Keras as TensorFlow's high-level API - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the correct Keras model for image classification

You want to build a simple image classifier using Keras in TensorFlow. Which model type is best suited for this task?

A Sequential model with Conv2D and Dense layers

B Functional API model with only Dense layers

C Sequential model with only LSTM layers

D Functional API model with Embedding layers only

💡 Hint

Think about the type of data images are and which layers process spatial information.

Images have spatial structure best captured by convolutional layers (Conv2D). A Sequential model with Conv2D and Dense layers is a simple and effective choice for image classification.

❓ Predict Output

intermediate

Output shape of a Keras Conv2D layer

What is the output shape of this Keras layer when input shape is (32, 32, 3)?

TensorFlow

from tensorflow.keras.layers import Conv2D
layer = Conv2D(filters=16, kernel_size=3, strides=1, padding='valid')
output_shape = layer.compute_output_shape((None, 32, 32, 3))
print(output_shape)

A (None, 32, 32, 16)

B (None, 31, 31, 16)

C (None, 30, 30, 16)

D (None, 30, 30, 3)

💡 Hint

Padding='valid' means no padding, so output size shrinks by kernel_size - 1.

With kernel size 3 and valid padding, output height and width = input - 3 + 1 = 30. Filters define output channels = 16.

❓ Hyperparameter

advanced

Choosing the right optimizer for faster convergence

You train a Keras model but it learns very slowly. Which optimizer change is most likely to speed up training without losing stability?

A Switch from Adam to SGD optimizer

B Switch from SGD to Adam optimizer

C Switch from RMSprop to SGD optimizer with momentum=0

D Switch from Adam to RMSprop with learning rate 10 times smaller

💡 Hint

Adam adapts learning rates per parameter and often converges faster than vanilla SGD.

Adam optimizer combines momentum and adaptive learning rates, usually speeding up convergence compared to SGD.

❓ Metrics

advanced

Interpreting Keras model accuracy during training

After training a Keras classification model, the training accuracy is 95% but validation accuracy is 70%. What does this indicate?

A The model is overfitting the training data

B The model is underfitting the training data

C The model has perfect generalization

D The validation data is corrupted

💡 Hint

High training accuracy but much lower validation accuracy usually means the model memorizes training data.

Overfitting happens when the model learns training data too well but fails to generalize to new data, causing lower validation accuracy.

🔧 Debug

expert

Identifying the cause of a Keras model training error

You run this Keras code and get a ValueError: 'Input 0 of layer dense_1 is incompatible with the layer: expected axis -1 of input shape to have value 64 but received input with shape (None, 32)'. What is the most likely cause?

TensorFlow

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
model = Sequential([
  Flatten(input_shape=(8,8)),
  Dense(64, activation='relu'),
  Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.fit(x_train, y_train, epochs=5)

A The input_shape in Flatten is incorrect; it should be (64,) instead of (8,8)

B The Dense layer expects input with last dimension 64, but Flatten outputs (None, 64), so the error is in the Dense layer

C The model is missing an input layer, causing shape mismatch

D The Flatten layer output shape is (None, 64), but Dense expects input with last dimension 64, so input data shape is wrong

💡 Hint

Flatten converts (8,8) to 64 features. The error says input to Dense has shape (None, 32), which is unexpected.

The error means the data fed to the model has shape (None, 8, 4) or similar, not (None, 8, 8). Flatten outputs 64 features, but input data shape is inconsistent.

Practice

1. What is the main purpose of Keras in TensorFlow?

easy

A. To replace TensorFlow's core functionalities

B. To provide a simple way to build and train neural networks

C. To visualize data with charts and graphs

D. To manage databases for machine learning

Solution

1. Step 1: Understand Keras role in TensorFlow

   Keras is designed as a user-friendly API to build and train neural networks easily within TensorFlow.

2. Step 2: Compare options with Keras purpose

   Options B, C, and D describe unrelated tasks. Only To provide a simple way to build and train neural networks correctly states Keras's main purpose.

3. Final Answer:

   To provide a simple way to build and train neural networks -> Option B

4. Quick Check:

   Keras purpose = simple neural network building [OK]

Hint: Keras makes neural networks easy to build and train [OK]

Common Mistakes:

• Thinking Keras replaces TensorFlow core
• Confusing Keras with data visualization tools
• Assuming Keras manages databases

2. Which of the following is the correct way to import Keras from TensorFlow?

easy

A. from tensorflow import keras

B. import tensorflow.keras as tfk

C. import keras

D. from keras import tensorflow

Solution

1. Step 1: Recall the standard import syntax for Keras in TensorFlow

   The recommended way is to import Keras as a module from TensorFlow using 'from tensorflow import keras'.

