dlnd_tv_script_generation_t1-checkpoint


TV Script Generation

In this project, you'll generate your own Simpsons TV scripts using RNNs. You'll be using part of the Simpsons dataset of scripts from 27 seasons. The Neural Network you'll build will generate a new TV script for a scene at Moe's Tavern.

Get the Data

The data is already provided for you. You'll be using a subset of the original dataset. It consists of only the scenes in Moe's Tavern. This doesn't include other versions of the tavern, like "Moe's Cavern", "Flaming Moe's", "Uncle Moe's Family Feed-Bag", etc..


In [1]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper

data_dir = './data/simpsons/moes_tavern_lines.txt'
text = helper.load_data(data_dir)
# Ignore notice, since we don't use it for analysing the data
text = text[81:]

Explore the Data

Play around with view_sentence_range to view different parts of the data.


In [2]:
view_sentence_range = (0, 10)

"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import numpy as np

print('Dataset Stats')
print('Roughly the number of unique words: {}'.format(len({word: None for word in text.split()})))
scenes = text.split('\n\n')
print('Number of scenes: {}'.format(len(scenes)))
sentence_count_scene = [scene.count('\n') for scene in scenes]
print('Average number of sentences in each scene: {}'.format(np.average(sentence_count_scene)))

sentences = [sentence for scene in scenes for sentence in scene.split('\n')]
print('Number of lines: {}'.format(len(sentences)))
word_count_sentence = [len(sentence.split()) for sentence in sentences]
print('Average number of words in each line: {}'.format(np.average(word_count_sentence)))

print()
print('The sentences {} to {}:'.format(*view_sentence_range))
print('\n'.join(text.split('\n')[view_sentence_range[0]:view_sentence_range[1]]))


Dataset Stats
Roughly the number of unique words: 11492
Number of scenes: 262
Average number of sentences in each scene: 15.248091603053435
Number of lines: 4257
Average number of words in each line: 11.50434578341555

The sentences 0 to 10:
Moe_Szyslak: (INTO PHONE) Moe's Tavern. Where the elite meet to drink.
Bart_Simpson: Eh, yeah, hello, is Mike there? Last name, Rotch.
Moe_Szyslak: (INTO PHONE) Hold on, I'll check. (TO BARFLIES) Mike Rotch. Mike Rotch. Hey, has anybody seen Mike Rotch, lately?
Moe_Szyslak: (INTO PHONE) Listen you little puke. One of these days I'm gonna catch you, and I'm gonna carve my name on your back with an ice pick.
Moe_Szyslak: What's the matter Homer? You're not your normal effervescent self.
Homer_Simpson: I got my problems, Moe. Give me another one.
Moe_Szyslak: Homer, hey, you should not drink to forget your problems.
Barney_Gumble: Yeah, you should only drink to enhance your social skills.


Implement Preprocessing Functions

The first thing to do to any dataset is preprocessing. Implement the following preprocessing functions below:

  • Lookup Table
  • Tokenize Punctuation

Lookup Table

To create a word embedding, you first need to transform the words to ids. In this function, create two dictionaries:

  • Dictionary to go from the words to an id, we'll call vocab_to_int
  • Dictionary to go from the id to word, we'll call int_to_vocab

Return these dictionaries in the following tuple (vocab_to_int, int_to_vocab)


In [3]:
import numpy as np
import problem_unittests as tests

def create_lookup_tables(text):
    """
    Create lookup tables for vocabulary
    :param text: The text of tv scripts split into words
    :return: A tuple of dicts (vocab_to_int, int_to_vocab)
    """
    # TODO: Implement Function
    vocab_to_int = {w:i for i, w in enumerate(set(text))}
    int_to_vocab = {i:w for i, w in enumerate(set(text))}
    return vocab_to_int, int_to_vocab


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_create_lookup_tables(create_lookup_tables)


Tests Passed

Tokenize Punctuation

We'll be splitting the script into a word array using spaces as delimiters. However, punctuations like periods and exclamation marks make it hard for the neural network to distinguish between the word "bye" and "bye!".

