Text generation with RNN in TensorFlow - Model Pipeline Trace

Model Pipeline - Text generation with RNN

This pipeline trains a Recurrent Neural Network (RNN) to learn patterns in text and generate new text one character at a time. It starts with raw text data, processes it into sequences, trains the RNN to predict the next character, and then uses the trained model to create new text.

Data Flow - 5 Stages

1Raw Text Input

1 string (e.g., 198 characters)→Load raw text data as a single string→1 string (198 characters)

"hello world this is a sample text for training"

↓

2Text Vectorization

1 string (198 characters)→Convert characters to integer indices→198 integers (1D array)

[7, 4, 11, 11, 14, 26, 22, 14, 17, 11, 3, ...]

↓

3Create Sequences

198 integers→Split into overlapping sequences of length 100→99 sequences x 100 integers each

[[7,4,11,..., 14], [4,11,11,..., 22], ...]

↓

4Train/Test Split

99 sequences x 100 integers→Split sequences into training (80) and validation (19)→80 train sequences, 19 validation sequences

Train: first 80 sequences, Validation: last 19 sequences

↓

5Model Training

80 sequences x 100 integers→Train RNN to predict next character for each sequence→Trained RNN model

Model learns to predict next char given previous 100 chars

Training Trace - Epoch by Epoch

Loss
2.3 |************
2.1 |**********
1.8 |********
1.6 |******
1.4 |*****
1.2 |****
1.0 |***
    +----------------
     1  3  5  7  10 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.30	0.25	Model starts with high loss and low accuracy
2	2.10	0.32	Loss decreases, accuracy improves slightly
3	1.85	0.40	Model begins to learn character patterns
4	1.60	0.48	Loss continues to decrease steadily
5	1.40	0.55	Model shows clear improvement in prediction
6	1.25	0.60	Training converges with better accuracy
7	1.15	0.63	Loss decreases slower, accuracy plateaus
8	1.10	0.65	Model fine-tunes predictions
9	1.05	0.67	Small improvements continue
10	1.00	0.68	Training stabilizes with good accuracy

Prediction Trace - 5 Layers

Layer 1: Input Layer

Layer 2: Embedding Layer

Layer 3: RNN Layer (LSTM)

Layer 4: Dense Layer with Softmax

Layer 5: Prediction Sampling

Model Quiz - 3 Questions

What does the RNN model learn during training?

A How to cluster data points without labels

B Patterns of characters to predict the next character

C How to classify images into categories

D How to reduce the size of input data

Key Insight

This visualization shows how an RNN learns to generate text by predicting the next character based on previous ones. The training process reduces loss and improves accuracy, enabling the model to produce coherent text sequences.

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