Flatten and Dense layers in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to add a Flatten layer to the model.

TensorFlow

model = tf.keras.Sequential([
    [1](input_shape=(28, 28, 1))
])

Drag options to blanks, or click blank then click option'

AFlatten

BDense

CConv2D

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense layer directly without flattening causes shape errors.

Using Conv2D layer without specifying filters and kernel size.

The Flatten layer converts the 2D image input into a 1D vector, which is needed before feeding into Dense layers.

2fill in blank

medium

Complete the code to add a Dense layer with 128 units and ReLU activation.

TensorFlow

model.add([1](128, activation='relu'))

Drag options to blanks, or click blank then click option'

AFlatten

BMaxPooling2D

CConv2D

DDense

Attempts:

3 left

💡 Hint

Common Mistakes

Using Flatten instead of Dense for fully connected layers.

Forgetting to specify activation function.

The Dense layer creates a fully connected layer with 128 neurons and ReLU activation.

3fill in blank

hard

Fix the error in the code to correctly add a Dense output layer with 10 units and softmax activation.

TensorFlow

model.add(Dense([1], activation='softmax'))

Drag options to blanks, or click blank then click option'

A1

B10

CNone

D'10'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing number of units as a string causes errors.

Using 1 unit instead of 10 for multi-class classification.

The output layer should have 10 units (one per class) as an integer, not a string or other value.

4fill in blank

hard

Fill both blanks to create a model with a Flatten layer followed by a Dense layer with 64 units.

TensorFlow

model = tf.keras.Sequential([
    [1](input_shape=(32, 32, 3)),
    [2](64, activation='relu')
])

Drag options to blanks, or click blank then click option'

AFlatten

BDense

CConv2D

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2D instead of Flatten for first layer.

Missing activation in Dense layer.

The Flatten layer converts the input to 1D, then the Dense layer creates 64 neurons with ReLU activation.

5fill in blank

hard

Fill all three blanks to build a model with Flatten, Dense 128 ReLU, and Dense 10 softmax layers.

TensorFlow

model = tf.keras.Sequential([
    [1](input_shape=(28, 28, 1)),
    [2](128, activation='relu'),
    [3](10, activation='softmax')
])

Drag options to blanks, or click blank then click option'

AFlatten

BDense

CConv2D

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2D instead of Flatten for input layer.

Using Dropout instead of Dense for hidden layers.

Wrong number of units in output layer.

The model first flattens input, then adds a Dense layer with 128 units and ReLU, and finally a Dense output layer with 10 units and softmax.