("block3_conv3").output)
loss_model.trainable = False
return tf.reduce_mean(tf.square(loss_model(y_true), loss_model(y_pred)))
encoder_embedding = Embedding(vocab_size, 200, mask_zero=True)(encoder_inputs)
#参考链接：嵌入层 Embedding<https://keras.io/zh/layers/embeddings/#embedding>
encoder_outputs, state_h, state_c = tf.keras.layers.LSTM(
200, return_state=True)(encoder_embedding)
#参考链接：https://keras.io/zh/layers/recurrent/#lstm
encoder_states = [state_h, state_c]
decoder_inputs = Input(shape=(None, ))
decoder_embedding = Embedding(vocab_size, 200, mask_zero=True)(decoder_inputs)
decoder_lstm = LSTM(200, return_state=True, return_sequences=True)
decoder_outputs, _, _ = decoder_lstm(decoder_embedding,
initial_state=encoder_states)
decoder_dense = Dense(vocab_size, activation=tf.keras.activations.softmax)
output = decoder_dense(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], output)
model.compile(optimizer=optimizers.RMSprop(),
loss='categorical_crossentropy',
metrics=['accuracy'])
#参考链接：RMSprop<https://keras.io/zh/optimizers/#rmsprop>
#categorical_crossentropy<https://keras.io/zh/backend/#categorical_crossentropy>
model.summary()
# 模型训练以及保存
model.fit([encoder_input_data, decoder_input_data],
decoder_output_data,
batch_size=50,
epochs=150)
model.save('model.h5')
class SGAN:
def __init__(self, args):
self.input_shape = 28
self.num_classes = 2
self.latent_dim = 100
optimizer = Adam(0.0002, 0.5)
# Build and compile the discriminator
self.discriminator = self.build_discriminator()
self.discriminator.compile(
loss=['binary_crossentropy', 'categorical_crossentropy'],
loss_weights=[0.5, 0.5],
optimizer=optimizer,
metrics=['accuracy'])
# Build the generator
self.generator = self.build_generator()
# The generator takes noise as input and generates imgs
noise = Input(shape=(64, ))
img = self.generator(noise)
# For the combined model we will only train the generator
self.discriminator.trainable = False
# The valid takes generated images as input and determines validity
valid, _ = self.discriminator(img)
# The combined model (stacked generator and discriminator)
# Trains generator to fool discriminator
self.combined = Model(noise, valid)
self.combined.compile(loss=['binary_crossentropy'],
optimizer=optimizer)
def build_generator(self):
model = Sequential()
model.add(Dense(78, activation="relu", input_dim=self.latent_dim))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(56, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(32, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(28, activation="tanh"))
model.summary()
noise = Input(shape=(self.latent_dim, ))
img = model(noise)
return Model(noise, img)
def build_discriminator(self):
model = Sequential()
model.add(Dense(78, activation="relu", input_dim=self.input_shape))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(56, activation="relu"))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(32, activation="relu"))
model.add(Dropout(rate=0.3))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(28, activation="relu"))
model.add(Dropuout(rate=0.3))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(10, activation="relu"))
model.summary()
img = Input(shape=self.img_shape)
features = model(img)
valid = Dense(1, activation="sigmoid")(features)
label = Dense(self.num_classes + 1, activation="softmax")(features)
return Model(img, [valid, label])
def train(self, epochs, batch_size=100, sample_interval=50):
# Load the dataset
data = data_load("credit_fraud_sampled.csv")
x_train, y_train = data[:2]
x_val, y_val = data[2:4]
x_test, y_test = data[4:]
