Sequence padding in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Sequence padding

Which metric matters for Sequence Padding and WHY

Sequence padding helps models handle inputs of different lengths by making them the same size. The key metrics to check are loss and accuracy during training and validation. These show if the model learns well despite padded data. Also, masking-aware metrics are important to ensure padded parts do not affect results.

Confusion Matrix Example

    Actual \ Predicted | Positive | Negative
    -------------------|----------|---------
    Positive           |    40    |   10    
    Negative           |    5     |   45    
  

This matrix shows how well the model predicts sequences after padding. The padded parts are ignored during evaluation.

Precision vs Recall Tradeoff with Sequence Padding

When padding sequences, the model might learn to ignore padded zeros. If it focuses too much on padded parts, precision or recall can drop.

Example: In speech recognition, padding short audio clips helps batch processing. High precision means the model correctly identifies spoken words without false alarms. High recall means it catches most spoken words. Padding must not confuse the model, or recall might drop.

Good vs Bad Metric Values for Sequence Padding

Good: Loss decreases steadily, accuracy improves, and masking ensures padded parts do not affect results.

Bad: Loss stays high or fluctuates, accuracy is low, or metrics are skewed because padded zeros are treated as real data.

Common Pitfalls with Metrics and Sequence Padding

• Not using masking causes padded zeros to affect loss and accuracy.
• Evaluating metrics on padded sequences without ignoring padding leads to wrong results.
• Overfitting to padded patterns instead of real data.
• Ignoring variable sequence lengths during batching can cause poor model performance.

Self Check

Your model has 98% accuracy but 12% recall on padded sequence data. Is it good?

Answer: No. High accuracy can be misleading if the model ignores rare but important sequences. Low recall means it misses many true cases. You should improve how the model handles padded sequences and check masking.

Key Result

Masking padded parts is key to accurate loss and recall metrics in sequence models.

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