Sequence padding in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output shape after padding?

Given the following code that pads sequences, what will be the shape of the padded sequences?

TensorFlow

import tensorflow as tf
sequences = [[1, 2, 3], [4, 5], [6]]
padded = tf.keras.preprocessing.sequence.pad_sequences(sequences, maxlen=4, padding='post')
print(padded.shape)

A (3, 3)

B (4, 3)

C (3, 4)

D (4, 4)

💡 Hint

Remember that padding adds elements to each sequence to reach maxlen.

The input has 3 sequences, and maxlen=4 means each sequence is padded to length 4, so shape is (3,4).

❓ Model Choice

intermediate

Choosing padding for RNN input

You want to feed variable-length sequences into an RNN model in TensorFlow. Which padding option is best to keep the original sequence order intact?

A No padding, truncate all sequences to the shortest length

B padding='post' to add zeros at the end

C padding='middle' to add zeros in the middle

D padding='pre' to add zeros at the start

💡 Hint

RNNs process sequences in order; padding at the end preserves the start.

Padding at the end ('post') keeps the original sequence order at the start, which is important for RNNs to learn meaningful patterns.

❓ Hyperparameter

advanced

Effect of maxlen in sequence padding

What happens if you set maxlen smaller than the longest sequence when using tf.keras.preprocessing.sequence.pad_sequences?

A Sequences longer than maxlen are truncated to maxlen

B Sequences longer than maxlen cause an error

C Sequences shorter than maxlen are truncated

D Sequences are padded to the length of the longest sequence ignoring maxlen

💡 Hint

maxlen controls the final length after padding or truncation.

If maxlen is smaller than some sequences, those sequences are truncated to maxlen length.

🔧 Debug

advanced

Why does this padding code raise an error?

Consider this code snippet: import tensorflow as tf sequences = [[1, 2], [3, 4, 5]] padded = tf.keras.preprocessing.sequence.pad_sequences(sequences, padding='sideways') What error will this code raise?

A TypeError: sequences must be a numpy array

B No error, code runs successfully

C IndexError: list index out of range

D ValueError: Unknown padding type: sideways

💡 Hint

Check the allowed values for the padding parameter.

The padding parameter only accepts 'pre' or 'post'. 'sideways' is invalid and causes a ValueError.

🧠 Conceptual

expert

Why use masking with padded sequences?

When feeding padded sequences into a neural network, why is it important to use masking layers or techniques?

A To ignore padded zeros so the model does not treat them as real data

B To convert padded zeros into random noise for regularization

C To speed up training by removing padded sequences entirely

D To automatically increase the sequence length during training

💡 Hint

Padded zeros are not real data and can confuse the model if not masked.

Masking tells the model which parts of the input are padding so it can ignore them during training and prediction.

Practice

1. What is the main purpose of sequence padding in TensorFlow?

easy

A. To make all sequences the same length by adding zeros

B. To shuffle the sequences randomly

C. To normalize the values in sequences

D. To remove zeros from sequences

Solution

1. Step 1: Understand sequence length requirements

   Models need inputs of the same length to process batches efficiently.

2. Step 2: Role of padding

   Padding adds zeros to shorter sequences to match the longest sequence length.

3. Final Answer:

   To make all sequences the same length by adding zeros -> Option A

4. Quick Check:

   Sequence padding = same length sequences [OK]

Hint: Padding adds zeros to equalize sequence lengths [OK]

Common Mistakes:

• Thinking padding shuffles sequences
• Confusing padding with normalization
• Assuming padding removes zeros

2. Which of the following is the correct way to pad sequences using TensorFlow's tf.keras.preprocessing.sequence.pad_sequences function?

easy

A. pad_sequences(sequences, maxlen=5, padding='post')

B. pad_sequences(sequences, maxlen=5, pad='after')

C. pad_sequences(sequences, length=5, padding='pre')

D. pad_sequences(sequences, max_length=5, padding='middle')

Solution

1. Step 1: Check function parameters

   The correct parameter for length is maxlen, and padding accepts 'pre' or 'post'.

2. Step 2: Validate option syntax

   pad_sequences(sequences, maxlen=5, padding='post') uses maxlen=5 and padding='post', which is correct syntax.

