Error analysis patterns in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Identifying common causes of high training loss

Which of the following is least likely to cause a persistently high training loss in a TensorFlow model?

A Having a dataset with mislabeled examples in the training set

B Evaluating the model on the training data instead of validation data

C Using a model architecture that is too simple to capture the data patterns

D Using a learning rate that is too high, causing the model to overshoot minima

💡 Hint

Think about what affects training loss versus evaluation procedure.

Evaluating on training data does not cause high training loss; it just measures it. The other options directly cause the model to perform poorly during training.

❓ Predict Output

intermediate

Output of TensorFlow model predictions with incorrect input shape

What error will this TensorFlow code produce when running predictions?

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Dense(5, activation='relu', input_shape=(3,))
])
model.compile(optimizer='adam', loss='mse')

import numpy as np
input_data = np.array([[1, 2]])  # Shape (1, 2), should be (1, 3)
predictions = model.predict(input_data)

A ValueError: Input 0 of layer sequential is incompatible with the layer: expected shape=(None, 3), found shape=(None, 2)

B TypeError: Unsupported operand type(s) for +: 'int' and 'str'

C No error, predictions will run and output shape (1, 5)

D RuntimeError: Model has not been compiled yet

💡 Hint

Check if the input shape matches the model's expected input shape.

The model expects input shape (None, 3) but receives (None, 2), causing a ValueError about incompatible input shape.

❓ Model Choice

advanced

Choosing a model to reduce overfitting detected in error analysis

You notice your TensorFlow model performs very well on training data but poorly on validation data. Which model change is most likely to reduce overfitting?

A Increase the number of layers and neurons to improve model capacity

B Remove batch normalization layers to simplify the model

C Add dropout layers to randomly disable neurons during training

D Use a smaller batch size during training

💡 Hint

Think about regularization techniques that prevent overfitting.

Dropout is a regularization method that helps reduce overfitting by randomly disabling neurons during training, forcing the model to generalize better.

❓ Metrics

advanced

Interpreting confusion matrix metrics for imbalanced data

Given a binary classification confusion matrix:

[[90, 10],
 [40, 60]]

Where rows are true classes and columns are predicted classes, what is the precision for the positive class?

A 0.857

B 0.4

C 0.6

D 0.75

💡 Hint

Precision = True Positives / (True Positives + False Positives)

True Positives = 60, False Positives = 10, so precision = 60 / (60 + 10) ≈ 0.857.

🔧 Debug

expert

Debugging exploding gradients in TensorFlow training

During training a deep neural network in TensorFlow, the loss suddenly becomes NaN after several epochs. Which debugging step is most effective to identify and fix exploding gradients?

A Increase the learning rate to speed up convergence

B Switch optimizer from Adam to SGD without momentum

C Remove dropout layers to stabilize training

D Add gradient clipping to limit the gradient values during backpropagation

💡 Hint

Exploding gradients cause very large updates; controlling gradient size helps.

Gradient clipping limits the size of gradients during backpropagation, preventing them from becoming too large and causing NaN loss.

Practice

1. What is the main purpose of error analysis in TensorFlow models?

easy

A. To find where and why the model makes mistakes

B. To increase the size of the training dataset

C. To speed up model training

D. To reduce the number of layers in the model

Solution

1. Step 1: Understand error analysis purpose

   Error analysis focuses on identifying mistakes made by the model during prediction.

2. Step 2: Compare options with purpose

   Only To find where and why the model makes mistakes correctly states that error analysis finds where and why the model makes mistakes.

3. Final Answer:

   To find where and why the model makes mistakes -> Option A

4. Quick Check:

   Error analysis = find model mistakes [OK]

Hint: Error analysis = find and understand model mistakes [OK]

Common Mistakes:

• Confusing error analysis with data augmentation
• Thinking error analysis speeds up training
• Believing error analysis changes model architecture

2. Which TensorFlow function is commonly used to compare model predictions with true labels during error analysis?

easy

A. tf.argmax()

B. tf.equal()

C. tf.reshape()

D. tf.reduce_sum()

Solution

1. Step 1: Identify function for comparing predictions and labels

   tf.equal() compares two tensors element-wise and returns True where they match.

2. Step 2: Check other options

   tf.argmax() finds index of max value, tf.reshape() changes shape, tf.reduce_sum() sums values; none compare predictions to labels.

3. Final Answer:

   tf.equal() -> Option B

4. Quick Check:

   Compare predictions and labels = tf.equal() [OK]

Hint: Use tf.equal() to check prediction correctness [OK]

Common Mistakes:

• Using tf.argmax() to compare directly
• Confusing reshape with comparison
• Summing values instead of comparing

3. Given the following TensorFlow code snippet, what will be the output?

predictions = tf.constant([1, 0, 1, 1])
labels = tf.constant([1, 1, 0, 1])
errors = tf.not_equal(predictions, labels)
print(tf.reduce_sum(tf.cast(errors, tf.int32)).numpy())

medium

A. 4

B. 1

C. 3

D. 2

Solution

1. Step 1: Compare predictions and labels element-wise

   predictions = [1,0,1,1], labels = [1,1,0,1]. Differences at index 1 (0 vs 1) and index 2 (1 vs 0).

2. Step 2: Count number of errors

   tf.not_equal returns True for mismatches. There are 2 mismatches, so sum is 2.

3. Final Answer:

   2 -> Option D

4. Quick Check:

   Count mismatches = 2 [OK]

Hint: Count mismatches with tf.not_equal and sum [OK]

Common Mistakes:

• Counting matches instead of mismatches
• Confusing tf.equal with tf.not_equal
• Forgetting to cast booleans to int before summing

4. You run this TensorFlow code to find errors but get a TypeError:

errors = tf.not_equal(predictions, labels)
error_count = tf.reduce_sum(errors).numpy()

What is the likely cause and fix?

medium

A. predictions and labels have different shapes

B. tf.reduce_sum() requires a Python list input

C. errors is boolean; cast to int before summing

D. numpy() cannot be called on TensorFlow tensors

Solution

1. Step 1: Identify error cause

   tf.not_equal returns a boolean tensor. tf.reduce_sum on booleans causes TypeError without casting.

2. Step 2: Fix by casting booleans to int

   Use tf.cast(errors, tf.int32) before tf.reduce_sum to count True values correctly.

3. Final Answer:

   errors is boolean; cast to int before summing -> Option C

4. Quick Check:

   Cast booleans to int before sum [OK]

Hint: Cast booleans to int before summing [OK]

Common Mistakes:

• Ignoring data type of errors tensor
• Assuming reduce_sum works on booleans directly
• Misunderstanding numpy() usage

5. You want to perform error analysis by grouping model errors by class label in TensorFlow. Which approach best helps identify which classes have the most errors?

hard

A. Use tf.boolean_mask to select errors per class, then count errors per class

B. Shuffle the dataset randomly before error analysis

C. Increase batch size during model training

D. Use tf.argmax on predictions without comparing to labels

Solution

1. Step 1: Understand grouping errors by class

   To find errors per class, select errors where label equals that class using tf.boolean_mask.

2. Step 2: Count errors per class

   Counting errors per class after masking helps identify classes with most mistakes.

3. Final Answer:

   Use tf.boolean_mask to select errors per class, then count errors per class -> Option A

4. Quick Check:

   Group errors by class using boolean mask [OK]

Hint: Mask errors by class label to count per class [OK]

Common Mistakes:

• Shuffling data does not group errors
• Batch size affects training, not error grouping
• Using tf.argmax alone ignores true labels