# Class weights:
# To balance the difference in occurences of digit class labels.
# 50% of labels that the discriminator trains on are 'fake'.
# Weight = 1 / frequency
half_batch = batch_size // 2
cw1 = {0: 1, 1: 1}
cw2 = {
i: self.num_classes / half_batch
for i in range(self.num_classes)
}
cw2[self.num_classes] = 1 / half_batch
# Adversarial ground truths
valid = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for epoch in range(epochs):
# ---------------------
# Train Discriminator
# ---------------------
# Select a random batch of images
idx = np.random.randint(0, X_train.shape[0], batch_size)
imgs = X_train[idx]
# Sample noise and generate a batch of new images
noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# One-hot encoding of labels
labels = to_categorical(y_train[idx],
num_classes=self.num_classes + 1)
fake_labels = to_categorical(np.full((batch_size, 1),
self.num_classes),
num_classes=self.num_classes + 1)
# Train the discriminator
d_loss_real = self.discriminator.train_on_batch(
imgs, [valid, labels], class_weight=[cw1, cw2])
d_loss_fake = self.discriminator.train_on_batch(
gen_imgs, [fake, fake_labels], class_weight=[cw1, cw2])
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
# ---------------------
# Train Generator
# ---------------------
g_loss = self.combined.train_on_batch(noise,
valid,
class_weight=[cw1, cw2])
# Plot the progress
if epoch % 100 == 0:
print(
"%d [D loss: %f, acc: %.2f%%, op_acc: %.2f%%] [G loss: %f]"
% (epoch, d_loss[0], 100 * d_loss[3], 100 * d_loss[4],
g_loss))
# If at save interval => save generated image samples
if epoch % sample_interval == 0:
self.sample_images(epoch)
def sample_images(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i, j].imshow(gen_imgs[cnt, :, :, 0], cmap='gray')
axs[i, j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()
def save_model(self):
def save(model, model_name):
model_path = "saved_model/%s.json" % model_name
weights_path = "saved_model/%s_weights.hdf5" % model_name
options = {"file_arch": model_path, "file_weight": weights_path}
json_string = model.to_json()
open(options['file_arch'], 'w').write(json_string)
model.save_weights(options['file_weight'])
save(self.generator, "mnist_sgan_generator")
save(self.discriminator, "mnist_sgan_discriminator")
save(self.combined, "mnist_sgan_adversarial")
def __init__(self,
n_word_vocab=50001,
n_role_vocab=7,
n_factors_emb=256,
n_factors_cls=512,
n_hidden=256,
word_vocabulary={},
role_vocabulary={},
unk_word_id=50000,
unk_role_id=7,
missing_word_id=50001,
using_dropout=False,
dropout_rate=0.3,
optimizer='adagrad',
loss='sparse_categorical_crossentropy',
metrics=['accuracy']):
super(NNRF, self).__init__(n_word_vocab, n_role_vocab, n_factors_emb,
n_hidden, word_vocabulary, role_vocabulary,
unk_word_id, unk_role_id, missing_word_id,
using_dropout, dropout_rate, optimizer,
loss, metrics)
# minus 1 here because one of the role is target role
self.input_length = n_role_vocab - 1
# each input is a fixed window of frame set, each word correspond to one role
input_words = Input(
shape=(self.input_length, ), dtype=tf.uint32,
name='input_words') # Switched dtype to tf specific (team1-change)
input_roles = Input(
shape=(self.input_length, ), dtype=tf.uint32,
name='input_roles') # Switched dtype to tf specific (team1-change)
target_role = Input(
shape=(1, ), dtype=tf.uint32,
name='target_role') # Switched dtype to tf specific (team1-change)
# role based embedding layer
embedding_layer = role_based_word_embedding(
input_words, input_roles, n_word_vocab, n_role_vocab,
glorot_uniform(), missing_word_id, self.input_length,
n_factors_emb, True, using_dropout, dropout_rate)
# sum on input_length direction;
# obtaining context embedding layer, shape is (batch_size, n_factors_emb)
event_embedding = Lambda(
lambda x: K.sum(x, axis=1),
name='event_embedding',
output_shape=(n_factors_emb, ))(embedding_layer)
# fully connected layer, output shape is (batch_size, input_length, n_hidden)
hidden = Dense(n_hidden,
activation='linear',
input_shape=(n_factors_emb, ),
name='projected_event_embedding')(event_embedding)
# non-linear layer, using 1 to initialize
non_linearity = PReLU(alpha_initializer='ones',
name='context_embedding')(hidden)
# hidden layer
hidden_layer2 = target_word_hidden(non_linearity,
target_role,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_factors_cls,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# softmax output layer
output_layer = Dense(n_word_vocab,
activation='softmax',
input_shape=(n_factors_cls, ),
name='softmax_word_output')(hidden_layer2)
self.model = Model(inputs=[input_words, input_roles, target_role],
outputs=[output_layer])
self.model.compile(optimizer, loss, metrics)
class NNRF(GenericModel):
"""Non-incremental model role-filler
"""
def __init__(self,
n_word_vocab=50001,
n_role_vocab=7,
n_factors_emb=256,
n_factors_cls=512,
n_hidden=256,
word_vocabulary={},
role_vocabulary={},