2. Step 2: Evaluate each option

   import keras imports standalone keras (not recommended). import tensorflow.keras as tfk is valid syntax but aliases it as 'tfk' (keras not directly available). from keras import tensorflow reverses the import incorrectly. Only from tensorflow import keras is correct.

3. Final Answer:

   from tensorflow import keras -> Option A

4. Quick Check:

   Correct import = from tensorflow import keras [OK]

Hint: Use 'from tensorflow import keras' to import Keras [OK]

Common Mistakes:

• Using 'import keras' without tensorflow prefix
• Swapping import order incorrectly
• Trying to alias with invalid syntax

3. What will be the output shape of the model defined below?

from tensorflow import keras
model = keras.Sequential([
    keras.layers.Dense(10, input_shape=(5,)),
    keras.layers.Dense(3)
])
print(model.output_shape)

medium

A. (3, 5)

B. (5, 3)

C. (None, 3)

D. (None, 10)

Solution

1. Step 1: Analyze model layers and input shape

   The first Dense layer outputs 10 units for each input of shape (5,). The second Dense layer outputs 3 units. The batch size is None (unknown).

2. Step 2: Determine final output shape

   The model output shape is (None, 3), where None is batch size and 3 is output units of last layer.

3. Final Answer:

   (None, 3) -> Option C

4. Quick Check:

   Output shape = (None, 3) [OK]

Hint: Output shape matches last layer units with batch size None [OK]

Common Mistakes:

• Confusing input shape with output shape
• Using batch size 5 instead of None
• Mixing layer output units

4. Identify the error in the following Keras model code:

from tensorflow import keras
model = keras.Sequential()
model.add(keras.layers.Dense(10))
model.add(keras.layers.Dense(1))
model.compile(optimizer='adam', loss='mse')
model.summary()
model.fit(x_train, y_train, epochs=5)

medium

A. Missing input shape in first Dense layer

B. Incorrect optimizer name

C. Loss function 'mse' is invalid

D. fit method missing batch_size argument

Solution

1. Step 1: Check model layer definitions

   The first Dense layer lacks an input shape, which is required for the model to know input dimensions.

2. Step 2: Verify compile and fit parameters

   Optimizer 'adam' and loss 'mse' are valid. Batch size is optional in fit. So no error there.

3. Final Answer:

   Missing input shape in first Dense layer -> Option A

4. Quick Check:

   Input shape missing = error [OK]

Hint: Always specify input shape in first layer [OK]

Common Mistakes:

• Assuming batch_size is mandatory in fit
• Thinking 'mse' is invalid loss
• Confusing optimizer names

5. You want to build a Keras model that accepts images of size 28x28 with 1 color channel and outputs 10 class probabilities. Which model definition is correct?

hard

A. model = keras.Sequential([
keras.layers.Flatten(input_shape=(28,28)),
keras.layers.Dense(10)
])

B. model = keras.Sequential([
keras.layers.Dense(128, input_shape=(28,28,1), activation='relu'),
keras.layers.Dense(10, activation='softmax')
])

C. model = keras.Sequential([
keras.layers.Conv2D(32, (3,3), input_shape=(28,28)),
keras.layers.Dense(10, activation='softmax')
])

D. model = keras.Sequential([
keras.layers.Flatten(input_shape=(28,28,1)),
keras.layers.Dense(128, activation='relu'),
keras.layers.Dense(10, activation='softmax')
])

Solution

1. Step 1: Check input shape and layer compatibility

   Images have shape (28,28,1). Flatten layer must match this shape exactly to convert to vector.

2. Step 2: Verify output layer for classification

   Output layer with 10 units and softmax activation correctly outputs class probabilities.

3. Step 3: Evaluate each option

   model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) correctly uses Flatten with input_shape (28,28,1) and final Dense with softmax. model = keras.Sequential([ keras.layers.Dense(128, input_shape=(28,28,1), activation='relu'), keras.layers.Dense(10, activation='softmax') ]) incorrectly uses Dense with 3D input. model = keras.Sequential([ keras.layers.Conv2D(32, (3,3), input_shape=(28,28)), keras.layers.Dense(10, activation='softmax') ]) misses channel dimension and uses Conv2D incorrectly. model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28)), keras.layers.Dense(10) ]) misses channel dimension and lacks activation.

4. Final Answer:

   model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) -> Option D

5. Quick Check:

   Correct input shape and softmax output = model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) [OK]

Hint: Match input shape exactly and use softmax for classes [OK]

Common Mistakes:

• Ignoring channel dimension in input shape
• Using Dense layer directly on 3D input
• Missing softmax activation for classification