Prediction and evaluation in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of model prediction shape

Given a TensorFlow model trained on images of shape (28, 28, 1), what is the shape of the output predictions for a batch of 10 images?

TensorFlow

import tensorflow as tf
import numpy as np

model = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
    tf.keras.layers.Dense(10, activation='softmax')
])

batch = np.random.rand(10, 28, 28, 1).astype(np.float32)
predictions = model(batch)
print(predictions.shape)

A (1, 10)

B (28, 28, 10)

C (10, 10)

D (10, 28, 28)

💡 Hint

The model outputs one prediction vector per input image.

The model outputs a vector of length 10 (number of classes) for each of the 10 input images, so the output shape is (10, 10).

❓ Metrics

intermediate

Correct metric for binary classification

Which TensorFlow metric is most appropriate to evaluate a binary classification model's accuracy during training?

A tf.keras.metrics.MeanSquaredError()

B tf.keras.metrics.CategoricalAccuracy()

C tf.keras.metrics.TopKCategoricalAccuracy(k=3)

D tf.keras.metrics.BinaryAccuracy()

💡 Hint

Binary classification means two classes only.

BinaryAccuracy is designed to measure accuracy for two-class problems, while CategoricalAccuracy is for multi-class classification.

❓ Model Choice

advanced

Best model output layer for multi-class classification

You want to build a TensorFlow model to classify images into 5 categories. Which output layer configuration is best?

A Dense(5, activation='softmax')

B Dense(1, activation='sigmoid')

C Dense(5, activation='sigmoid')

D Dense(1, activation='softmax')

💡 Hint

Softmax outputs probabilities for multiple classes.

For multi-class classification, a Dense layer with units equal to number of classes and softmax activation is standard.

🔧 Debug

advanced

Identify the error in evaluation code

What error will this TensorFlow code raise when evaluating a model on test data?

TensorFlow

loss, accuracy = model.evaluate(x_test, y_test)
print(f"Loss: {loss}, Accuracy: {accuracy}")

A No error, prints loss and accuracy correctly

B ValueError because y_test shape does not match model output

C TypeError because model.evaluate returns a dictionary, not tuple

D NameError because model is not defined

💡 Hint

Assume model and data are correctly defined and compatible.

model.evaluate returns loss and metrics as a tuple, so unpacking into loss and accuracy works if accuracy metric was compiled.

🧠 Conceptual

expert

Effect of batch size on evaluation metrics

How does changing the batch size during model evaluation affect the reported accuracy and loss metrics in TensorFlow?

A Smaller batch sizes always produce higher accuracy values

B Batch size does not affect final accuracy or loss values, only evaluation speed

C Larger batch sizes cause the model to overfit during evaluation

D Changing batch size changes the model weights and thus metrics

💡 Hint

Evaluation does not update model weights.

Evaluation metrics are computed over the whole dataset and are independent of batch size; batch size only affects computation speed and memory use.

Practice

1. What does the model.predict() function do in TensorFlow?

easy

A. It saves the model to a file

B. It trains the model on the data

C. It deletes the model from memory

D. It gives the model's guesses on new data

Solution

1. Step 1: Understand the purpose of model.predict()

   This function is used to get the model's output predictions for new input data after training.

2. Step 2: Differentiate from other functions

   Training uses model.fit(), saving uses model.save(), and deleting is manual memory management, none of which are predict().

3. Final Answer:

   It gives the model's guesses on new data -> Option D

4. Quick Check:

   model.predict() = model guesses [OK]

Hint: Predict means guess output for new inputs [OK]

Common Mistakes:

• Confusing predict() with fit() for training
• Thinking predict() saves the model
• Assuming predict() deletes the model

2. Which of the following is the correct way to evaluate a TensorFlow model on test data stored in X_test and y_test?

easy

A. model.score(X_test, y_test)

B. model.evaluate(X_test, y_test)

C. model.fit(X_test, y_test)

D. model.predict(X_test, y_test)

Solution

1. Step 1: Identify the evaluation function

   TensorFlow uses model.evaluate() to measure performance on test data.

