text_CNN.input_y: y_batch,
text_CNN.dropout_keep_prob: 1.0
}
step, summaries, loss, accuracy = sess.run([
global_step, validation_summary_op, text_CNN.loss,
text_CNN.accuracy
], feed)
time_str = time.strftime('%Y-%m-%d_%H-%M-%S',
time.localtime(time.time()))
print("{}: step {}, loss {:g}, accuracy {:g}".format(
time_str, step, loss, accuracy))
if writer:
writer.add_summary(summaries, step)
# Generate batches
batches = data_processor.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.period_evaluation == 0:
print("\nEvaluation:")
validate_step(x_validation,
y_validation,
writer=validation_summary_writer)
print("")
if current_step % FLAGS.period_checkpoint == 0:
path = saver.save(sess,
checkpoint_filename,
global_step=current_step)
def train(x_train, y_train, vocab_processor, 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],
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)
# 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
vocab_processor.save(os.path.join(out_dir, "vocab"))
# 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 = data_processor.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))
pred = np.concatenate(predicts)
y_dev = np.concatenate(actuals)
f1 = f1_score(y_dev, pred, average='weighted')
accuracy = np.sum(pred == y_dev) / len(pred)
time_str = datetime.datetime.now().isoformat()
print("{}: step {}, loss {:g}, dev acc {}, f1-score {}".format(
time_str, step, loss, accuracy, f1))
with open(logfile, "a") as log:
log.write(
"{}: step {}, loss {:g}, dev acc {:g},f1-score {:g} \n"
.format(time_str, step, loss, accuracy, f1))
log.write("\n")
log.write("Training Steps: \n")
# Generating batches
batches = data_processor.batch_iter(list(zip(train_x, train_y)),
batch_size, num_epoch)
# Training executions
devbatches = data_processor.batch_iter(list(zip(dev_x, dev_y)),
100, 1)
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 % 6000 == 0:
with open(logfile, "a") as log:
log.write("\nDev Set Evaluation:\n")
print("\nDev Set Evaluation:")
dev_step(devbatches)
# input_y = graph.get_operation_by_name("input_y").outputs[0]
dropout_keep_prob = graph.get_operation_by_name(
"dropout_keep_prob").outputs[0]
# Tensors we want to evaluate
predictions = graph.get_operation_by_name(
"output/predictions").outputs[0]
scores = graph.get_operation_by_name("output/scores").outputs[0]
features = graph.get_operation_by_name("reshape").outputs[0]
feature_length = sess.run(
graph.get_operation_by_name("feature_length").outputs[0])
# Generate batches for one epoch
batches = data_processor.batch_iter(list(x_test),
FLAGS.batch_size,
1,
shuffle=False)
# Collect the features
all_features = np.zeros(feature_length)
all_predictions = []
for x_test_batch in batches:
batch_predictions = sess.run(predictions, {
input_x: x_test_batch,
dropout_keep_prob: 1.0
})
all_predictions = np.concatenate(
[all_predictions, batch_predictions])
batch_features = sess.run(features, {
input_x: x_test_batch,
def model(txt):
# Map data into vocabulary
checkpoint = './runs/1518619812/checkpoints/'
vocab_path = os.path.join(checkpoint, "..", "vocab")
vocab_processor = learn.preprocessing.VocabularyProcessor.restore(
vocab_path)
# x_test = np.array(list(vocab_processor.transform(x_raw)))
print("\nEvaluating...\n")
checkpoint_file = tf.train.latest_checkpoint(checkpoint)
graph = tf.Graph()
with 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():
# Load the saved meta graph and restore variables
saver = tf.train.import_meta_graph(
"{}.meta".format(checkpoint_file))
saver.restore(sess, checkpoint_file)
# Get the placeholders from the graph by name
input_x = graph.get_operation_by_name("input_x").outputs[0]
# input_y = graph.get_operation_by_name("input_y").outputs[0]
dropout_keep_prob = graph.get_operation_by_name(
"dropout_keep_prob").outputs[0]
# Tensors we want to evaluate
predictions = graph.get_operation_by_name(
"output/predictions").outputs[0]
x_raw = []
#y_test=None
x_raw.append(txt)
x_test = np.array(list(vocab_processor.transform(x_raw)))
batches = data_processor.batch_iter(list(x_test),
FLAGS.batch_size,
1,
shuffle=False)
# Collect the predictions here
all_predictions = []
for x_test_batch in batches:
batch_predictions = sess.run(predictions, {
input_x: x_test_batch,
dropout_keep_prob: 1.0
})
batch_predictions = [
_CLASSES[x] for x in batch_predictions
]
all_predictions = np.concatenate(
[all_predictions, batch_predictions])
print(batch_predictions)
for i in range(len(x_raw)):
output_data = {
"input": txt,
"output": all_predictions[i]
}
print(output_data)
return output_data