unk_word_id=50000,
unk_role_id=7,
missing_word_id=50001,
using_dropout=False,
dropout_rate=0.3,
optimizer='adagrad',
loss='sparse_categorical_crossentropy',
metrics=['accuracy']):
super(NNRF, self).__init__(n_word_vocab, n_role_vocab, n_factors_emb,
n_hidden, word_vocabulary, role_vocabulary,
unk_word_id, unk_role_id, missing_word_id,
using_dropout, dropout_rate, optimizer,
loss, metrics)
# minus 1 here because one of the role is target role
self.input_length = n_role_vocab - 1
# each input is a fixed window of frame set, each word correspond to one role
input_words = Input(
shape=(self.input_length, ), dtype=tf.uint32,
name='input_words') # Switched dtype to tf specific (team1-change)
input_roles = Input(
shape=(self.input_length, ), dtype=tf.uint32,
name='input_roles') # Switched dtype to tf specific (team1-change)
target_role = Input(
shape=(1, ), dtype=tf.uint32,
name='target_role') # Switched dtype to tf specific (team1-change)
# role based embedding layer
embedding_layer = role_based_word_embedding(
input_words, input_roles, n_word_vocab, n_role_vocab,
glorot_uniform(), missing_word_id, self.input_length,
n_factors_emb, True, using_dropout, dropout_rate)
# sum on input_length direction;
# obtaining context embedding layer, shape is (batch_size, n_factors_emb)
event_embedding = Lambda(
lambda x: K.sum(x, axis=1),
name='event_embedding',
output_shape=(n_factors_emb, ))(embedding_layer)
# fully connected layer, output shape is (batch_size, input_length, n_hidden)
hidden = Dense(n_hidden,
activation='linear',
input_shape=(n_factors_emb, ),
name='projected_event_embedding')(event_embedding)
# non-linear layer, using 1 to initialize
non_linearity = PReLU(alpha_initializer='ones',
name='context_embedding')(hidden)
# hidden layer
hidden_layer2 = target_word_hidden(non_linearity,
target_role,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_factors_cls,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# softmax output layer
output_layer = Dense(n_word_vocab,
activation='softmax',
input_shape=(n_factors_cls, ),
name='softmax_word_output')(hidden_layer2)
self.model = Model(inputs=[input_words, input_roles, target_role],
outputs=[output_layer])
self.model.compile(optimizer, loss, metrics)
def set_0_bias(self):
""" This function is used as a hack that set output bias to 0.
According to Ottokar's advice in the paper, during the *evaluation*, the output bias needs to be 0
in order to replicate the best performance reported in the paper.
"""
word_output_weights = self.model.get_layer(
"softmax_word_output").get_weights()
word_output_kernel = word_output_weights[0]
word_output_bias = np.zeros(self.n_word_vocab)
self.model.get_layer("softmax_word_output").set_weights(
[word_output_kernel, word_output_bias])
return word_output_weights[1]
def set_bias(self, bias):
word_output_weights = self.model.get_layer(
"softmax_word_output").get_weights()
word_output_kernel = word_output_weights[0]
self.model.get_layer("softmax_word_output").set_weights(
[word_output_kernel, bias])
return bias
# Deprecated temporarily
def train(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
batch_size=256,
epochs=100,
validation_split=0.05,
verbose=0):
train_result = self.model.fit([i_w, i_r, t_r], t_w_c, batch_size,
epochs, validation_split, verbose)
return train_result
def test(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
batch_size=256,
verbose=0):
test_result = self.model.evaluate([i_w, i_r, t_r], t_w_c, batch_size,
verbose)
return test_result
def train_on_batch(self, i_w, i_r, t_w, t_r, t_w_c, t_r_c):
train_result = self.model.train_on_batch([i_w, i_r, t_r], t_w_c)
return train_result
def test_on_batch(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
sample_weight=None):
test_result = self.model.test_on_batch([i_w, i_r, t_r], t_w_c,
sample_weight)
return test_result
def predict(self, i_w, i_r, t_r, batch_size=1, verbose=0):
""" Return the output from softmax layer. """
predict_result = self.model.predict([i_w, i_r, t_r], batch_size,
verbose)
return predict_result
def summary(self):
self.model.summary()
def predict_class(self, i_w, i_r, t_r, batch_size=1, verbose=0):
""" Return predicted target word from prediction. """
predict_result = self.predict(i_w, i_r, t_r, batch_size, verbose)
return np.argmax(predict_result, axis=1)
def p_words(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return the output scores given target words. """
predict_result = self.predict(i_w, i_r, t_r, batch_size, verbose)
return predict_result[range(batch_size), list(t_w)]
def top_words(self, i_w, i_r, t_r, topN=20, batch_size=1, verbose=0):
""" Return top N target words given context. """
predict_result = self.predict(i_w, i_r, t_r, batch_size, verbose)
rank_list = np.argsort(predict_result, axis=1)
return [r[-topN:][::-1] for r in rank_list]
def list_top_words(self, i_w, i_r, t_r, topN=20, batch_size=1, verbose=0):
""" Return a list of decoded top N target words.
