train_model.py

# training the built model_inputs

from build_model import *
from tensorflow.python.layers.core import Dense
from tensorflow.python.ops.rnn_cell_impl import _zero_state_tensors
# Set the Hyperparameters
epochs = 100
batch_size = 64
rnn_size = 256
num_layers = 2
learning_rate = 0.005
keep_probability = 0.75

# Build the graph
train_graph = tf.Graph()
# Set the graph to default to ensure that it is ready for training
with train_graph.as_default():

    # Load the model inputs
    input_data, targets, lr, keep_prob, summary_length, max_summary_length, text_length = model_inputs()

    # Create the training and inference logits
    training_logits, inference_logits = seq2seq_model(tf.reverse(input_data, [-1]),
                                                      targets,
                                                      keep_prob,
                                                      text_length,
                                                      summary_length,
                                                      max_summary_length,
                                                      len(vocab_to_int)+1,
                                                      rnn_size,
                                                      num_layers,
                                                      vocab_to_int,
                                                      batch_size)

    # Create tensors for the training logits and inference logits
    training_logits = tf.identity(training_logits.rnn_output, 'logits')
    inference_logits = tf.identity(inference_logits.sample_id, name='predictions')

    # Create the weights for sequence_loss
    masks = tf.sequence_mask(summary_length, max_summary_length, dtype=tf.float32, name='masks')

    with tf.name_scope("optimization"):
        # Loss function
        cost = tf.contrib.seq2seq.sequence_loss(
            training_logits,
            targets,
            masks)

        # Optimizer
        optimizer = tf.train.AdamOptimizer(learning_rate)

        # Gradient Clipping
        gradients = optimizer.compute_gradients(cost)
        capped_gradients = [(tf.clip_by_value(grad, -5., 5.), var) for grad, var in gradients if grad is not None]
        train_op = optimizer.apply_gradients(capped_gradients)
print("Graph is built.")