Implement the function token_lookup to return a dict that will be used to tokenize symbols like "!" into "||Exclamation_Mark||". Create a dictionary for the following symbols where the symbol is the key and value is the token:

  • Period ( . )
  • Comma ( , )
  • Quotation Mark ( " )
  • Semicolon ( ; )
  • Exclamation mark ( ! )
  • Question mark ( ? )
  • Left Parentheses ( ( )
  • Right Parentheses ( ) )
  • Dash ( -- )
  • Return ( \n )

This dictionary will be used to token the symbols and add the delimiter (space) around it. This separates the symbols as it's own word, making it easier for the neural network to predict on the next word. Make sure you don't use a token that could be confused as a word. Instead of using the token "dash", try using something like "||dash||".


In [4]:
def token_lookup():
    """
    Generate a dict to turn punctuation into a token.
    :return: Tokenize dictionary where the key is the punctuation and the value is the token
    """
    return {
        '.': '||Period||',
        ',': '||Comma||',
        '"': '||Quotation_Mark||',
        ';': '||Semicolon||',
        '!': '||Exclamation_mark||',
        '?': '||Question_mark||',
        '(': '||Left_Parentheses||',
        ')': '||Right_Parentheses||',
        '--': '||Dash||',
        "\n": '||Return||'
    }

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_tokenize(token_lookup)


Tests Passed

Preprocess all the data and save it

Running the code cell below will preprocess all the data and save it to file.


In [5]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
# Preprocess Training, Validation, and Testing Data
helper.preprocess_and_save_data(data_dir, token_lookup, create_lookup_tables)

Check Point

This is your first checkpoint. If you ever decide to come back to this notebook or have to restart the notebook, you can start from here. The preprocessed data has been saved to disk.


In [6]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import helper
import numpy as np
import problem_unittests as tests

int_text, vocab_to_int, int_to_vocab, token_dict = helper.load_preprocess()

Build the Neural Network

You'll build the components necessary to build a RNN by implementing the following functions below:

  • get_inputs
  • get_init_cell
  • get_embed
  • build_rnn
  • build_nn
  • get_batches

Check the Version of TensorFlow and Access to GPU


In [7]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from distutils.version import LooseVersion
import warnings
import tensorflow as tf

# Check TensorFlow Version
assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer'
print('TensorFlow Version: {}'.format(tf.__version__))

# Check for a GPU
if not tf.test.gpu_device_name():
    warnings.warn('No GPU found. Please use a GPU to train your neural network.')
else:
    print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))


TensorFlow Version: 1.0.1
Default GPU Device: /gpu:0

Input

Implement the get_inputs() function to create TF Placeholders for the Neural Network. It should create the following placeholders:

  • Input text placeholder named "input" using the TF Placeholder name parameter.
  • Targets placeholder
  • Learning Rate placeholder

Return the placeholders in the following the tuple (Input, Targets, LearingRate)


In [8]:
def get_inputs():
    """
    Create TF Placeholders for input, targets, and learning rate.
    :return: Tuple (input, targets, learning rate)
    """
    # TODO: Implement Function
    inputs = tf.placeholder(dtype=tf.int32, shape=[None, None], name='input')
    targets = tf.placeholder(dtype=tf.int32, shape=[None, None], name='targets')
    learning_rate = tf.placeholder(dtype=tf.float32, name='learning_rate')
    return inputs, targets, learning_rate


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_get_inputs(get_inputs)


Tests Passed

Build RNN Cell and Initialize

Stack one or more BasicLSTMCells in a MultiRNNCell.

  • The Rnn size should be set using rnn_size
  • Initalize Cell State using the MultiRNNCell's zero_state() function
    • Apply the name "initial_state" to the initial state using tf.identity()

Return the cell and initial state in the following tuple (Cell, InitialState)


In [9]:
def get_init_cell(batch_size, rnn_size, keep_prob=0.8, layers=3):
    """
    Create an RNN Cell and initialize it.
    :param batch_size: Size of batches
    :param rnn_size: Size of RNNs
    :return: Tuple (cell, initialize state)
    """
    cell = tf.contrib.rnn.BasicLSTMCell(rnn_size)
    cell = tf.contrib.rnn.DropoutWrapper(cell, output_keep_prob=keep_prob)
    multi = tf.contrib.rnn.MultiRNNCell([cell] * layers)
    init_state = multi.zero_state(batch_size, tf.float32)
    init_state = tf.identity(init_state, 'initial_state')
    return multi, init_state


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_get_init_cell(get_init_cell)


Tests Passed

Word Embedding

Apply embedding to input_data using TensorFlow. Return the embedded sequence.


