Kernel size, stride, padding in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a 2D convolutional layer with a kernel size of 3.

PyTorch

conv = torch.nn.Conv2d(in_channels=1, out_channels=1, kernel_size=[1])

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

A3

B5

C1

D7

Attempts:

3 left

💡 Hint

Common Mistakes

Using a kernel size too large for the input image.

Confusing kernel size with stride.

The kernel size defines the size of the filter that slides over the input image. Here, 3 means a 3x3 filter.

2fill in blank

medium

Complete the code to set the stride of the convolutional layer to 2.

PyTorch

conv = torch.nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3, stride=[1])

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

A2

B1

C3

D4

Attempts:

3 left

💡 Hint

Common Mistakes

Setting stride to 0 which is invalid.

Confusing stride with padding.

Stride controls how much the filter moves at each step. A stride of 2 means the filter moves 2 pixels at a time.

3fill in blank

hard

Fix the error in the code by choosing the correct padding value to keep output size same as input size with kernel size 3 and stride 1.

PyTorch

conv = torch.nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3, stride=1, padding=[1])

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

A0

B3

C1

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using padding 0 which shrinks output size.

Using padding too large which increases output size.

Padding of 1 adds a border of zeros around the input, keeping output size same when kernel size is 3 and stride is 1.

4fill in blank

hard

Fill both blanks to create a convolutional layer with kernel size 5 and stride 2.

PyTorch

conv = torch.nn.Conv2d(in_channels=3, out_channels=6, kernel_size=[1], stride=[2])

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

A5

B1

C2

D3

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up kernel size and stride values.

Using stride 1 when stride 2 is required.

Kernel size 5 means a 5x5 filter. Stride 2 means the filter moves 2 pixels at a time.

5fill in blank

hard

Fill all three blanks to create a convolutional layer with kernel size 7, stride 1, and padding 3.

PyTorch

conv = torch.nn.Conv2d(in_channels=[1], out_channels=[2], kernel_size=[3], stride=1, padding=3)

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

A3

B6

C7

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong number of input or output channels.

Incorrect kernel size or padding causing size mismatch.

in_channels=3 for RGB images, out_channels=6 for 6 filters, kernel_size=7 for a 7x7 filter, stride=1 and padding=3 to keep output size.

Practice

1. What does the stride parameter control in a convolutional layer in PyTorch?

easy

A. How far the filter moves on the input each step

B. The size of the filter scanning the input

C. The number of filters used in the layer

D. The amount of zero padding added around the input

Solution

1. Step 1: Understand stride in convolution

   Stride defines the step size the filter moves when scanning the input image or feature map.

2. Step 2: Differentiate stride from other parameters

   Kernel size is the filter size, padding adds pixels around input, and number of filters controls output depth.

3. Final Answer:

   How far the filter moves on the input each step -> Option A

4. Quick Check:

   Stride = step size of filter movement [OK]

Hint: Stride = filter step size, not size or padding [OK]

Common Mistakes:

• Confusing stride with kernel size
• Thinking stride controls padding
• Mixing stride with number of filters

2. Which of the following is the correct way to create a 2D convolutional layer in PyTorch with kernel size 3, stride 2, and padding 1?

easy

A. nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1)

B. nn.Conv2d(1, 10, kernel=3, stride=2, pad=1)

C. nn.Conv2d(1, 10, kernel_size=3, stride=1, padding=2)

D. nn.Conv2d(in_channels=1, out_channels=10, kernel_size=2, stride=2, padding=1)

Solution

1. Step 1: Check PyTorch Conv2d parameter names

   Correct parameters are in_channels, out_channels, kernel_size, stride, and padding.

2. Step 2: Match values to question

   Kernel size=3, stride=2, padding=1 matches only nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1) exactly.

3. Final Answer:

   nn.Conv2d(in_channels=1, out_channels=10, kernel_size=3, stride=2, padding=1) -> Option A

4. Quick Check:

   Correct parameter names and values used [OK]

Hint: Use exact PyTorch parameter names: kernel_size, stride, padding [OK]

Common Mistakes:

• Using wrong parameter names like kernel or pad
• Mixing stride and padding values
• Wrong kernel size or stride values

3. Given an input tensor of size (1, 1, 7, 7), a Conv2d layer with kernel_size=3, stride=2, and padding=1 is applied. What is the output spatial size (height and width)?

medium

A. (1, 1, 3, 3)

B. (1, 1, 5, 5)

C. (1, 1, 2, 2)

D. (1, 1, 4, 4)

Solution

1. Step 1: Use output size formula for Conv2d

   Output size = floor((Input + 2*padding - kernel_size)/stride) + 1

2. Step 2: Calculate output height and width

   Input=7, padding=1, kernel=3, stride=2
   Output = floor((7 + 2*1 - 3)/2) + 1 = floor((7 + 2 - 3)/2) + 1 = floor(6/2) + 1 = 3 + 1 = 4

3. Final Answer:

   (1, 1, 4, 4) -> Option D

4. Quick Check:

   Output size formula applied correctly [OK]

Hint: Apply formula: floor((I+2P-K)/S)+1 for each dimension [OK]

Common Mistakes:

• Forgetting to add padding twice
• Using ceil instead of floor
• Mixing stride and kernel size in formula

4. You wrote this PyTorch code but get an error:

nn.Conv2d(1, 10, kernel_size=3, stride=2, padding=0)

on input size (1, 1, 1, 1). What is the likely cause?

medium

A. Kernel size must be even number

B. Padding is too small for the input size causing negative output dimension

C. Stride value must be 1 for kernel size 3

D. Input channels and output channels are swapped

Solution

1. Step 1: Check output size with given parameters

   Output size = floor((1 + 2*0 - 3)/2) + 1 = floor((-2)/2) + 1 = floor(-1) + 1 = -1 + 1 = 0 (invalid)

2. Step 2: Consider if padding causes error

   Padding=0 on small input (1x1) causes the calculated output size to be zero, which PyTorch raises as a runtime error due to insufficient padding for the kernel size.

3. Final Answer:

   Padding is too small for the input size causing negative output dimension -> Option B

4. Quick Check:

   Padding too small -> invalid output size [OK]

Hint: Check if padding is too small for input size [OK]

Common Mistakes:

• Assuming stride must be 1 for kernel 3
• Thinking kernel size must be even
• Swapping input and output channels

5. You want to keep the output size the same as the input size (7x7) after a Conv2d layer with kernel_size=5 and stride=1. What padding value should you use?

hard

A. 1

B. 0

C. 2

D. 3

Solution

1. Step 1: Use formula for output size with stride=1

   Output size = Input size if padding = (kernel_size - 1) / 2

2. Step 2: Calculate padding

   Padding = (5 - 1) / 2 = 4 / 2 = 2

3. Final Answer:

   2 -> Option C

4. Quick Check:

   Padding = (kernel_size - 1)/2 keeps size same [OK]

Hint: Padding = (kernel_size - 1) / 2 for same size with stride 1 [OK]

Common Mistakes:

• Using padding 0 or 1 incorrectly
• Forgetting stride must be 1 for same size
• Using padding larger than needed