Text generation with an RNN

View on TensorFlow.org Run in Google Colab View source on GitHub Download notebook

This tutorial demonstrates how to generate text using a character-based RNN. We will work with a dataset of Shakespeare's writing from Andrej Karpathy's The Unreasonable Effectiveness of Recurrent Neural Networks. Given a sequence of characters from this data ("Shakespear"), train a model to predict the next character in the sequence ("e"). Longer sequences of text can be generated by calling the model repeatedly.

This tutorial includes runnable code implemented using tf.keras and eager execution. The following is sample output when the model in this tutorial trained for 30 epochs, and started with the string "Q":

I had thought thou hadst a Roman; for the oracle,
Thus by All bids the man against the word,
Which are so weak of care, by old care done;
Your children were in your holy love,
And the precipitation through the bleeding throne.

Marry, and will, my lord, to weep in such a one were prettiest;
Yet now I was adopted heir
Of the world's lamentable day,
To watch the next way with his father with his face?

The cause why then we are all resolved more sons.

O, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, no, it is no sin it should be dead,
And love and pale as any will to that word.

But how long have I heard the soul for this world,
And show his hands of life be proved to stand.

I say he look'd on, if I must be content
To stay him from the fatal of our country's bliss.
His lordship pluck'd from this sentence then for prey,
And then let us twain, being the moon,
were she such a case as fills m

While some of the sentences are grammatical, most do not make sense. The model has not learned the meaning of words, but consider:

  • The model is character-based. When training started, the model did not know how to spell an English word, or that words were even a unit of text.

  • The structure of the output resembles a play—blocks of text generally begin with a speaker name, in all capital letters similar to the dataset.

  • As demonstrated below, the model is trained on small batches of text (100 characters each), and is still able to generate a longer sequence of text with coherent structure.


Import TensorFlow and other libraries

import tensorflow as tf

import numpy as np
import os
import time

Download the Shakespeare dataset

Change the following line to run this code on your own data.

path_to_file = tf.keras.utils.get_file('shakespeare.txt', 'https://storage.googleapis.com/download.tensorflow.org/data/shakespeare.txt')
Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/shakespeare.txt
1122304/1115394 [==============================] - 0s 0us/step

Read the data

First, look in the text:

# Read, then decode for py2 compat.
text = open(path_to_file, 'rb').read().decode(encoding='utf-8')
# length of text is the number of characters in it
print ('Length of text: {} characters'.format(len(text)))
Length of text: 1115394 characters

# Take a look at the first 250 characters in text
First Citizen:
Before we proceed any further, hear me speak.

Speak, speak.

First Citizen:
You are all resolved rather to die than to famish?

Resolved. resolved.

First Citizen:
First, you know Caius Marcius is chief enemy to the people.

# The unique characters in the file
vocab = sorted(set(text))
print ('{} unique characters'.format(len(vocab)))
65 unique characters

Process the text

Vectorize the text

Before training, we need to map strings to a numerical representation. Create two lookup tables: one mapping characters to numbers, and another for numbers to characters.

# Creating a mapping from unique characters to indices
char2idx = {u:i for i, u in enumerate(vocab)}
idx2char = np.array(vocab)

text_as_int = np.array([char2idx[c] for c in text])

Now we have an integer representation for each character. Notice that we mapped the character as indexes from 0 to len(unique).

for char,_ in zip(char2idx, range(20)):
    print('  {:4s}: {:3d},'.format(repr(char), char2idx[char]))
print('  ...\n}')
  '\n':   0,
  ' ' :   1,
  '!' :   2,
  '$' :   3,
  '&' :   4,
  "'" :   5,
  ',' :   6,
  '-' :   7,
  '.' :   8,
  '3' :   9,
  ':' :  10,
  ';' :  11,
  '?' :  12,
  'A' :  13,
  'B' :  14,
  'C' :  15,
  'D' :  16,
  'E' :  17,
  'F' :  18,
  'G' :  19,

# Show how the first 13 characters from the text are mapped to integers
print ('{} ---- characters mapped to int ---- > {}'.format(repr(text[:13]), text_as_int[:13]))
'First Citizen' ---- characters mapped to int ---- > [18 47 56 57 58  1 15 47 58 47 64 43 52]

The prediction task

Given a character, or a sequence of characters, what is the most probable next character? This is the task we're training the model to perform. The input to the model will be a sequence of characters, and we train the model to predict the output—the following character at each time step.