In [10]:
def get_embed(input_data, vocab_size, embed_dim):
    """
    Create embedding for <input_data>.
    :param input_data: TF placeholder for text input.
    :param vocab_size: Number of words in vocabulary.
    :param embed_dim: Number of embedding dimensions
    :return: Embedded input.
    """
    embeddings = tf.Variable(tf.random_uniform((vocab_size, embed_dim), -1, 1))
    embed = tf.nn.embedding_lookup(embeddings, input_data)
    return embed


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_get_embed(get_embed)


Tests Passed

Build RNN

You created a RNN Cell in the get_init_cell() function. Time to use the cell to create a RNN.

Return the outputs and final_state state in the following tuple (Outputs, FinalState)


In [11]:
def build_rnn(cell, inputs):
    """
    Create a RNN using a RNN Cell
    :param cell: RNN Cell
    :param inputs: Input text data
    :return: Tuple (Outputs, Final State)
    """
    outputs, final_state = tf.nn.dynamic_rnn(cell, inputs, dtype=tf.float32)
    final_state = tf.identity(final_state, 'final_state')
    return outputs, final_state


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_build_rnn(build_rnn)


Tests Passed

Build the Neural Network

Apply the functions you implemented above to:

  • Apply embedding to input_data using your get_embed(input_data, vocab_size, embed_dim) function.
  • Build RNN using cell and your build_rnn(cell, inputs) function.
  • Apply a fully connected layer with a linear activation and vocab_size as the number of outputs.

Return the logits and final state in the following tuple (Logits, FinalState)


In [12]:
def build_nn(cell, rnn_size, input_data, vocab_size):
    """
    Build part of the neural network
    :param cell: RNN cell
    :param rnn_size: Size of rnns
    :param input_data: Input data
    :param vocab_size: Vocabulary size
    :return: Tuple (Logits, FinalState)
    """
    embed = get_embed(input_data, vocab_size, rnn_size)
    outputs, final_state = build_rnn(cell, embed)
    logits = tf.contrib.layers.fully_connected(outputs, vocab_size, activation_fn=None)
    return logits, final_state


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_build_nn(build_nn)


Tests Passed

Batches

Implement get_batches to create batches of input and targets using int_text. The batches should be a Numpy array with the shape (number of batches, 2, batch size, sequence length). Each batch contains two elements:

  • The first element is a single batch of input with the shape [batch size, sequence length]
  • The second element is a single batch of targets with the shape [batch size, sequence length]

If you can't fill the last batch with enough data, drop the last batch.

For exmple, get_batches([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], 2, 3) would return a Numpy array of the following:

[
  # First Batch
  [
    # Batch of Input
    [[ 1  2  3], [ 7  8  9]],
    # Batch of targets
    [[ 2  3  4], [ 8  9 10]]
  ],

  # Second Batch
  [
    # Batch of Input
    [[ 4  5  6], [10 11 12]],
    # Batch of targets
    [[ 5  6  7], [11 12 13]]
  ]
]

In [13]:
def get_batches(int_text, batch_size, seq_length):
    """
    Return batches of input and target
    :param int_text: Text with the words replaced by their ids
    :param batch_size: The size of batch
    :param seq_length: The length of sequence
    :return: Batches as a Numpy array
    """
    # TODO: Implement Function
    n_batches = len(int_text) // (batch_size * seq_length)
    result = []
    for i in range(n_batches):
        inputs = []
        targets = []
        for j in range(batch_size):
            idx = i * seq_length + j * seq_length
            inputs.append(int_text[idx:idx + seq_length])
            targets.append(int_text[idx + 1:idx + seq_length + 1])
        result.append([inputs, targets])
    return np.array(result)


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_get_batches(get_batches)


Tests Passed

Neural Network Training

Hyperparameters

Tune the following parameters:

  • Set num_epochs to the number of epochs.
  • Set batch_size to the batch size.
  • Set rnn_size to the size of the RNNs.
  • Set seq_length to the length of sequence.
  • Set learning_rate to the learning rate.
  • Set show_every_n_batches to the number of batches the neural network should print progress.