(Only for reference, can be removed.)
"""
top_words_lists = self.top_words(i_w, i_r, t_r, topN, batch_size,
verbose)
print(
type(top_words_lists)) # Updated to python3 syntax (team1-change)
result = []
for i in range(batch_size):
top_words_list = top_words_lists[i]
result.append([self.word_decoder[w] for w in top_words_list])
return result
def __init__(self,
n_word_vocab=50001,
n_role_vocab=7,
n_factors_emb=300,
n_hidden=300,
word_vocabulary=None,
role_vocabulary=None,
unk_word_id=50000,
unk_role_id=7,
missing_word_id=50001,
using_dropout=False,
dropout_rate=0.3,
optimizer='adagrad',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
loss_weights=[1., 1.]):
super(MTRFv4, self).__init__(n_word_vocab, n_role_vocab, n_factors_emb,
n_hidden, word_vocabulary,
role_vocabulary, unk_word_id, unk_role_id,
missing_word_id, using_dropout,
dropout_rate, optimizer, loss, metrics)
# minus 1 here because one of the role is target role
input_length = n_role_vocab - 1
n_factors_cls = n_hidden
# each input is a fixed window of frame set, each word correspond to one role
input_words = Input(
shape=(input_length, ), dtype=tf.uint32,
name='input_words') # Switched dtype to tf specific (team1-change)
input_roles = Input(
shape=(input_length, ), dtype=tf.uint32,
name='input_roles') # Switched dtype to tf specific (team1-change)
target_word = Input(
shape=(1, ), dtype=tf.uint32,
name='target_word') # Switched dtype to tf specific (team1-change)
target_role = Input(
shape=(1, ), dtype=tf.uint32,
name='target_role') # Switched dtype to tf specific (team1-change)
# role based embedding layer
embedding_layer = factored_embedding(input_words, input_roles,
n_word_vocab, n_role_vocab,
glorot_uniform(), missing_word_id,
input_length, n_factors_emb,
n_hidden, True, using_dropout,
dropout_rate)
# non-linear layer, using 1 to initialize
non_linearity = PReLU(alpha_initializer='ones')(embedding_layer)
# mean on input_length direction;
# obtaining context embedding layer, shape is (batch_size, n_hidden)
context_embedding = Lambda(lambda x: K.mean(x, axis=1),
name='context_embedding',
output_shape=(n_hidden, ))(non_linearity)
# target word hidden layer
tw_hidden = target_word_hidden(context_embedding,
target_role,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_hidden,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# target role hidden layer
tr_hidden = target_role_hidden(context_embedding,
target_word,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_hidden,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# softmax output layer
target_word_output = Dense(n_word_vocab,
activation='softmax',
input_shape=(n_hidden, ),
name='softmax_word_output')(tw_hidden)
# softmax output layer
target_role_output = Dense(n_role_vocab,
activation='softmax',
input_shape=(n_hidden, ),
name='softmax_role_output')(tr_hidden)
self.model = Model(
inputs=[input_words, input_roles, target_word, target_role],
outputs=[target_word_output, target_role_output])
self.model.compile(optimizer, loss, metrics, loss_weights)
# (10) 양방향 LSTM 모델링 작업
from tf.keras.models import Model, Sequential
from tf.keras.layers import SimpleRNN, Input, Dense, LSTM
from tf.keras.layers import Bidirectional, TimeDistributed
# 학습
from tf.keras.callbacks import EarlyStopping
# 조기종료 콜백함수 정의
xInput = Input(batch_shape=(None, right_idx3, 256))
xBiLstm = Bidirectional(LSTM(240, return_sequences=True),
merge_mode='concat')(xInput)
xOutput = TimeDistributed(Dense(1, activation='sigmoid'))(xBiLstm)