Since RNNs maintain an internal state that depends on the previously seen elements, given all the characters computed until this moment, what is the next character?

Create training examples and targets

Next divide the text into example sequences. Each input sequence will contain seq_length characters from the text.

For each input sequence, the corresponding targets contain the same length of text, except shifted one character to the right.

So break the text into chunks of seq_length+1. For example, say seq_length is 4 and our text is "Hello". The input sequence would be "Hell", and the target sequence "ello".

To do this first use the tf.data.Dataset.from_tensor_slices function to convert the text vector into a stream of character indices.

# The maximum length sentence we want for a single input in characters
seq_length = 100
examples_per_epoch = len(text)//(seq_length+1)

# Create training examples / targets
char_dataset = tf.data.Dataset.from_tensor_slices(text_as_int)

for i in char_dataset.take(5):

The batch method lets us easily convert these individual characters to sequences of the desired size.

sequences = char_dataset.batch(seq_length+1, drop_remainder=True)

for item in sequences.take(5):
'First Citizen:\nBefore we proceed any further, hear me speak.\n\nAll:\nSpeak, speak.\n\nFirst Citizen:\nYou '
'are all resolved rather to die than to famish?\n\nAll:\nResolved. resolved.\n\nFirst Citizen:\nFirst, you k'
"now Caius Marcius is chief enemy to the people.\n\nAll:\nWe know't, we know't.\n\nFirst Citizen:\nLet us ki"
"ll him, and we'll have corn at our own price.\nIs't a verdict?\n\nAll:\nNo more talking on't; let it be d"
'one: away, away!\n\nSecond Citizen:\nOne word, good citizens.\n\nFirst Citizen:\nWe are accounted poor citi'

For each sequence, duplicate and shift it to form the input and target text by using the map method to apply a simple function to each batch:

def split_input_target(chunk):
    input_text = chunk[:-1]
    target_text = chunk[1:]
    return input_text, target_text

dataset = sequences.map(split_input_target)

Print the first examples input and target values:

for input_example, target_example in  dataset.take(1):
  print ('Input data: ', repr(''.join(idx2char[input_example.numpy()])))
  print ('Target data:', repr(''.join(idx2char[target_example.numpy()])))
Input data:  'First Citizen:\nBefore we proceed any further, hear me speak.\n\nAll:\nSpeak, speak.\n\nFirst Citizen:\nYou'
Target data: 'irst Citizen:\nBefore we proceed any further, hear me speak.\n\nAll:\nSpeak, speak.\n\nFirst Citizen:\nYou '

Each index of these vectors are processed as one time step. For the input at time step 0, the model receives the index for "F" and trys to predict the index for "i" as the next character. At the next timestep, it does the same thing but the RNN considers the previous step context in addition to the current input character.

for i, (input_idx, target_idx) in enumerate(zip(input_example[:5], target_example[:5])):
    print("Step {:4d}".format(i))
    print("  input: {} ({:s})".format(input_idx, repr(idx2char[input_idx])))
    print("  expected output: {} ({:s})".format(target_idx, repr(idx2char[target_idx])))
Step    0
  input: 18 ('F')
  expected output: 47 ('i')
Step    1
  input: 47 ('i')
  expected output: 56 ('r')
Step    2
  input: 56 ('r')
  expected output: 57 ('s')
Step    3
  input: 57 ('s')
  expected output: 58 ('t')
Step    4
  input: 58 ('t')
  expected output: 1 (' ')

Create training batches

We used tf.data to split the text into manageable sequences. But before feeding this data into the model, we need to shuffle the data and pack it into batches.

# Batch size

# Buffer size to shuffle the dataset
# (TF data is designed to work with possibly infinite sequences,
# so it doesn't attempt to shuffle the entire sequence in memory. Instead,
# it maintains a buffer in which it shuffles elements).

dataset = dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE, drop_remainder=True)

<BatchDataset shapes: ((64, 100), (64, 100)), types: (tf.int64, tf.int64)>

Build The Model

Use tf.keras.Sequential to define the model. For this simple example three layers are used to define our model:

# Length of the vocabulary in chars
vocab_size = len(vocab)

# The embedding dimension
embedding_dim = 256

# Number of RNN units
rnn_units = 1024
def build_model(vocab_size, embedding_dim, rnn_units, batch_size):
  model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim,
                              batch_input_shape=[batch_size, None]),
  return model
model = build_model(
  vocab_size = len(vocab),

For each character the model looks up the embedding, runs the GRU one timestep with the embedding as input, and applies the dense layer to generate logits predicting the log-likelihood of the next character:

A drawing of the data passing through the model

Please note that we choose to Keras sequential model here since all the layers in the model only have single input and produce single output. In case you want to retrieve and reuse the states from stateful RNN layer, you might want to build your model with Keras functional API or model subclassing. Please check Keras RNN guide for more details.