In [14]:
# Number of Epochs
num_epochs = 100
# Batch Size
batch_size = 64
# RNN Size
rnn_size = 256
# Sequence Length
seq_length = 25
# Learning Rate
learning_rate = 0.01
# Show stats for every n number of batches
show_every_n_batches = 10

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
save_dir = './save'

Build the Graph

Build the graph using the neural network you implemented.


In [15]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
from tensorflow.contrib import seq2seq

train_graph = tf.Graph()
with train_graph.as_default():
    vocab_size = len(int_to_vocab)
    input_text, targets, lr = get_inputs()
    input_data_shape = tf.shape(input_text)
    cell, initial_state = get_init_cell(input_data_shape[0], rnn_size)
    logits, final_state = build_nn(cell, rnn_size, input_text, vocab_size)

    # Probabilities for generating words
    probs = tf.nn.softmax(logits, name='probs')

    # Loss function
    cost = seq2seq.sequence_loss(
        logits,
        targets,
        tf.ones([input_data_shape[0], input_data_shape[1]]))

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

    # Gradient Clipping
    gradients = optimizer.compute_gradients(cost)
    capped_gradients = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gradients]
    train_op = optimizer.apply_gradients(capped_gradients)

Train

Train the neural network on the preprocessed data. If you have a hard time getting a good loss, check the forms to see if anyone is having the same problem.


In [16]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
batches = get_batches(int_text, batch_size, seq_length)

with tf.Session(graph=train_graph) as sess:
    sess.run(tf.global_variables_initializer())

    for epoch_i in range(num_epochs):
        state = sess.run(initial_state, {input_text: batches[0][0]})

        for batch_i, (x, y) in enumerate(batches):
            feed = {
                input_text: x,
                targets: y,
                initial_state: state,
                lr: learning_rate}
            train_loss, state, _ = sess.run([cost, final_state, train_op], feed)

            # Show every <show_every_n_batches> batches
            if (epoch_i * len(batches) + batch_i) % show_every_n_batches == 0:
                print('Epoch {:>3} Batch {:>4}/{}   train_loss = {:.3f}'.format(
                    epoch_i,
                    batch_i,
                    len(batches),
                    train_loss))

    # Save Model
    saver = tf.train.Saver()
    saver.save(sess, save_dir)
    print('Model Trained and Saved')


---------------------------------------------------------------------------
ResourceExhaustedError                    Traceback (most recent call last)
/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1021     try:
-> 1022       return fn(*args)
   1023     except errors.OpError as e:

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1003                                  feed_dict, fetch_list, target_list,
-> 1004                                  status, run_metadata)
   1005 

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
     65             try:
---> 66                 next(self.gen)
     67             except StopIteration:

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
    465           compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466           pywrap_tensorflow.TF_GetCode(status))
    467   finally:

ResourceExhaustedError: OOM when allocating tensor with shape[256,6779]
	 [[Node: fully_connected/weights/Initializer/random_uniform/mul = Mul[T=DT_FLOAT, _class=["loc:@fully_connected/weights"], _device="/job:localhost/replica:0/task:0/gpu:0"](fully_connected/weights/Initializer/random_uniform/RandomUniform, fully_connected/weights/Initializer/random_uniform/sub)]]

During handling of the above exception, another exception occurred:

ResourceExhaustedError                    Traceback (most recent call last)
<ipython-input-16-396c263e7e73> in <module>()
      5 
      6 with tf.Session(graph=train_graph) as sess:
----> 7     sess.run(tf.global_variables_initializer())
      8 
      9     for epoch_i in range(num_epochs):

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    765     try:
    766       result = self._run(None, fetches, feed_dict, options_ptr,
--> 767                          run_metadata_ptr)
    768       if run_metadata:
    769         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
    963     if final_fetches or final_targets:
    964       results = self._do_run(handle, final_targets, final_fetches,
--> 965                              feed_dict_string, options, run_metadata)
    966     else:
    967       results = []