# 각 스텝에서 cost가 전송되고, 오류가 다음 step으로 전송됨.
model1 = Model(xInput, xOutput)
model1.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model1.summary()
from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(monitor='val_loss', patience=3) # 조기종료 콜백함수 정의
# In[24]:
########## 3gram
# 교차검증 kfold
from sklearn.model_selection import KFold
# Accuracy, Precision, Recall, F1-Score
def eval_GS(model_name,
experiment_name,
eval_file_name,
model=None,
print_result=True,
verb_baseline=False):
MODEL_NAME = experiment_name
eval_file = os.path.join(EVAL_PATH, eval_file_name)
result_file = os.path.join(MODEL_PATH, MODEL_NAME + '_' + eval_file_name)
if model:
net = model
else:
description = model_builder.load_description(MODEL_PATH, MODEL_NAME)
net = model_builder.build_model(model_name, description)
net.load(MODEL_PATH, MODEL_NAME, description)
sent_layer = 'context_embedding'
sent_model = Model(inputs=net.model.input,
outputs=net.model.get_layer(sent_layer).output)
# if print_result:
# sent_model.summary()
n_input_length = len(net.role_vocabulary) - 1
print net.role_vocabulary
scores = []
similarities = []
original_sim_f = []
similarities_f = []
lo_similarities = []
hi_similarities = []
records = []
print("Embedding: " + experiment_name)
print("=" * 60)
print("\n")
print("sentence1\tsentence2\taverage_score\tembedding_cosine")
print("-" * 60)
with open(eval_file, 'r') as f, \
open(result_file, 'w') as f_out:
first = True
for line in f:
# skip header
if first:
first = False
continue
s = line.split()
sentence = " ".join(s[1:5])
score = float(s[5])
hilo = s[6].upper()
# verb subject object landmark
# A1 - object; A0 - subject
V1, A0, A1, V2 = sentence.split()
V1 = wnl.lemmatize(V1, wn.VERB)
A0 = wnl.lemmatize(A0, wn.NOUN)
A1 = wnl.lemmatize(A1, wn.NOUN)
V2 = wnl.lemmatize(V2, wn.VERB)
V1_i = net.word_vocabulary.get(V1, net.unk_word_id)
A0_i = net.word_vocabulary.get(A0, net.unk_word_id)
A1_i = net.word_vocabulary.get(A1, net.unk_word_id)
V2_i = net.word_vocabulary.get(V2, net.unk_word_id)
# if np.array([V1_i, A0_i, A1_i, V2_i]).any() == net.unk_word_id:
# print 'OOV: ', A0, A1, V1, V2
V_ri = net.role_vocabulary['V']
A0_ri = net.role_vocabulary['A0']
A1_ri = net.role_vocabulary['A1']
sent1_x = dict((r, net.missing_word_id)
for r in (net.role_vocabulary.values()))
sent2_x = dict((r, net.missing_word_id)
for r in (net.role_vocabulary.values()))
sent1_x.pop(n_input_length)
sent2_x.pop(n_input_length)
sent1_x[V_ri] = V1_i
sent2_x[V_ri] = V2_i
if not verb_baseline:
sent1_x[A0_ri] = A0_i
sent1_x[A1_ri] = A1_i
sent2_x[A0_ri] = A0_i
sent2_x[A1_ri] = A1_i
zeroA = np.array([0])
s1_w = np.array(sent1_x.values()).reshape((1, n_input_length))
s1_r = np.array(sent1_x.keys()).reshape((1, n_input_length))
s2_w = np.array(sent2_x.values()).reshape((1, n_input_length))
s2_r = np.array(sent2_x.keys()).reshape((1, n_input_length))
if re.search('NNRF', model_name):
sent1_emb = sent_model.predict([s1_w, s1_r, zeroA])
sent2_emb = sent_model.predict([s2_w, s2_r, zeroA])
else:
sent1_emb = sent_model.predict([s1_w, s1_r, zeroA, zeroA])
sent2_emb = sent_model.predict([s2_w, s2_r, zeroA, zeroA])
# Baseline
#sent1_emb = V1_i
#sent2_emb = V2_i
# Compositional
# sent1_emb = V1_i + A0_i + A1_i
# sent2_emb = V2_i + A0_i + A1_i
#sent1_emb = V1_i * A0_i * A1_i
#sent2_emb = V2_i * A0_i * A1_i
similarity = -(cosine(sent1_emb, sent2_emb) - 1.0
) # convert distance to similarity
if hilo == "HIGH":
hi_similarities.append(similarity)
elif hilo == "LOW":
lo_similarities.append(similarity)
else:
raise Exception("Unknown hilo value %s" % hilo)
if (V1, A0, A1, V2) not in records:
records.append((V1, A0, A1, V2))
# print "\"%s %s %s\"\t\"%s %s %s\"\t%.2f\t%.2f \n" % (A0, V1, A1, A0, V2, A1, score, similarity)
scores.append(score)