Try the model

Now run the model to see that it behaves as expected.

First check the shape of the output:

for input_example_batch, target_example_batch in dataset.take(1):
  example_batch_predictions = model(input_example_batch)
  print(example_batch_predictions.shape, "# (batch_size, sequence_length, vocab_size)")
(64, 100, 65) # (batch_size, sequence_length, vocab_size)

In the above example the sequence length of the input is 100 but the model can be run on inputs of any length:

Model: "sequential"
Layer (type)                 Output Shape              Param #   
embedding (Embedding)        (64, None, 256)           16640     
gru (GRU)                    (64, None, 1024)          3938304   
dense (Dense)                (64, None, 65)            66625     
Total params: 4,021,569
Trainable params: 4,021,569
Non-trainable params: 0

To get actual predictions from the model we need to sample from the output distribution, to get actual character indices. This distribution is defined by the logits over the character vocabulary.

Try it for the first example in the batch:

sampled_indices = tf.random.categorical(example_batch_predictions[0], num_samples=1)
sampled_indices = tf.squeeze(sampled_indices,axis=-1).numpy()

This gives us, at each timestep, a prediction of the next character index:

array([ 3, 26, 28, 34, 20, 22, 57, 12, 32, 12,  4, 35, 29, 37, 52, 24, 36,
       37, 52, 18, 61, 56, 63, 36, 15, 27,  3, 38, 38, 59, 41, 58,  2, 32,
       24, 49, 62, 17, 14, 56,  3, 44, 32, 58, 15, 63,  4, 46, 30, 59, 10,
        0, 15, 58, 25, 25, 44, 34, 17, 26, 63, 23, 59,  6, 32, 15,  1,  6,
       22,  6, 37,  3, 40,  0, 20, 22, 22, 30,  7, 56, 48, 15, 11, 49, 27,
       27,  7,  4, 22, 19, 46,  1, 43, 56, 41, 44, 11, 41, 13, 39])

Decode these to see the text predicted by this untrained model:

print("Input: \n", repr("".join(idx2char[input_example_batch[0]])))
print("Next Char Predictions: \n", repr("".join(idx2char[sampled_indices ])))
 "ee--keep it to thyself--\nThis day those enemies are put to death,\nAnd I in better state than e'er I "

Next Char Predictions: 
 '$NPVHJs?T?&WQYnLXYnFwryXCO$ZZuct!TLkxEBr$fTtCy&hRu:\nCtMMfVENyKu,TC ,J,Y$b\nHJJR-rjC;kOO-&JGh ercf;cAa'

Train the model

At this point the problem can be treated as a standard classification problem. Given the previous RNN state, and the input this time step, predict the class of the next character.

Attach an optimizer, and a loss function

The standard tf.keras.losses.sparse_categorical_crossentropy loss function works in this case because it is applied across the last dimension of the predictions.

Because our model returns logits, we need to set the from_logits flag.

def loss(labels, logits):
  return tf.keras.losses.sparse_categorical_crossentropy(labels, logits, from_logits=True)

example_batch_loss  = loss(target_example_batch, example_batch_predictions)
print("Prediction shape: ", example_batch_predictions.shape, " # (batch_size, sequence_length, vocab_size)")
print("scalar_loss:      ", example_batch_loss.numpy().mean())
Prediction shape:  (64, 100, 65)  # (batch_size, sequence_length, vocab_size)
scalar_loss:       4.174199

Configure the training procedure using the tf.keras.Model.compile method. We'll use tf.keras.optimizers.Adam with default arguments and the loss function.

model.compile(optimizer='adam', loss=loss)

Configure checkpoints

Use a tf.keras.callbacks.ModelCheckpoint to ensure that checkpoints are saved during training:

# Directory where the checkpoints will be saved
checkpoint_dir = './training_checkpoints'
# Name of the checkpoint files
checkpoint_prefix = os.path.join(checkpoint_dir, "ckpt_{epoch}")


Execute the training

To keep training time reasonable, use 10 epochs to train the model. In Colab, set the runtime to GPU for faster training.