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1013     if handle is None:
   1014       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1015                            target_list, options, run_metadata)
   1016     else:
   1017       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1033         except KeyError:
   1034           pass
-> 1035       raise type(e)(node_def, op, message)
   1036 
   1037   def _extend_graph(self):

ResourceExhaustedError: OOM when allocating tensor with shape[256,6779]
	 [[Node: fully_connected/weights/Initializer/random_uniform/mul = Mul[T=DT_FLOAT, _class=["loc:@fully_connected/weights"], _device="/job:localhost/replica:0/task:0/gpu:0"](fully_connected/weights/Initializer/random_uniform/RandomUniform, fully_connected/weights/Initializer/random_uniform/sub)]]

Caused by op 'fully_connected/weights/Initializer/random_uniform/mul', defined at:
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/__main__.py", line 3, in <module>
    app.launch_new_instance()
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/kernelapp.py", line 474, in start
    ioloop.IOLoop.instance().start()
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/zmq/eventloop/ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tornado/ioloop.py", line 887, in start
    handler_func(fd_obj, events)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 276, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
    handler(stream, idents, msg)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 390, in execute_request
    user_expressions, allow_stdin)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/ipykernel/zmqshell.py", line 501, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
    if self.run_code(code, result):
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2881, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-15-33f70c17d6c6>", line 12, in <module>
    logits, final_state = build_nn(cell, rnn_size, input_text, vocab_size)
  File "<ipython-input-12-48f1ab25c4a9>", line 12, in build_nn
    logits = tf.contrib.layers.fully_connected(outputs, vocab_size, activation_fn=None)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 177, in func_with_args
    return func(*args, **current_args)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1409, in fully_connected
    outputs = layer.apply(inputs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/layers/base.py", line 303, in apply
    return self.__call__(inputs, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/layers/base.py", line 269, in __call__
    self.build(input_shapes[0])
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/layers/core.py", line 123, in build
    trainable=True)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 988, in get_variable
    custom_getter=custom_getter)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 890, in get_variable
    custom_getter=custom_getter)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 341, in get_variable
    validate_shape=validate_shape)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/layers/base.py", line 258, in variable_getter
    variable_getter=functools.partial(getter, **kwargs))
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/layers/base.py", line 208, in _add_variable
    trainable=trainable and self.trainable)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1310, in layer_variable_getter
    return _model_variable_getter(getter, *args, **kwargs)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1299, in _model_variable_getter
    custom_getter=getter)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 177, in func_with_args
    return func(*args, **current_args)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 268, in model_variable
    partitioner=partitioner, custom_getter=custom_getter)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 177, in func_with_args
    return func(*args, **current_args)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 225, in variable
    partitioner=partitioner)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 333, in _true_getter
    caching_device=caching_device, validate_shape=validate_shape)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 684, in _get_single_variable
    validate_shape=validate_shape)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 197, in __init__
    expected_shape=expected_shape)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 274, in _init_from_args
    initial_value(), name="initial_value", dtype=dtype)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/variable_scope.py", line 673, in <lambda>
    shape.as_list(), dtype=dtype, partition_info=partition_info)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/initializers.py", line 145, in _initializer
    dtype, seed=seed)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/random_ops.py", line 245, in random_uniform
    return math_ops.add(rnd * (maxval - minval), minval, name=name)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py", line 794, in binary_op_wrapper
    return func(x, y, name=name)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py", line 1015, in _mul_dispatch
    return gen_math_ops._mul(x, y, name=name)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1625, in _mul
    result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op
    op_def=op_def)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2327, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/leiming/anaconda2/envs/dlnd-tf-lab/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1226, in __init__
    self._traceback = _extract_stack()

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[256,6779]
	 [[Node: fully_connected/weights/Initializer/random_uniform/mul = Mul[T=DT_FLOAT, _class=["loc:@fully_connected/weights"], _device="/job:localhost/replica:0/task:0/gpu:0"](fully_connected/weights/Initializer/random_uniform/RandomUniform, fully_connected/weights/Initializer/random_uniform/sub)]]

Save Parameters

Save seq_length and save_dir for generating a new TV script.