2. Step 2: Check other options

   model.predict() makes predictions, model.fit() trains, and model.score() is not a TensorFlow method.

3. Final Answer:

   model.evaluate(X_test, y_test) -> Option B

4. Quick Check:

   Evaluate = measure performance [OK]

Hint: Use evaluate() to check model accuracy on test data [OK]

Common Mistakes:

• Using predict() instead of evaluate() for metrics
• Trying to train with evaluate()
• Using non-existent model.score() method

3. What will be the output of the following code snippet?

import tensorflow as tf
import numpy as np

model = tf.keras.Sequential([
  tf.keras.layers.Dense(1, input_shape=(1,))
])
model.compile(optimizer='sgd', loss='mse')

X = np.array([1, 2, 3, 4], dtype=float)
y = np.array([2, 4, 6, 8], dtype=float)

model.fit(X, y, epochs=10, verbose=0)
predictions = model.predict(np.array([5.0]))
print(predictions)

medium

A. A numpy array close to [[1.0]]

B. A numpy array close to [[5.0]]

C. A numpy array close to [[10.0]]

D. An error because input shape is wrong

Solution

1. Step 1: Understand the model and data

   The model is a simple linear layer trained to learn y = 2*x approximately.

2. Step 2: Predict for input 5.0

   After training, the model should predict close to 2*5 = 10, so output is near [[10.0]].

3. Final Answer:

   A numpy array close to [[10.0]] -> Option C

4. Quick Check:

   Prediction for 5 ≈ 10 [OK]

Hint: Model learns y=2x, predict(5) ≈ 10 [OK]

Common Mistakes:

• Expecting exact 10 instead of approximate
• Confusing input shape causing error
• Thinking prediction returns scalar, not array

4. You run model.evaluate(X_test, y_test) but get a ValueError about mismatched shapes. What is the most likely cause?

medium

A. The shapes of X_test and y_test do not match the model's expected input and output shapes

B. The model was not compiled before evaluation

C. The model.predict() function was called instead of evaluate()

D. The optimizer was set incorrectly

Solution

1. Step 1: Understand the error cause

   A ValueError about shape mismatch usually means input or output data shapes don't match what the model expects.

2. Step 2: Check other options

   Not compiling causes different errors, predict() vs evaluate() is unrelated, and optimizer issues cause training errors, not shape errors.

3. Final Answer:

   The shapes of X_test and y_test do not match the model's expected input and output shapes -> Option A

4. Quick Check:

   Shape mismatch causes ValueError in evaluate() [OK]

Hint: Check input/output shapes match model before evaluate() [OK]

Common Mistakes:

• Ignoring shape mismatch and blaming optimizer
• Confusing predict() with evaluate() errors
• Not compiling model but blaming shape error

5. You trained a model and want to compare its performance on two test sets: X_test1, y_test1 and X_test2, y_test2. Which approach correctly compares their accuracy using TensorFlow?

hard

A. Use model.evaluate() on both test sets separately and compare the returned loss or accuracy values

B. Use model.predict() on both test sets and compare the raw predictions directly

C. Train the model again on X_test2, y_test2 and compare training losses

D. Use model.fit() on both test sets and compare the final epoch losses

Solution

1. Step 1: Understand evaluation for performance

   model.evaluate() returns loss and metrics on test data without training, ideal for comparing performance.

2. Step 2: Why other options are incorrect

   Comparing raw predictions is not a direct accuracy measure; retraining or fitting on test sets changes the model and is not a fair comparison.

3. Final Answer:

   Use model.evaluate() on both test sets separately and compare the returned loss or accuracy values -> Option A

4. Quick Check:

   Evaluate test sets separately for fair comparison [OK]

Hint: Evaluate test sets separately, compare metrics [OK]

Common Mistakes:

• Comparing raw predictions without metrics
• Retraining on test data for comparison
• Using fit() on test data instead of evaluate()