def get_model(model_name):
if model_name == 'cnn1':
model = TextCNN(
model_name='CNN',
nb_epoch=10,
max_len=config.word_maxlen,
embed_size=config.embed_size,
batch_size=128,
lr=0.01,
kfold=5,
word_embed_weight=config.word_embed_weight,
stack_path=config.stack_path,
model_dir=config.model_dir,
use_pretrained=True,
trainable=True,
# **kwargs
)
if model_name == 'cnn2':
model = TextCNN(
model_name='CNN2',
nb_epoch=10,
max_len=config.word_maxlen,
embed_size=config.embed_size,
batch_size=128,
lr=0.01,
kfold=5,
word_embed_weight=config.word_embed_weight,
stack_path=config.stack_path,
use_pretrained=True,
trainable=True,
# **kwargs
)
if model_name == 'rnn1':
model = TextRNN(
model_name='RNN',
nb_epoch=10,
max_len=config.word_maxlen,
embed_size=config.embed_size,
batch_size=128,
lr=0.01,
kfold=5,
word_embed_weight=config.word_embed_weight,
stack_path=config.stack_path,
model_dir=config.model_dir,
use_pretrained=True,
trainable=True,
# **kwargs
)
#0.66
if model_name == 'rnn2':
model = TextRNN2(
model_name='RNN2',
nb_epoch=10,
max_len=config.word_maxlen,
embed_size=config.embed_size,
batch_size=128,
lr=0.01,
kfold=5,
word_embed_weight=config.word_embed_weight,
stack_path=config.stack_path,
model_dir=config.model_dir,
use_pretrained=True,
trainable=True,
# **kwargs
)
return model
def train(x_train, y_train, vocabulary, x_dev, y_dev):
# Training
# ==================================================
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
cnn = TextCNN(
sequence_length=x_train.shape[1],
model_path=
"/Users/pxu3/Desktop/Spring 2019/Research/Code/updated_pretrained_googlewv.bin",
num_classes=y_train.shape[1],
embedding_size=FLAGS.embedding_dim,
filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
l2_reg_lambda=FLAGS.l2_reg_lambda)
# Define Training procedure
global_step = tf.Variable(0, name="global_step", trainable=False)
optimizer = tf.train.AdamOptimizer(1e-3)
grads_and_vars = optimizer.compute_gradients(cnn.loss)
train_op = optimizer.apply_gradients(grads_and_vars,
global_step=global_step)
# Keep track of gradient values and sparsity (optional)
grad_summaries = []
for g, v in grads_and_vars:
if g is not None:
grad_hist_summary = tf.summary.histogram(
"{}/grad/hist".format(v.name), g)
sparsity_summary = tf.summary.scalar(
"{}/grad/sparsity".format(v.name),
tf.nn.zero_fraction(g))
grad_summaries.append(grad_hist_summary)
grad_summaries.append(sparsity_summary)
grad_summaries_merged = tf.summary.merge(grad_summaries)
# Output directory for models and summaries
timestamp = str(int(time.time()))
out_dir = os.path.abspath(
os.path.join(os.path.curdir, "runs", timestamp))
print("Writing to {}\n".format(out_dir))
# Summaries for loss and accuracy
loss_summary = tf.summary.scalar("loss", cnn.loss)
acc_summary = tf.summary.scalar("accuracy", cnn.accuracy)
# Train Summaries
train_summary_op = tf.summary.merge(
[loss_summary, acc_summary, grad_summaries_merged])
train_summary_dir = os.path.join(out_dir, "summaries", "train")
train_summary_writer = tf.summary.FileWriter(
train_summary_dir, sess.graph)
# Dev summaries
dev_summary_op = tf.summary.merge([loss_summary, acc_summary])
dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
dev_summary_writer = tf.summary.FileWriter(dev_summary_dir,
sess.graph)
# Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it
checkpoint_dir = os.path.abspath(
os.path.join(out_dir, "checkpoints"))
checkpoint_prefix = os.path.join(checkpoint_dir, "model")
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
saver = tf.train.Saver(tf.global_variables(),
max_to_keep=FLAGS.num_checkpoints)
# Write vocabulary
with open('vocab.json', 'w') as fp:
json.dump(vocabulary, fp, sort_keys=True, indent=4)
# Initialize all variables
sess.run(tf.global_variables_initializer())
def train_step(x_batch, y_batch):
"""
A single training step
"""
feed_dict = {
cnn.input_x: x_batch,
cnn.input_y: y_batch,
cnn.dropout_keep_prob: FLAGS.dropout_keep_prob
}
_, step, summaries, loss, accuracy = sess.run([
train_op, global_step, train_summary_op, cnn.loss,
cnn.accuracy
], feed_dict)
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(
time_str, step, loss, accuracy))
train_summary_writer.add_summary(summaries, step)
def dev_step(x_batch, y_batch, writer=None):
"""
Evaluates model on a dev set
"""
feed_dict = {
cnn.input_x: x_batch,
cnn.input_y: y_batch,
cnn.dropout_keep_prob: 1.0
}
step, summaries, loss, accuracy = sess.run(
[global_step, dev_summary_op, cnn.loss, cnn.accuracy],
feed_dict)
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, acc {:g}".format(
time_str, step, loss, accuracy))
if writer:
writer.add_summary(summaries, step)
# Generate batches
batches = get_data.batch_iter(list(zip(x_train, y_train)),
FLAGS.batch_size, FLAGS.num_epochs)