history = model.fit(dataset, epochs=EPOCHS, callbacks=[checkpoint_callback])
Epoch 1/10
172/172 [==============================] - 4s 26ms/step - loss: 2.6670
Epoch 2/10
172/172 [==============================] - 5s 26ms/step - loss: 1.9463
Epoch 3/10
172/172 [==============================] - 5s 26ms/step - loss: 1.6820
Epoch 4/10
172/172 [==============================] - 4s 26ms/step - loss: 1.5353
Epoch 5/10
172/172 [==============================] - 4s 26ms/step - loss: 1.4499
Epoch 6/10
172/172 [==============================] - 4s 26ms/step - loss: 1.3902
Epoch 7/10
172/172 [==============================] - 4s 26ms/step - loss: 1.3458
Epoch 8/10
172/172 [==============================] - 4s 26ms/step - loss: 1.3072
Epoch 9/10
172/172 [==============================] - 4s 26ms/step - loss: 1.2722
Epoch 10/10
172/172 [==============================] - 4s 26ms/step - loss: 1.2400

Generate text

Restore the latest checkpoint

To keep this prediction step simple, use a batch size of 1.

Because of the way the RNN state is passed from timestep to timestep, the model only accepts a fixed batch size once built.

To run the model with a different batch_size, we need to rebuild the model and restore the weights from the checkpoint.

model = build_model(vocab_size, embedding_dim, rnn_units, batch_size=1)


model.build(tf.TensorShape([1, None]))
Model: "sequential_1"
Layer (type)                 Output Shape              Param #   
embedding_1 (Embedding)      (1, None, 256)            16640     
gru_1 (GRU)                  (1, None, 1024)           3938304   
dense_1 (Dense)              (1, None, 65)             66625     
Total params: 4,021,569
Trainable params: 4,021,569
Non-trainable params: 0

The prediction loop

The following code block generates the text:

  • It Starts by choosing a start string, initializing the RNN state and setting the number of characters to generate.

  • Get the prediction distribution of the next character using the start string and the RNN state.

  • Then, use a categorical distribution to calculate the index of the predicted character. Use this predicted character as our next input to the model.

  • The RNN state returned by the model is fed back into the model so that it now has more context, instead than only one character. After predicting the next character, the modified RNN states are again fed back into the model, which is how it learns as it gets more context from the previously predicted characters.

To generate text the model's output is fed back to the input

Looking at the generated text, you'll see the model knows when to capitalize, make paragraphs and imitates a Shakespeare-like writing vocabulary. With the small number of training epochs, it has not yet learned to form coherent sentences.

def generate_text(model, start_string):
  # Evaluation step (generating text using the learned model)

  # Number of characters to generate
  num_generate = 1000

  # Converting our start string to numbers (vectorizing)
  input_eval = [char2idx[s] for s in start_string]
  input_eval = tf.expand_dims(input_eval, 0)

  # Empty string to store our results
  text_generated = []

  # Low temperatures results in more predictable text.
  # Higher temperatures results in more surprising text.
  # Experiment to find the best setting.
  temperature = 1.0

  # Here batch size == 1
  for i in range(num_generate):
      predictions = model(input_eval)
      # remove the batch dimension
      predictions = tf.squeeze(predictions, 0)

      # using a categorical distribution to predict the character returned by the model
      predictions = predictions / temperature
      predicted_id = tf.random.categorical(predictions, num_samples=1)[-1,0].numpy()

      # We pass the predicted character as the next input to the model
      # along with the previous hidden state
      input_eval = tf.expand_dims([predicted_id], 0)


  return (start_string + ''.join(text_generated))
print(generate_text(model, start_string=u"ROMEO: "))
ROMEO: thou shadester'd in the wish proud body.

About it, let no harberit to do
that matter to look upon her, every
treal true to my dismal tupond Ifam and his grayly
They was but a dinnates, as I have thosping upon:
Tybalt. Betoesellign: you are gone.

Nay, to my sure they stand not am England;
I will not baw you gone to joy of him, if ever
Most in upon my branches and the prince'll repealt
to prison; and will I lean to her.
Good, lords, less sentenced the new damn'd
Their man that please you, to kept thou not know my milanam th.

Do you must not, dogs Burgud,
He'ld not be crouched: thou have wound
The priest-traitor's larpet-times, to'er hours
I' this thy days of mine.
Please the midicts or this,--begin was denied the
trivianhy robosy well;
And we will forget you from blown.
For mangle's beloves; took--

What are you all, you'll merry least up,
And tradies thee reverend pitch
Did conjeys a bit me? if we would sure, for ever
the true puns worl

The easiest thing you can do to improve the results it to train it for longer (try EPOCHS=30).

