def __init__(self,
batch_size=FLAGS.batch_size,
learning_rate=FLAGS.learning_rate,
keep_prob=FLAGS.keep_prob,
l2_reg=FLAGS.l2_reg,
display_step=FLAGS.display_step,
training_iter=FLAGS.training_iter,
embedding_dim=FLAGS.embedding_dim,
n_class=FLAGS.n_class,
max_doc_len=FLAGS.max_doc_len,
train_file_path=FLAGS.train_file_path,
w2v_file=FLAGS.embedding_file_path,
test_index=FLAGS.test_index,
embedding_type=FLAGS.embedding_type,
scope='test'):
self.batch_size = batch_size
self.learning_rate = learning_rate
self.Keep_Prob = keep_prob
self.l2_reg = l2_reg
self.display_step = display_step
self.training_iter = training_iter
self.embedding_dim = embedding_dim
self.n_class = n_class
self.max_doc_len = max_doc_len
self.train_file_path = train_file_path
self.w2v_file = w2v_file
self.test_index = test_index
self.embedding_type = embedding_type
self.scope = scope
self.word_id_mapping, self.w2v = load_w2v(self.w2v_file,
self.embedding_dim)
if embedding_type == 0: # Pretrained and Untrainable
self.word_embedding = tf.constant(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 1: # Pretrained and Trainable
self.word_embedding = tf.Variable(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 2: # Random and Trainable
self.word_embedding = tf.Variable(tf.random_uniform(
[len(self.word_id_mapping) + 1, self.embedding_dim], -0.1,
0.1),
name='word_embedding')
with tf.name_scope('inputs'):
self.x = tf.placeholder(tf.int32, [None, self.max_doc_len])
self.y = tf.placeholder(tf.float32, [None, self.n_class])
self.doc_len = tf.placeholder(tf.int32, None)
self.keep_prob = tf.placeholder(tf.float32)
def init_variable(shape):
initial = tf.random_uniform(shape, -0.01, 0.01)
return tf.Variable(initial)
with tf.name_scope('weights'):
self.weights = {
'softmax': init_variable([100, self.n_class]),
'softmax1': init_variable([200, self.n_class]),
}
with tf.name_scope('biases'):
self.biases = {
'softmax': init_variable([self.n_class]),
}
def __init__(self,
batch_size=FLAGS.batch_size,
learning_rate=FLAGS.learning_rate,
keep_prob1=FLAGS.keep_prob1,
keep_prob2=FLAGS.keep_prob2,
l2_reg=FLAGS.l2_reg,
n_hidden=FLAGS.n_hidden,
n_topic=FLAGS.n_topic,
display_step=FLAGS.display_step,
training_iter=FLAGS.training_iter,
n_doc_class=FLAGS.n_doc_class,
n_sentence_class=FLAGS.n_sentence_class,
max_sentence_len=FLAGS.max_sentence_len,
max_doc_len=FLAGS.max_doc_len,
train_file_path=FLAGS.train_file_path,
emoWord_file_path=FLAGS.emoWord_file_path,
w2v_file=FLAGS.embedding_file_path,
embedding_dim=FLAGS.embedding_dim,
test_index=FLAGS.test_index,
embedding_type=FLAGS.embedding_type,
alpha=FLAGS.alpha,
scope='test'):
self.batch_size = batch_size
self.learning_rate = learning_rate
self.keep_prob1 = keep_prob1
self.keep_prob2 = keep_prob2
self.l2_reg = l2_reg
self.n_hidden = n_hidden
self.n_topic = n_topic
self.display_step = display_step
self.training_iter = training_iter
self.n_doc_class = n_doc_class
self.n_sentence_class = n_sentence_class
self.max_sentence_len = max_sentence_len
self.max_doc_len = max_doc_len
self.train_file_path = train_file_path
self.emoWord_file_path = emoWord_file_path
self.w2v_file = w2v_file
self.embedding_dim = embedding_dim
self.test_index = test_index
self.embedding_type = embedding_type
self.alpha = alpha
self.scope = scope
self.word_id_mapping, self.w2v = load_w2v(self.w2v_file,
self.emoWord_file_path,
self.embedding_dim)
if embedding_type == 0: # Pretrained and Untrainable
self.word_embedding = tf.constant(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 1: # Pretrained and Trainable
self.word_embedding = tf.Variable(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 2: # Random and Trainable
self.word_embedding = tf.Variable(tf.random_uniform(
[len(self.word_id_mapping) + 1, self.embedding_dim], -0.1,
0.1),
name='word_embedding')
#定义需feed数据的tensor
with tf.name_scope('inputs'):
self.x = tf.placeholder(
tf.int32, [None, self.max_doc_len, self.max_sentence_len])
# self.y = tf.placeholder(tf.float32, [None, self.n_class])
self.y_doc = tf.placeholder(tf.float32, [None, self.n_doc_class])
self.y_sen = tf.placeholder(
tf.float32, [None, self.max_doc_len, self.n_sentence_class])
self.sen_len = tf.placeholder(tf.int32, [None, self.max_doc_len])
self.doc_len = tf.placeholder(tf.int32, None)
# self.topic = tf.placeholder(tf.float32, [None, self.max_doc_len, self.n_topic])
# add aspect id
self.aspect_id = tf.placeholder(tf.int32, [None, self.max_doc_len],
name='aspect_id')
self.keep_prob1 = tf.placeholder(tf.float32)
