Architecture search concepts in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to define a simple convolutional layer in a neural network.

Computer Vision

conv_layer = Conv2D(filters=32, kernel_size=3, activation=[1])

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

A'softmax'

B'sigmoid'

C'relu'

D'linear'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'softmax' in a convolutional layer activation instead of ReLU.

Forgetting to add an activation function.

The ReLU activation function is commonly used in convolutional layers to introduce non-linearity and help the model learn complex patterns.

2fill in blank

medium

Complete the code to add a pooling layer after a convolutional layer.

Computer Vision

pool_layer = MaxPooling2D(pool_size=[1])

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

A(3, 3)

B(2, 2)

C(1, 1)

D(4, 4)

Attempts:

3 left

💡 Hint

Common Mistakes

Using a pool size of (1, 1) which does not reduce dimensions.

Choosing too large pool sizes that overly reduce feature maps.

A pool size of (2, 2) is commonly used to reduce the spatial dimensions by half, helping to reduce computation and control overfitting.

3fill in blank

hard

Fix the error in the code to correctly compile a model with categorical crossentropy loss.

Computer Vision

model.compile(optimizer='adam', loss=[1], metrics=['accuracy'])

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

A'categorical_crossentropy'

B'hinge'

C'binary_crossentropy'

D'mean_squared_error'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'binary_crossentropy' for multi-class problems.

Using regression loss functions like 'mean_squared_error' incorrectly.

For multi-class classification problems, 'categorical_crossentropy' is the correct loss function to use.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps layer names to their output shapes if the output has more than 2 dimensions.

Computer Vision

layer_shapes = {layer.name: layer.output_shape for layer in model.layers if [1] > [2]

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

Alen(layer.output_shape)

B2

Clayer.name

Dlayer.output_shape

Attempts:

3 left

💡 Hint

Common Mistakes

Comparing layer.name to a number.

Using layer.output_shape directly in comparison without len().

We use len(layer.output_shape) to get the number of dimensions and filter layers with output shapes having more than 2 dimensions.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps layer names to the number of parameters if the layer has more than 1000 parameters.

Computer Vision

param_counts = {layer.[1]: layer.[2] for layer in model.layers if layer.[3] > 1000}

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

Aname

Bcount_params()

Doutput_shape

Attempts:

3 left

💡 Hint

Common Mistakes

Using layer.output_shape instead of count_params().

Not calling count_params() as a method.

We access layer.name for the key, use layer.count_params() to get the number of parameters for the value and filter layers with more than 1000 parameters.