You can also experiment with a different start string, or try adding another RNN layer to improve the model's accuracy, or adjusting the temperature parameter to generate more or less random predictions.

Advanced: Customized Training

The above training procedure is simple, but does not give you much control.

So now that you've seen how to run the model manually let's unpack the training loop, and implement it ourselves. This gives a starting point if, for example, to implement curriculum learning to help stabilize the model's open-loop output.

We will use tf.GradientTape to track the gradients. You can learn more about this approach by reading the eager execution guide.

The procedure works as follows:

  • First, initialize the RNN state. We do this by calling the tf.keras.Model.reset_states method.

  • Next, iterate over the dataset (batch by batch) and calculate the predictions associated with each.

  • Open a tf.GradientTape, and calculate the predictions and loss in that context.

  • Calculate the gradients of the loss with respect to the model variables using the tf.GradientTape.grads method.

  • Finally, take a step downwards by using the optimizer's tf.train.Optimizer.apply_gradients method.

model = build_model(
  vocab_size = len(vocab),
optimizer = tf.keras.optimizers.Adam()
def train_step(inp, target):
  with tf.GradientTape() as tape:
    predictions = model(inp)
    loss = tf.reduce_mean(
            target, predictions, from_logits=True))
  grads = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(grads, model.trainable_variables))

  return loss
# Training step

for epoch in range(EPOCHS):
  start = time.time()

  # initializing the hidden state at the start of every epoch
  # initally hidden is None
  hidden = model.reset_states()

  for (batch_n, (inp, target)) in enumerate(dataset):
    loss = train_step(inp, target)

    if batch_n % 100 == 0:
      template = 'Epoch {} Batch {} Loss {}'
      print(template.format(epoch+1, batch_n, loss))

  # saving (checkpoint) the model every 5 epochs
  if (epoch + 1) % 5 == 0:

  print ('Epoch {} Loss {:.4f}'.format(epoch+1, loss))
  print ('Time taken for 1 epoch {} sec\n'.format(time.time() - start))

Epoch 1 Batch 0 Loss 4.175290107727051
Epoch 1 Batch 100 Loss 2.331796884536743
Epoch 1 Loss 2.1474
Time taken for 1 epoch 6.129810571670532 sec

Epoch 2 Batch 0 Loss 2.159684658050537
Epoch 2 Batch 100 Loss 1.913728952407837
Epoch 2 Loss 1.7723
Time taken for 1 epoch 5.161072015762329 sec

Epoch 3 Batch 0 Loss 1.7521073818206787
Epoch 3 Batch 100 Loss 1.668346881866455
Epoch 3 Loss 1.6784
Time taken for 1 epoch 5.199112176895142 sec

Epoch 4 Batch 0 Loss 1.5660181045532227
Epoch 4 Batch 100 Loss 1.4729632139205933
Epoch 4 Loss 1.4882
Time taken for 1 epoch 5.200871706008911 sec

Epoch 5 Batch 0 Loss 1.4419196844100952
Epoch 5 Batch 100 Loss 1.4604172706604004
Epoch 5 Loss 1.4317
Time taken for 1 epoch 5.136796236038208 sec

Epoch 6 Batch 0 Loss 1.3333739042282104
Epoch 6 Batch 100 Loss 1.396125316619873
Epoch 6 Loss 1.3811
Time taken for 1 epoch 5.062854528427124 sec

Epoch 7 Batch 0 Loss 1.3015271425247192
Epoch 7 Batch 100 Loss 1.2896015644073486
Epoch 7 Loss 1.3486
Time taken for 1 epoch 5.06119441986084 sec

Epoch 8 Batch 0 Loss 1.2755285501480103
Epoch 8 Batch 100 Loss 1.2810440063476562
Epoch 8 Loss 1.2982
Time taken for 1 epoch 5.0638978481292725 sec

Epoch 9 Batch 0 Loss 1.2518764734268188
Epoch 9 Batch 100 Loss 1.2769352197647095
Epoch 9 Loss 1.3319
Time taken for 1 epoch 5.082948446273804 sec

Epoch 10 Batch 0 Loss 1.1955050230026245
Epoch 10 Batch 100 Loss 1.2386566400527954
Epoch 10 Loss 1.2556
Time taken for 1 epoch 5.066011190414429 sec