Why architecture design impacts performance in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

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

Computer Vision

conv_layer = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=[1])

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

A1

B5

C7

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing kernel size 1 which is too small to capture features.

Using kernel size 7 which may be too large for simple tasks.

The kernel size defines the size of the filter that slides over the image. A kernel size of 5 is commonly used to capture features effectively.

2fill in blank

medium

Complete the code to add a ReLU activation after a convolutional layer.

Computer Vision

model = nn.Sequential(
    nn.Conv2d(3, 16, 5),
    [1]()
)

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

ASoftmax

BSigmoid

CReLU

DTanh

Attempts:

3 left

💡 Hint

Common Mistakes

Using Sigmoid which can cause vanishing gradients.

Using Softmax which is for output layers in classification.

ReLU is a common activation function that helps the model learn non-linear features effectively.

3fill in blank

hard

Fix the error in the code to correctly flatten the output before a fully connected layer.

Computer Vision

x = x.view(x.size(0), [1])

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

A-1

B1

C0

Dx.size(1)

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1 or 0 which causes shape mismatch errors.

Using x.size(1) which only flattens one dimension.

Using -1 lets PyTorch automatically calculate the correct size for flattening all dimensions except the batch size.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps layer names to their output sizes if size is greater than 100.

Computer Vision

layer_sizes = {name: size for name, size in layers.items() if size [1] 100 and 'conv' [2] name}

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

A>

B<

Cin

Dnot in

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' which selects smaller sizes.

Using 'not in' which excludes 'conv' layers.

The comprehension filters layers with size greater than 100 and names containing 'conv'.

5fill in blank

hard

Fill all three blanks to create a dictionary of layer outputs where output size is less than 50 and layer name contains 'pool'.

Computer Vision

filtered_outputs = { [1]: [2] for [3] in outputs.items() if [2] < 50 and 'pool' in [1] }

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

Aname

Boutput

Cname, output

Dlayer

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'layer' which is undefined.

Mixing variable names inconsistently.

The comprehension iterates over (name, output) pairs, filters outputs less than 50, and checks if 'pool' is in the layer name.