similarities.append(similarity)
f_out.write("\"%s %s %s\"\t\"%s %s %s\"\t %.2f \t %.2f \n" %
(A0, V1, A1, A0, V2, A1, score, similarity))
print("-" * 60)
correlation, pvalue = spearmanr(scores, similarities)
if print_result:
print("Total number of samples: %d" % len(scores)
) #Added paranthesis to the print statements (team1-change)
print("Spearman correlation: %.4f; 2-tailed p-value: %.10f" %
(correlation, pvalue)
) #Added paranthesis to the print statements (team1-change)
print("High: %.2f; Low: %.2f" %
(np.mean(hi_similarities), np.mean(lo_similarities))
) #Added paranthesis to the print statements (team1-change)
# import pylab
# pylab.scatter(scores, similarities)
# pylab.show()
return correlation
class MTRFv4(GenericModel):
"""Multi-task non-incremental role-filler
"""
def __init__(self,
n_word_vocab=50001,
n_role_vocab=7,
n_factors_emb=300,
n_hidden=300,
word_vocabulary=None,
role_vocabulary=None,
unk_word_id=50000,
unk_role_id=7,
missing_word_id=50001,
using_dropout=False,
dropout_rate=0.3,
optimizer='adagrad',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
loss_weights=[1., 1.]):
super(MTRFv4, self).__init__(n_word_vocab, n_role_vocab, n_factors_emb,
n_hidden, word_vocabulary,
role_vocabulary, unk_word_id, unk_role_id,
missing_word_id, using_dropout,
dropout_rate, optimizer, loss, metrics)
# minus 1 here because one of the role is target role
input_length = n_role_vocab - 1
n_factors_cls = n_hidden
# each input is a fixed window of frame set, each word correspond to one role
input_words = Input(
shape=(input_length, ), dtype=tf.uint32,
name='input_words') # Switched dtype to tf specific (team1-change)
input_roles = Input(
shape=(input_length, ), dtype=tf.uint32,
name='input_roles') # Switched dtype to tf specific (team1-change)
target_word = Input(
shape=(1, ), dtype=tf.uint32,
name='target_word') # Switched dtype to tf specific (team1-change)
target_role = Input(
shape=(1, ), dtype=tf.uint32,
name='target_role') # Switched dtype to tf specific (team1-change)
# role based embedding layer
embedding_layer = factored_embedding(input_words, input_roles,
n_word_vocab, n_role_vocab,
glorot_uniform(), missing_word_id,
input_length, n_factors_emb,
n_hidden, True, using_dropout,
dropout_rate)
# non-linear layer, using 1 to initialize
non_linearity = PReLU(alpha_initializer='ones')(embedding_layer)
# mean on input_length direction;
# obtaining context embedding layer, shape is (batch_size, n_hidden)
context_embedding = Lambda(lambda x: K.mean(x, axis=1),
name='context_embedding',
output_shape=(n_hidden, ))(non_linearity)
# target word hidden layer
tw_hidden = target_word_hidden(context_embedding,
target_role,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_hidden,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# target role hidden layer
tr_hidden = target_role_hidden(context_embedding,
target_word,
n_word_vocab,
n_role_vocab,
glorot_uniform(),
n_hidden,
n_hidden,
using_dropout=using_dropout,
dropout_rate=dropout_rate)
# softmax output layer
target_word_output = Dense(n_word_vocab,
activation='softmax',
input_shape=(n_hidden, ),
name='softmax_word_output')(tw_hidden)
# softmax output layer
target_role_output = Dense(n_role_vocab,
activation='softmax',
input_shape=(n_hidden, ),
name='softmax_role_output')(tr_hidden)
self.model = Model(
inputs=[input_words, input_roles, target_word, target_role],
outputs=[target_word_output, target_role_output])
self.model.compile(optimizer, loss, metrics, loss_weights)
def set_0_bias(self):
word_output_weights = self.model.get_layer(
"softmax_word_output").get_weights()
word_output_kernel = word_output_weights[0]
word_output_bias = np.zeros(self.n_word_vocab)
