tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps")
tf.flags.DEFINE_integer("num_checkpoints", 1000, "Number of checkpoints to store")
#tf.flags.DEFINE_string("checkpoint_dir", "", "Chechpoint directory")
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")
FLAGS = tf.flags.FLAGS
FLAGS._parse_flags()
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
print("{}={}".format(attr.upper(), value))
print("")
print("Loading data...")
w = Word2Vec()
train_data = MData(word2vec=w)
train_data.open_file(FLAGS.positive_data_file, FLAGS.negative_data_file)
print("=" * 50)
print("training data size:", train_data.data_size)
print("training max len:", train_data.max_len)
print("=" * 50)
with tf.Graph().as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
session_conf.gpu_options.allow_growth=True
sess = tf.Session(config=session_conf)
with sess.as_default():
# --batch_size: batch size
# --model_type: model type
# --num_layers: number of convolution layers
# --data_type: dataset with which we want to train our model
################################
# default parameters
params = {
"lr": 0.08,
"ws": 4,
"l2_reg": 0.0004,
"epoch": 50,
"batch_size": 200,
"model_type": "BCNN",
"num_layers": 2,
"data_type": "BioASQ",
"word2vec": Word2Vec()
}
################################
print("=" * 50)
print("Parameters:")
for k in sorted(params.keys()):
print(k, ":", params[k])
################################
if len(sys.argv) > 1:
for arg in sys.argv[1:]:
k = arg.split("=")[0][2:]
v = arg.split("=")[1]
params[k] = v
################################
# Call train function to train our model
train(
filter_size = int(FLAGS.filter_size)
#----------------------------- define parameter end ----------------------------------
#----------------------------- define a logger -------------------------------
logger = logging.getLogger("test")
logger.setLevel(logging.INFO)
fh = logging.FileHandler("./test.log", mode="w")
fh.setLevel(logging.INFO)
logger.addHandler(fh)
#----------------------------- define a logger end ----------------------------------
#------------------------------------load data -------------------------------
#load data
word2Vec = Word2Vec()
data_type = "WikiQA"
if data_type == "WikiQA":
test_data = WikiQA(word2vec=word2Vec)
else:
test_data = MSRP(word2vec=word2Vec)
test_data.open_file(mode="test")
#----------------------------------- load data end ----------------------
#----------------------------------- begin to train -----------------------------------
with tf.Graph().as_default():
with tf.device("/gpu:1"):
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=FLAGS.gpu_options)
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,