def startTrain():
# Parameters
# ==================================================
del_all_flags(tf.flags.FLAGS)
# Model Hyperparameters
tf.flags.DEFINE_integer(
"embedding_dim", 128,
"Dimensionality of character embedding (default: 128)")
tf.flags.DEFINE_string("filter_sizes", "3,4,5",
"Comma-separated filter sizes (default: '3,4,5')")
tf.flags.DEFINE_integer(
"num_filters", 128, "Number of filters per filter size (default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5,
"Dropout keep probability (default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 0.0,
"L2 regularizaion lambda (default: 0.0)")
# Training parameters
tf.flags.DEFINE_integer("batch_size", 128, "Batch Size (default: 64)")
tf.flags.DEFINE_integer("num_epochs", 200,
"Number of training epochs (default: 200)")
tf.flags.DEFINE_integer(
"evaluate_every", 100,
"Evaluate model on dev set after this many steps (default: 100)")
tf.flags.DEFINE_integer("checkpoint_every", 100,
"Save model after this many steps (default: 100)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True,
"Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False,
"Log placement of ops on devices")
data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor())
data_loader.define_flags()
FLAGS = tf.flags.FLAGS
# FLAGS._parse_flags()
FLAGS(sys.argv)
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{}={}".format(attr.upper(), value))
print("")
# Data Preparatopn
# ==================================================
# Load data
print("Loading data...")
x_train, y_train, x_dev, y_dev = data_loader.prepare_data()
vocab_processor = data_loader.vocab_processor
print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(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))
# out_dir = '/home/taihoinst/icrRest/labelTrain/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())
# 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_helpers.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))
# Training parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)")
tf.flags.DEFINE_integer("num_epochs", 50,
"Number of training epochs (default: 200)")
tf.flags.DEFINE_integer(
"evaluate_every", 100,
"Evaluate model on dev set after this many steps (default: 100)")
tf.flags.DEFINE_integer("checkpoint_every", 100,
"Save model after this many steps (default: 100)")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True,
"Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", True,
"Log placement of ops on devices")
data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor())
data_loader.define_flags()
FLAGS = tf.flags.FLAGS
FLAGS(sys.argv)
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{}={}".format(attr.upper(), value))
print("")
# Data Preparatopn
# ==================================================
# Load data
print("Loading data...")
x_train, y_train, x_dev, y_dev = data_loader.prepare_data()
def startEval(ocrData):
# Parameters
# ==================================================
del_all_flags(tf.flags.FLAGS)
ocrData = json.loads(
'[{"location":"1018,240,411,87","text":"APEX"},{"location":"1019,338,409,23","text":"Partner of Choice"},{"location":"1562,509,178,25","text":"Voucher No"},{"location":"1562,578,206,25","text":"Voucher Date"},{"location":"206,691,274,27","text":"4153 Korean Re"},{"location":"208,756,525,34","text":"Proportional Treaty Statement"},{"location":"1842,506,344,25","text":"BV/HEO/2018/05/0626"},{"location":"1840,575,169,25","text":"01105/2018"},{"location":"206,848,111,24","text":"Cedant"},{"location":"206,908,285,24","text":"Class of Business"},{"location":"210,963,272,26","text":"Period of Quarter"},{"location":"207,1017,252,31","text":"Period of Treaty"},{"location":"206,1066,227,24","text":"Our Reference"},{"location":"226,1174,145,31","text":"Currency"},{"location":"227,1243,139,24","text":"Premium"},{"location":"226,1303,197,24","text":"Commission"},{"location":"226,1366,107,24","text":"Claims"},{"location":"227,1426,126,24","text":"Reserve"},{"location":"227,1489,123,24","text":"Release"},{"location":"227,1549,117,24","text":"Interest"},{"location":"227,1609,161,31","text":"Brokerage"},{"location":"233,1678,134,24","text":"Portfolio"},{"location":"227,1781,124,24","text":"Balance"},{"location":"574,847,492,32","text":": Solidarity- First Insurance 2018"},{"location":"574,907,568,32","text":": Marine Cargo Surplus 2018 - Inward"},{"location":"598,959,433,25","text":"01-01-2018 TO 31-03-2018"},{"location":"574,1010,454,25","text":": 01-01-2018 TO 31-12-2018"},{"location":"574,1065,304,25","text":": APEX/BORD/2727"},{"location":"629,1173,171,25","text":"JOD 1.00"},{"location":"639,1239,83,25","text":"25.53"},{"location":"639,1299,64,25","text":"5.74"},{"location":"639,1362,64,25","text":"0.00"},{"location":"639,1422,64,25","text":"7.66"},{"location":"639,1485,64,25","text":"0.00"},{"location":"639,1545,64,25","text":"0.00"},{"location":"639,1605,64,25","text":"0.64"},{"location":"648,1677,64,25","text":"0.00"},{"location":"641,1774,81,25","text":"11 .49"},{"location":"1706,1908,356,29","text":"APEX INSURANCE"}]'
)
# print('============startEval================')
# ocrData = json.loads(ocrData)
# print(ocrData)
# Eval Parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (default: 64)")
tf.flags.DEFINE_string("checkpoint_dir", "",
"Checkpoint directory from training run")
tf.flags.DEFINE_boolean("eval_train", False,
"Evaluate on all training data")
# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True,
"Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False,
"Log placement of ops on devices")
data_loader = MultiClassDataLoader(tf.flags, WordDataProcessor())
data_loader.define_flags()
FLAGS = tf.flags.FLAGS
# FLAGS._parse_flags()
FLAGS(sys.argv)
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{}={}".format(attr.upper(), value))
print("")
if FLAGS.eval_train:
x_raw, y_test = data_loader.load_data_and_labels()
y_test = np.argmax(y_test, axis=1)
else:
# x_raw, y_test = data_loader.load_dev_data_and_labels()
x_raw, y_test = data_loader.load_dev_data_and_labels_json(ocrData)
y_test = np.argmax(y_test, axis=1)
# checkpoint_dir이 없다면 가장 최근 dir 추출하여 셋팅
if FLAGS.checkpoint_dir == "":
all_subdirs = [
"./runs/" + d for d in os.listdir('./runs/.')
if os.path.isdir("./runs/" + d)
]
latest_subdir = max(all_subdirs, key=os.path.getmtime)
FLAGS.checkpoint_dir = latest_subdir + "/checkpoints/"
# Map data into vocabulary
vocab_path = os.path.join(FLAGS.checkpoint_dir, "..", "vocab")
vocab_processor = data_loader.restore_vocab_processor(vocab_path)
x_test = np.array(list(vocab_processor.transform(x_raw)))
print("\nEvaluating...\n")
# Evaluation
# ==================================================
checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
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]
# Generate batches for one epoch
batches = data_helpers.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
})
all_predictions = np.concatenate(
[all_predictions, batch_predictions])
# Print accuracy if y_test is defined
if y_test is not None:
correct_predictions = float(sum(all_predictions == y_test))
print("Total number of test examples: {}".format(len(y_test)))
print("Accuracy: {:g}".format(correct_predictions /
float(len(y_test))))
# Save the evaluation to a csv
class_predictions = data_loader.class_labels(all_predictions.astype(int))
predictions_human_readable = np.column_stack(
(np.array(x_raw), class_predictions))
out_path = os.path.join(FLAGS.checkpoint_dir, "../../../",
"prediction.csv")
print("Saving evaluation to {0}".format(out_path))
for i in predictions_human_readable:
for row in ocrData:
if i[0].lower() == row['text'].lower():
row['colLbl'] = i[1]
print(ocrData)
return ocrData
