Text generation with RNN in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple RNN layer in TensorFlow.

TensorFlow

rnn_layer = tf.keras.layers.SimpleRNN([1], return_sequences=True)

Drag options to blanks, or click blank then click option'

Arelu

B0.1

CTrue

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using a float value instead of an integer for units.

Using activation function name instead of units.

Setting return_sequences instead of units.

The number 128 specifies the number of units in the RNN layer, which controls the output dimension.

2fill in blank

medium

Complete the code to compile the model with an appropriate loss function for text generation.

TensorFlow

model.compile(optimizer='adam', loss=[1])

Drag options to blanks, or click blank then click option'

A'categorical_crossentropy'

B'mse'

C'binary_crossentropy'

D'hinge'

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean squared error which is for regression.

Using binary crossentropy which is for two-class problems.

For text generation with multiple classes (characters or words), categorical_crossentropy is the correct loss function.

3fill in blank

hard

Fix the error in the code to correctly prepare input sequences for training.

TensorFlow

sequences = [text[i:i+[1]] for i in range(len(text) - seq_length)]

Drag options to blanks, or click blank then click option'

Aseq_length

Blen(text)

Ci

Dbatch_size

Attempts:

3 left

💡 Hint

Common Mistakes

Using the entire text length instead of the sequence length.

Using the loop variable i as the slice length.

The slice length should be seq_length to get fixed-size input sequences.

4fill in blank

hard

Fill both blanks to define the model input shape and output layer activation for text generation.

TensorFlow

model = tf.keras.Sequential([
  tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=64, input_length=[1]),
  tf.keras.layers.SimpleRNN(128),
  tf.keras.layers.Dense(vocab_size, activation=[2])
])

Drag options to blanks, or click blank then click option'

Aseq_length

B'softmax'

C'relu'

Dvocab_size

Attempts:

3 left

💡 Hint

Common Mistakes

Using vocab_size as input_length.

Using relu activation in the output layer.

The input_length should be seq_length to match input sequences. The output activation is softmax to predict probabilities over the vocabulary.

5fill in blank

hard

Fill all three blanks to generate text from the trained model step-by-step.

TensorFlow

input_eval = [char2idx[[1]]]
input_eval = tf.expand_dims(input_eval, 0)
predictions = model(input_eval)
predicted_id = tf.random.categorical(predictions[:, [2]], num_samples=1)[[3]][0,0].numpy()

Drag options to blanks, or click blank then click option'

A'start_char'

B0

C1

D'end_char'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'end_char' instead of 'start_char' to begin generation.

Using wrong indices for predictions slicing.

We start with the 'start_char' to begin generation. We sample from predictions at index 0 (the first time step). The [1] selects the sample dimension.

Practice

1. What is the main purpose of using an RNN in text generation tasks?

easy

A. To sort words alphabetically

B. To count the number of words in a sentence

C. To learn patterns in sequences of words and predict the next word

D. To translate text into images

Solution

1. Step 1: Understand RNN function in text

   RNNs process sequences and learn how words follow each other.

2. Step 2: Identify the goal of text generation

   The goal is to predict the next word based on previous words.

3. Final Answer:

   To learn patterns in sequences of words and predict the next word -> Option C

4. Quick Check:

   RNN predicts next word = B [OK]

Hint: RNNs handle sequences and predict next items [OK]

Common Mistakes:

• Thinking RNNs sort or count words
• Confusing RNN with image processing
• Assuming RNNs translate text directly

2. Which of the following is the correct way to add an embedding layer in a TensorFlow RNN model for text generation?

easy

A. tf.keras.layers.MaxPooling1D(pool_size=2)

B. tf.keras.layers.Dense(units=embedding_dim)

C. tf.keras.layers.Conv2D(filters=embedding_dim, kernel_size=3)

D. tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim)

Solution

1. Step 1: Identify embedding layer syntax

   Embedding layers use input_dim and output_dim to map words to vectors.

2. Step 2: Match correct TensorFlow layer

   tf.keras.layers.Embedding is the correct layer for word embeddings.

