y_target_ph = tf.placeholder(tf.int32, [None], name="y_target_ph")
dropout_keep_prob_ph = tf.placeholder(tf.float32, name="dropout_keep_prob")
# Create embedding lookup
identity_mat = tf.diag(tf.ones(shape=[vocab_length]))
address1_embed = tf.nn.embedding_lookup(identity_mat, address1_ph)
address2_embed = tf.nn.embedding_lookup(identity_mat, address2_ph)
# Define Model
text_snn = model.snn(address1_embed, address2_embed, dropout_keep_prob_ph,
vocab_length, num_features, max_address_len)
# Define Accuracy
batch_accuracy = model.accuracy(text_snn, y_target_ph)
# Define Loss
batch_loss = model.loss(text_snn, y_target_ph, margin)
# Define Predictions
predictions = model.get_predictions(text_snn)
# Declare optimizer
optimizer = tf.train.AdamOptimizer(0.01)
# Apply gradients
train_op = optimizer.minimize(batch_loss)
# Initialize Variables
init = tf.global_variables_initializer()
sess.run(init)
# Train loop
train_loss_vec = []
train_acc_vec = []
y_target_ph = tf.placeholder(tf.int32, [None], name="y_target_ph")
dropout_keep_prob_ph = tf.placeholder(tf.float32, name="dropout_keep_prob")
# Create embedding lookup
identity_mat = tf.diag(tf.ones(shape=[vocab_length]))
address1_embed = tf.nn.embedding_lookup(identity_mat, address1_ph)
address2_embed = tf.nn.embedding_lookup(identity_mat, address2_ph)
# Define Model
text_snn = model.snn(address1_embed, address2_embed, dropout_keep_prob_ph,
vocab_length, num_features, max_address_len)
# Define Accuracy
batch_accuracy = model.accuracy(text_snn, y_target_ph)
# Define Loss
batch_loss = model.loss(text_snn, y_target_ph, margin)
# Define Predictions
predictions = model.get_predictions(text_snn)
# Declare optimizer
optimizer = tf.train.AdamOptimizer(0.01)
# Apply gradients
train_op = optimizer.minimize(batch_loss)
# Initialize Variables
init = tf.global_variables_initializer()
sess.run(init)
# Train loop
train_loss_vec = []
train_acc_vec = []