self.model.get_layer("softmax_word_output").set_weights(
[word_output_kernel, word_output_bias])
role_output_weights = self.model.get_layer(
"softmax_role_output").get_weights()
role_output_kernel = role_output_weights[0]
role_output_bias = np.zeros(self.n_role_vocab)
self.model.get_layer("softmax_role_output").set_weights(
[role_output_kernel, role_output_bias])
return word_output_weights[1], role_output_weights[1]
def set_bias(self, bias):
word_output_weights = self.model.get_layer(
"softmax_word_output").get_weights()
word_output_kernel = word_output_weights[0]
self.model.get_layer("softmax_word_output").set_weights(
[word_output_kernel, bias[0]])
role_output_weights = self.model.get_layer(
"softmax_role_output").get_weights()
role_output_kernel = role_output_weights[0]
self.model.get_layer("softmax_role_output").set_weights(
[role_output_kernel, bias[1]])
return bias
# Train and test
# Deprecated temporarily
def train(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
batch_size=256,
epochs=100,
validation_split=0.05,
verbose=0):
train_result = self.model.fit([i_w, i_r, t_w, t_r], [t_w_c, t_r_c],
batch_size, epochs, validation_split,
verbose)
return train_result
def test(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
batch_size=256,
verbose=0):
test_result = self.model.evaluate([i_w, i_r, t_w, t_r], [t_w_c, t_r_c],
batch_size, verbose)
return test_result
def train_on_batch(self, i_w, i_r, t_w, t_r, t_w_c, t_r_c):
train_result = self.model.train_on_batch([i_w, i_r, t_w, t_r],
[t_w_c, t_r_c])
return train_result
def test_on_batch(self,
i_w,
i_r,
t_w,
t_r,
t_w_c,
t_r_c,
sample_weight=None):
test_result = self.model.test_on_batch([i_w, i_r, t_w, t_r],
[t_w_c, t_r_c], sample_weight)
return test_result
def predict(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return the output from softmax layer. """
predict_result = self.model.predict([i_w, i_r, t_w, t_r], batch_size,
verbose)
return predict_result
def predict_word(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return predicted target word from prediction. """
predict_result = self.predict(i_w, i_r, t_w, t_r, batch_size, verbose)
return np.argmax(predict_result[0], axis=1)
def predict_role(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return predicted target role from prediction. """
predict_result = self.predict(i_w, i_r, t_w, t_r, batch_size, verbose)
return np.argmax(predict_result[1], axis=1)
def p_words(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return the output scores given target words. """
predict_result = self.predict(i_w, i_r, t_w, t_r, batch_size, verbose)
return predict_result[0][range(batch_size), list(t_w)]
def p_roles(self, i_w, i_r, t_w, t_r, batch_size=1, verbose=0):
""" Return the output scores given target roles. """
predict_result = self.predict(i_w, i_r, t_w, t_r, batch_size, verbose)
return predict_result[1][range(batch_size), list(t_r)]
def top_words(self, i_w, i_r, t_w, t_r, topN=20, batch_size=1, verbose=0):
""" Return top N target words given context. """
predict_result = self.predict(i_w, i_r, t_w, t_r, batch_size,
verbose)[0]
rank_list = np.argsort(predict_result, axis=1)[0]
return rank_list[-topN:][::-1]
# return [r[-topN:][::-1] for r in rank_list]
# TODO
def list_top_words(self, i_w, i_r, t_r, topN=20, batch_size=1, verbose=0):
""" Return a list of decoded top N target words.
(Only for reference, can be removed.)
"""
top_words_lists = self.top_words(i_w, i_r, t_r, topN, batch_size,
verbose)
print(
type(top_words_lists)) # Updated to python3 syntax (team1-change)
result = []
for i in range(batch_size):
top_words_list = top_words_lists[i]
result.append([self.word_decoder[w] for w in top_words_list])
return result
def summary(self):
self.model.summary()