3. Final Answer:

   tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim) -> Option D

4. Quick Check:

   Embedding layer uses input_dim and output_dim = A [OK]

Hint: Embedding layer uses input_dim and output_dim parameters [OK]

Common Mistakes:

• Using Dense instead of Embedding for word vectors
• Confusing Conv2D with text embedding
• Applying MaxPooling1D incorrectly for embeddings

3. Given the following code snippet, what will be the shape of the output from the RNN layer?

model = tf.keras.Sequential([
  tf.keras.layers.Embedding(input_dim=1000, output_dim=64),
  tf.keras.layers.SimpleRNN(128, return_sequences=False),
  tf.keras.layers.Dense(1000, activation='softmax')
])

input_shape = (32, 10)  # batch size 32, sequence length 10
output = model(tf.random.uniform(input_shape, maxval=1000, dtype=tf.int32))
print(output.shape)

medium

A. (32, 1000)

B. (32, 10, 128)

C. (10, 128)

D. (32, 128)

Solution

1. Step 1: Analyze RNN layer output shape

   SimpleRNN with return_sequences=False outputs (batch_size, units) = (32, 128).

2. Step 2: Check Dense layer output shape

   Dense layer with 1000 units outputs (32, 1000).

3. Final Answer:

   (32, 1000) -> Option A

4. Quick Check:

   Final output shape = (batch_size, vocab_size) = C [OK]

Hint: return_sequences=False means RNN outputs last step only [OK]

Common Mistakes:

• Confusing return_sequences=True output shape
• Ignoring batch size in output shape
• Mixing RNN units with Dense output units

4. Which of the following statements is CORRECT about this TensorFlow RNN model code for text generation:

model = tf.keras.Sequential([
  tf.keras.layers.Embedding(input_dim=5000, output_dim=64),
  tf.keras.layers.SimpleRNN(128, return_sequences=True),
  tf.keras.layers.Dense(5000, activation='softmax')
])

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

# Training data: input sequences of shape (batch_size, seq_length)
# Labels: next word indices of shape (batch_size, seq_length)

model.fit(train_data, train_labels, epochs=5)

medium

A. Loss function sparse_categorical_crossentropy is incorrect for this task

B. Using return_sequences=True but labels shape is (batch_size, seq_length) which is correct

C. Labels shape should be (batch_size,) not (batch_size, seq_length)

D. Embedding layer input_dim is too small

Solution

1. Step 1: Check RNN output and labels shape

   return_sequences=True outputs sequences matching label shape (batch_size, seq_length).

2. Step 2: Verify loss function suitability

   sparse_categorical_crossentropy is correct for integer labels in classification.

3. Final Answer:

   Using return_sequences=True but labels shape is (batch_size, seq_length) which is correct -> Option B

4. Quick Check:

   return_sequences=True matches label shape = A [OK]

Hint: return_sequences=True means labels must be sequences too [OK]

Common Mistakes:

• Assuming labels must be 1D when output is sequence
• Choosing wrong loss function for integer labels
• Changing embedding input_dim unnecessarily

5. You want to generate text using a trained RNN model. Which approach correctly generates new text step-by-step?

hard

A. Feed initial seed text, predict next word, append it, then feed updated text repeatedly

B. Feed entire training dataset at once to get all predictions

C. Use the model to predict all words in one call without updating input

D. Randomly select words without using the model predictions

Solution

1. Step 1: Understand text generation process

   Text generation uses seed text and predicts one word at a time.

2. Step 2: Describe iterative prediction

   After predicting a word, append it to input and predict next word repeatedly.

3. Final Answer:

   Feed initial seed text, predict next word, append it, then feed updated text repeatedly -> Option A

4. Quick Check:

   Stepwise prediction with updated input = D [OK]

Hint: Generate text word-by-word, updating input each time [OK]

Common Mistakes:

• Trying to predict all words at once without feedback
• Ignoring seed text and using random words
• Feeding entire dataset instead of seed for generation