self.keep_prob2 = tf.placeholder(tf.float32)
def init_variable(shape):
initial = tf.random_uniform(shape, -0.01, 0.01)
return tf.Variable(initial)
#所有的模型可训练参数
with tf.name_scope('weights'):
self.weights = {
# Attention sentence
# 'w_1': tf.Variable(tf.random_uniform([2 * self.n_hidden, 2 * self.n_hidden], -0.01, 0.01)),
# 'u_1': tf.Variable(tf.random_uniform([2 * self.n_hidden, 1], -0.01, 0.01)),
# 'w_1': tf.Variable(tf.random_uniform([2 * self.n_hidden + self.embedding_dim, 2 * self.n_hidden + self.embedding_dim], -0.01, 0.01)),
# 'u_1': tf.Variable(tf.random_uniform([2* self.n_hidden + self.embedding_dim, 1], -0.01, 0.01)),
# # Attention doc
# 'w_2': tf.Variable(tf.random_uniform([2 * self.n_hidden, 2 * self.n_hidden], -0.01, 0.01)),
# 'u_2': tf.Variable(tf.random_uniform([2 * self.n_hidden, 1], -0.01, 0.01)),
# softmax sentence
# 'softmax_sen': init_variable([self.n_hidden*2 + self.n_topic, self.n_sentence_class]),
'softmax_sen':
init_variable([2 * self.n_hidden, self.n_sentence_class]),
# softmax doc
# 'softmax_doc': init_variable([self.n_hidden*2, self.n_doc_class]),
}
with tf.name_scope('biases'):
self.biases = {
#Attention
# 'w_1': tf.Variable(tf.random_uniform([2 * self.n_hidden], -0.01, 0.01)),
# 'w_1': tf.Variable(tf.random_uniform([2 * self.n_hidden + self.embedding_dim], -0.01, 0.01)),
# # 'w_2': tf.Variable(tf.random_uniform([2 * self.n_hidden], -0.01, 0.01)),
'softmax_sen': init_variable([self.n_sentence_class]),
# 'softmax_doc': init_variable([self.n_doc_class]),
}
def __init__(
self,
batch_size=FLAGS.batch_size,
learning_rate=FLAGS.learning_rate,
keep_prob1=FLAGS.keep_prob1,
keep_prob2=FLAGS.keep_prob2,
l2_reg=FLAGS.l2_reg,
display_step=FLAGS.display_step,
training_iter=FLAGS.training_iter,
embedding_dim=FLAGS.embedding_dim,
n_class=FLAGS.n_class,
max_doc_len=FLAGS.max_doc_len,
max_sentence_len=FLAGS.max_sentence_len,
n_hidden=FLAGS.n_hidden,
train_file_path=FLAGS.train_file_path,
test_file_path=FLAGS.test_file_path,
w2v_file=FLAGS.embedding_file_path,
embedding_type=0,
scope='sentence',
):
self.batch_size = batch_size
self.learning_rate = learning_rate
self.Keep_Prob1 = keep_prob1
self.Keep_Prob2 = keep_prob2
self.l2_reg = l2_reg
self.display_step = display_step
self.training_iter = training_iter
self.embedding_dim = embedding_dim
self.n_class = n_class
self.max_doc_len = max_doc_len
self.max_sentence_len = max_sentence_len
self.n_hidden = n_hidden
self.train_file_path = train_file_path
self.test_file_path = test_file_path
self.w2v_file = w2v_file
self.scope = scope
self.word_id_mapping, self.w2v = load_w2v(self.w2v_file,
self.embedding_dim)
if embedding_type == 0: # Pretrained and Untrainable
self.word_embedding = tf.constant(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 1: # Pretrained and Trainable
self.word_embedding = tf.Variable(self.w2v,
dtype=tf.float32,
name='word_embedding')
elif embedding_type == 2: # Random and Trainable
self.word_embedding = tf.Variable(tf.random_uniform(
[len(self.word_id_mapping) + 1, self.embedding_dim], -0.1,
0.1),
name='word_embedding')
with tf.name_scope('inputs'):
self.x = tf.placeholder(
tf.int32, [None, self.max_doc_len, self.max_sentence_len])
self.y = tf.placeholder(tf.float32, [None, self.n_class])
self.sen_len = tf.placeholder(tf.int32, [None, self.max_doc_len])
self.doc_len = tf.placeholder(tf.int32, None)
self.keep_prob1 = tf.placeholder(tf.float32)
self.keep_prob2 = tf.placeholder(tf.float32)
def init_variable(shape):
initial = tf.random_uniform(shape, -0.01, 0.01)
return tf.Variable(initial)
with tf.name_scope('weights'):
self.weights = {
'conv1':
init_variable([3, self.embedding_dim, 1, self.n_hidden]),
'conv2':
init_variable([2, self.embedding_dim, 1, self.n_hidden]),
'conv3':
init_variable([1, self.embedding_dim, 1, self.n_hidden]),
'gconv1':
init_variable([3, self.embedding_dim, 1, self.n_hidden]),
'gconv2':
init_variable([2, self.embedding_dim, 1, self.n_hidden]),
'gconv3':
init_variable([1, self.embedding_dim, 1, self.n_hidden]),
'softmax': init_variable([2 * self.n_hidden, self.n_class]),
}
self.cell_fw = tf.nn.rnn_cell.GRUCell(self.n_hidden)
self.cell_bw = tf.nn.rnn_cell.GRUCell(self.n_hidden)
with tf.name_scope('biases'):
self.biases = {
'conv1': init_variable([self.n_hidden]),
'conv2': init_variable([self.n_hidden]),
'conv3': init_variable([self.n_hidden]),
'gconv1': init_variable([self.n_hidden]),
'gconv2': init_variable([self.n_hidden]),
'gconv3': init_variable([self.n_hidden]),
'softmax': init_variable([self.n_class]),
}
