Copyright 2019 The TensorFlow Authors.

Text generation with an RNN

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.

Note: Enable GPU acceleration to execute this notebook faster. In Colab: Runtime > Change runtime type > Hardware acclerator > GPU. If running locally make sure TensorFlow version >= 1.11.

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":

QUEENE:
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.

BISHOP OF ELY:
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?

ESCALUS:
The cause why then we are all resolved more sons.

VOLUMNIA:
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.

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

PETRUCHIO:
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.

Setup

Import TensorFlow and other libraries

Download the Shakespeare dataset

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

Read the data

First, look in the text:

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.

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

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

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:

Print the first examples input and target values:

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.

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.

Build The Model

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

• tf.keras.layers.Embedding: The input layer. A trainable lookup table that will map the numbers of each character to a vector with embedding_dim dimensions;
• tf.keras.layers.GRU: A type of RNN with size units=rnn_units (You can also use a LSTM layer here.)
• tf.keras.layers.Dense: The output layer, with vocab_size outputs.

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:

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:

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

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.

Note: It is important to sample from this distribution as taking the argmax of the distribution can easily get the model stuck in a loop.

Try it for the first example in the batch:

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

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

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.

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.

Configure checkpoints

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

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.

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.

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.

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.

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.