3. Final Answer:

   pad_sequences(sequences, maxlen=5, padding='post') -> Option A

4. Quick Check:

   Correct param names = pad_sequences(sequences, maxlen=5, padding='post') [OK]

Hint: Use maxlen and padding='pre' or 'post' in pad_sequences [OK]

Common Mistakes:

• Using wrong parameter names like pad or length
• Using invalid padding values like 'middle'
• Confusing maxlen with max_length

3. What will be the output of this code?

import tensorflow as tf
sequences = [[1, 2, 3], [4, 5], [6]]
padded = tf.keras.preprocessing.sequence.pad_sequences(sequences, maxlen=4, padding='pre')
print(padded.tolist())

medium

A. [[1, 2, 3], [4, 5], [6]]

B. [[0, 1, 2, 3], [0, 0, 4, 5], [0, 0, 0, 6]]

C. [[1, 2, 3, 0], [4, 5, 0, 0], [6, 0, 0, 0]]

D. [[0, 0, 1, 2], [0, 4, 5, 0], [6, 0, 0, 0]]

Solution

1. Step 1: Understand padding='pre'

   Padding adds zeros before the sequence to reach maxlen=4.

2. Step 2: Apply padding to each sequence

   First: [1,2,3] -> [0,1,2,3]; Second: [4,5] -> [0,0,4,5]; Third: [6] -> [0,0,0,6]

3. Final Answer:

   [[0, 1, 2, 3], [0, 0, 4, 5], [0, 0, 0, 6]] -> Option B

4. Quick Check:

   Pre-padding adds zeros before sequences [OK]

Hint: Pre-padding adds zeros at the start of sequences [OK]

Common Mistakes:

• Confusing pre-padding with post-padding
• Expecting original sequences without padding
• Miscounting zeros added

4. This code throws an error. What is the mistake?

import tensorflow as tf
sequences = [[1, 2], [3, 4, 5]]
padded = tf.keras.preprocessing.sequence.pad_sequences(sequences, maxlen=3, padding='middle')
print(padded)

medium

A. Sequences must be numpy arrays, not lists

B. maxlen should be larger than longest sequence

C. Invalid padding value 'middle' used

D. Missing argument 'value' for padding

Solution

1. Step 1: Check padding parameter values

   Valid padding values are 'pre' or 'post'. 'middle' is invalid.

2. Step 2: Identify error cause

   Using 'middle' causes a ValueError because it's not supported.

3. Final Answer:

   Invalid padding value 'middle' used -> Option C

4. Quick Check:

   Padding must be 'pre' or 'post' [OK]

Hint: Use only 'pre' or 'post' for padding parameter [OK]

Common Mistakes:

• Using unsupported padding values
• Thinking maxlen must be bigger than longest sequence
• Assuming lists cause errors

5. You have sequences of different lengths and want to pad them so that all sequences have length 6. You want zeros added after the sequences. Which code correctly achieves this and why?

hard

A. pad_sequences(sequences, maxlen=6, value=1) because it pads with ones to length 6

B. pad_sequences(sequences, maxlen=6, padding='pre') because it pads zeros before sequences to length 6

C. pad_sequences(sequences, maxlen=6, truncating='post') because it truncates sequences after length 6

D. pad_sequences(sequences, maxlen=6, padding='post') because it pads zeros after sequences to length 6

Solution

1. Step 1: Understand padding='post'

   Padding='post' adds zeros after the sequence to reach maxlen.

2. Step 2: Check other options

   pad_sequences(sequences, maxlen=6, padding='pre') because it pads zeros before sequences to length 6 pads before sequences, not after. pad_sequences(sequences, maxlen=6, truncating='post') because it truncates sequences after length 6 truncates sequences, not pads. pad_sequences(sequences, maxlen=6, value=1) because it pads with ones to length 6 pads with ones, not zeros.

3. Final Answer:

   pad_sequences(sequences, maxlen=6, padding='post') -> Option D

4. Quick Check:

   Post-padding adds zeros after sequences [OK]

Hint: Use padding='post' to add zeros after sequences [OK]

Common Mistakes:

• Confusing pre and post padding
• Using truncating instead of padding
• Changing pad value from zero unintentionally