In [ ]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
# Save parameters for checkpoint
helper.save_params((seq_length, save_dir))

Checkpoint


In [ ]:
"""
DON'T MODIFY ANYTHING IN THIS CELL
"""
import tensorflow as tf
import numpy as np
import helper
import problem_unittests as tests

_, vocab_to_int, int_to_vocab, token_dict = helper.load_preprocess()
seq_length, load_dir = helper.load_params()

Implement Generate Functions

Get Tensors

Get tensors from loaded_graph using the function get_tensor_by_name(). Get the tensors using the following names:

  • "input:0"
  • "initial_state:0"
  • "final_state:0"
  • "probs:0"

Return the tensors in the following tuple (InputTensor, InitialStateTensor, FinalStateTensor, ProbsTensor)


In [ ]:
def get_tensors(loaded_graph):
    """
    Get input, initial state, final state, and probabilities tensor from <loaded_graph>
    :param loaded_graph: TensorFlow graph loaded from file
    :return: Tuple (InputTensor, InitialStateTensor, FinalStateTensor, ProbsTensor)
    """
    inputs = loaded_graph.get_tensor_by_name('input:0')
    init_state = loaded_graph.get_tensor_by_name('initial_state:0')
    final_state = loaded_graph.get_tensor_by_name('final_state:0')
    probs = loaded_graph.get_tensor_by_name('probs:0')
    return inputs, init_state, final_state, probs


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_get_tensors(get_tensors)

Choose Word

Implement the pick_word() function to select the next word using probabilities.


In [ ]:
def pick_word(probabilities, int_to_vocab):
    """
    Pick the next word in the generated text
    :param probabilities: Probabilites of the next word
    :param int_to_vocab: Dictionary of word ids as the keys and words as the values
    :return: String of the predicted word
    """
    # TODO: Implement Function
    return int_to_vocab[np.argmax(probabilities)]


"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
tests.test_pick_word(pick_word)

Generate TV Script

This will generate the TV script for you. Set gen_length to the length of TV script you want to generate.


In [ ]:
gen_length = 200
# homer_simpson, moe_szyslak, or Barney_Gumble
prime_word = 'moe_szyslak'

"""
DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE
"""
loaded_graph = tf.Graph()
with tf.Session(graph=loaded_graph) as sess:
    # Load saved model
    loader = tf.train.import_meta_graph(load_dir + '.meta')
    loader.restore(sess, load_dir)

    # Get Tensors from loaded model
    input_text, initial_state, final_state, probs = get_tensors(loaded_graph)

    # Sentences generation setup
    gen_sentences = [prime_word + ':']
    prev_state = sess.run(initial_state, {input_text: np.array([[1]])})

    # Generate sentences
    for n in range(gen_length):
        # Dynamic Input
        dyn_input = [[vocab_to_int[word] for word in gen_sentences[-seq_length:]]]
        dyn_seq_length = len(dyn_input[0])

        # Get Prediction
        probabilities, prev_state = sess.run(
            [probs, final_state],
            {input_text: dyn_input, initial_state: prev_state})
        
        pred_word = pick_word(probabilities[dyn_seq_length-1], int_to_vocab)

        gen_sentences.append(pred_word)
    
    # Remove tokens
    tv_script = ' '.join(gen_sentences)
    for key, token in token_dict.items():
        ending = ' ' if key in ['\n', '(', '"'] else ''
        tv_script = tv_script.replace(' ' + token.lower(), key)
    tv_script = tv_script.replace('\n ', '\n')
    tv_script = tv_script.replace('( ', '(')
        
    print(tv_script)

The TV Script is Nonsensical

It's ok if the TV script doesn't make any sense. We trained on less than a megabyte of text. In order to get good results, you'll have to use a smaller vocabulary or get more data. Luckly there's more data! As we mentioned in the begging of this project, this is a subset of another dataset. We didn't have you train on all the data, because that would take too long. However, you are free to train your neural network on all the data. After you complete the project, of course.

Submitting This Project

When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as "dlnd_tv_script_generation.ipynb" and save it as a HTML file under "File" -> "Download as". Include the "helper.py" and "problem_unittests.py" files in your submission.