print("Train/Hold-out/Test split: {:d}/{:d}/{:d}".format(len(y_train), len(y_dev), len(y_test)))
# 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 = cnn_class(
embedding_mat = embedding_mat,
sequence_length=x_train.shape[1],
num_classes=y.shape[1],
vocab_size=len(vocabulary),
embedding_size=FLAGS.embedding_dim,
filter_sizes=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
grad_summaries = []
for g, v in grads_and_vars:
if g is not None:
print("Train/Hold-out/Test split: {:d}/{:d}/{:d}".format(len(y_train), len(y_dev), len(y_test)))
# 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 = cnn_class(
embedding_mat = embedding_mat,
sequence_length=x_train.shape[1],
num_classes=y.shape[1],
vocab_size=len(vocabulary),
embedding_size=FLAGS.embedding_dim,
filter_sizes=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
grad_summaries = []
for g, v in grads_and_vars:
if g is not None: