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.