# Training loop. For each batch...
for batch in batches:
x_batch, y_batch = zip(*batch)
train_step(x_batch, y_batch)
current_step = tf.train.global_step(sess, global_step)
if current_step % FLAGS.evaluate_every == 0:
print("\nEvaluation:")
dev_step(x_dev, y_dev, writer=dev_summary_writer)
print("")
if current_step % FLAGS.checkpoint_every == 0:
path = saver.save(sess,
checkpoint_prefix,
global_step=current_step)
print("Saved model checkpoint to {}\n".format(path))
sents, labels = data_helper.load_data('./data/train.txt')
test_sents, test_labels = data_helper.load_data('./data/test.txt')
max_len = 1024
vocab = data_helper.read_vocab()
data = data_helper.sent2idx(sents, vocab, max_len)
test_data = data_helper.sent2idx(test_sents, vocab, max_len)
epoch = 100
with tf.Graph().as_default():
session_conf = tf.ConfigProto()
sess = tf.Session(config=session_conf)
with sess.as_default():
cnn = TextCNN(vocab_size=len(vocab),
seq_len=max_len,
embedding_size=256,
num_classes=2,
filter_sizes=[3, 4, 5],
num_filters=256)
# 指定优化器（梯度下降）
optimizer = tf.train.AdamOptimizer(1e-3)
# 梯度
train_op = optimizer.minimize(cnn.loss)
# 全局初始化 Initialize all variables
sess.run(tf.global_variables_initializer())
train(cnn, data, labels, test_data, test_labels, epoch, sess, train_op)
y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
del x, y, x_shuffled, y_shuffled
#starting the traning session
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
cnn = TextCNN(sequence_length=x_train.shape[1],
num_classes=y_train.shape[1],
vocab_size=len(vocab_processor.vocabulary_),
embedding_size=FLAGS.embedding_dim,
filter_sizes=list(map(int,
FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
l2_reg_lambda=FLAGS.l2_reg_lambda)
# Defining the procedure
global_step = tf.Variable(0, name="global_step", trainable=True)
optimizer = tf.train.AdamOptimizer(1e-3)
grads_and_vars = optimizer.compute_gradients(cnn.loss)
train_op = optimizer.apply_gradients(grads_and_vars,
global_step=global_step)
# Keep track of gradient values and sparsity (optional)
grad_summaries = []
for g, v in grads_and_vars:
if g is not None:
##### +code added until here (see functions in the helpers file) #####
# Training
# ==================================================
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
cnn = TextCNN(sequence_length=x_train.shape[1],
num_classes=2,
vocab_size=len(d_vocab),
embedding_size=FLAGS.embedding_dim,
filter_sizes=list(map(int,
FLAGS.filter_sizes.split(","))),
num_filters=FLAGS.num_filters,
initW=initW,
l2_reg_lambda=FLAGS.l2_reg_lambda)
# Define Training procedure
global_step = tf.Variable(0, name="global_step", trainable=False)
optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate)
grads_and_vars = optimizer.compute_gradients(cnn.loss)
train_op = optimizer.apply_gradients(grads_and_vars,
global_step=global_step)
# Keep track of gradient values and sparsity (optional)
grad_summaries = []
for g, v in grads_and_vars: