nn.Conv2d layers in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does nn.Conv2d layer do in a neural network?

It applies a set of filters (kernels) to 2D input data (like images) to extract features such as edges or textures by sliding the filters over the input.

beginner

What are the main parameters of nn.Conv2d?

The main parameters are: in_channels (input depth), out_channels (number of filters), kernel_size (filter size), stride (step size for sliding), padding (border added), and dilation (spacing inside the kernel).

intermediate

How does padding affect the output size of nn.Conv2d?

Padding adds pixels around the input edges, allowing the filter to cover border areas. This can keep the output size the same as input or control shrinking.

intermediate

What is the effect of stride in nn.Conv2d?

Stride controls how far the filter moves each step. A stride of 1 moves one pixel at a time, producing larger outputs. Larger strides skip pixels, reducing output size.

beginner

Why do we use multiple filters (out_channels) in nn.Conv2d?

Multiple filters let the network learn different features from the input, like edges, colors, or shapes, improving the model's ability to understand complex patterns.

What does the kernel_size parameter in nn.Conv2d specify?

A The number of filters used

B The size of the filter applied to the input

C The step size of the filter movement

D The amount of padding added

kernel_size defines the height and width of the filter sliding over the input.

If stride is set to 2 in nn.Conv2d, what happens to the output size compared to stride 1?

A Output size becomes zero

B Output size doubles

C Output size stays the same

D Output size halves approximately

A stride of 2 moves the filter two pixels at a time, reducing output size roughly by half.

What is the role of padding in nn.Conv2d?

A To add borders so output size can be controlled

B To speed up training

C To change the input channels

D To increase the number of filters

Padding adds pixels around input edges to control output size and preserve border information.

What does out_channels parameter control in nn.Conv2d?

A Number of filters applied

B Number of input channels

C Size of the input image

D Stride length

out_channels sets how many filters the layer uses, determining output depth.

Which of these is NOT a typical use of nn.Conv2d?

A Extracting image features

B Reducing image size

C Classifying text documents directly

D Detecting edges in images

nn.Conv2d is designed for 2D data like images, not for direct text classification.

Explain how the parameters kernel_size, stride, and padding affect the output size of an nn.Conv2d layer.

Think about how the filter moves and covers the input image.

Describe why multiple filters (out_channels) are used in nn.Conv2d and how they help the model learn.

Imagine looking at an image with different colored glasses to see different details.

Practice

1. What does the nn.Conv2d layer in PyTorch primarily do?

easy

A. It increases the image size by adding pixels.

B. It slides filters over images to find patterns.

C. It converts images to grayscale.

D. It sorts images by color intensity.

Solution

1. Step 1: Understand the role of convolution layers

   Convolution layers slide small filters over input images to detect features like edges or textures.

2. Step 2: Match the function to the options

   Only It slides filters over images to find patterns. correctly describes this sliding filter action, while others describe unrelated image operations.

3. Final Answer:

   It slides filters over images to find patterns. -> Option B

4. Quick Check:

   Convolution = sliding filters [OK]

Hint: Conv2d = sliding filters over images to find features [OK]

Common Mistakes:

• Thinking Conv2d changes image size by adding pixels
• Confusing Conv2d with image color adjustments
• Assuming Conv2d sorts or rearranges pixels

2. Which of the following is the correct way to create a Conv2d layer with 3 input channels, 16 output channels, and a 3x3 kernel in PyTorch?

easy

A. nn.Conv2d(3, 16, kernel_size=3)

B. nn.Conv2d(16, 3, kernel_size=3)

C. nn.Conv2d(3, 16, kernel=3)

D. nn.Conv2d(input=3, output=16, size=3)

Solution

1. Step 1: Recall Conv2d constructor parameters

   The correct order is nn.Conv2d(in_channels, out_channels, kernel_size).

2. Step 2: Check each option

   nn.Conv2d(3, 16, kernel_size=3) matches the correct parameter order and uses the correct keyword for kernel size. The other options have wrong parameter order or incorrect keywords.

3. Final Answer:

   nn.Conv2d(3, 16, kernel_size=3) -> Option A

4. Quick Check:

   Conv2d(in, out, kernel_size) = A [OK]

Hint: Remember Conv2d(in_channels, out_channels, kernel_size) [OK]

Common Mistakes:

• Swapping input and output channels
• Using wrong parameter names like 'kernel' instead of 'kernel_size'
• Passing parameters as keywords not supported by Conv2d

3. What will be the output shape of the following PyTorch Conv2d layer when applied to an input tensor of shape (1, 3, 32, 32)?

conv = nn.Conv2d(3, 6, kernel_size=5)
output = conv(torch.randn(1, 3, 32, 32))
print(output.shape)

medium

A. torch.Size([1, 3, 28, 28])

B. torch.Size([1, 6, 32, 32])

C. torch.Size([6, 3, 28, 28])

D. torch.Size([1, 6, 28, 28])

Solution

1. Step 1: Calculate output spatial size

   Output size = (Input size - Kernel size + 1) = (32 - 5 + 1) = 28 for both height and width.

2. Step 2: Determine output channels and batch size

   Output channels = 6, batch size = 1, so output shape is (1, 6, 28, 28).

3. Final Answer:

   torch.Size([1, 6, 28, 28]) -> Option D

4. Quick Check:

   Output shape = (batch, out_channels, 28, 28) [OK]

Hint: Output size = input - kernel + 1 if stride=1, padding=0 [OK]

Common Mistakes:

• Assuming output size equals input size without padding
• Mixing up input and output channels in shape
• Forgetting batch size dimension

4. Identify the error in this Conv2d layer definition:

conv = nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=3)
output = conv(torch.randn(1, 3, 28, 28))
print(output.shape)

medium

A. Stride cannot be 2 in Conv2d.

B. Input tensor shape is incorrect for 3 input channels.

C. Padding is too large causing output size to increase unexpectedly.

D. Kernel size must be an odd number.

Solution

1. Step 1: Calculate output size with given parameters

   Output size formula: floor((Input + 2*padding - kernel_size)/stride) + 1 = floor((28 + 6 - 3)/2) + 1 = floor(31/2) + 1 = 15 + 1 = 16.

2. Step 2: Understand padding effect

   Padding=3 is large for kernel=3, causing output spatial size to increase unexpectedly, which is unusual and may cause unexpected behavior.

3. Final Answer:

   Padding is too large causing output size to increase unexpectedly. -> Option C

4. Quick Check:

   Large padding inflates output size [OK]

Hint: Check padding size relative to kernel size for output shape [OK]

Common Mistakes:

• Thinking stride=2 is invalid
• Assuming input shape is wrong for 3 channels
• Believing kernel size must be odd always

5. You want to design a Conv2d layer that keeps the input image size (28x28) unchanged after convolution with a 5x5 kernel and stride 1. Which padding value should you use?

hard

A. Padding = 2

B. Padding = 1

C. Padding = 0

D. Padding = 3

Solution

1. Step 1: Use output size formula for Conv2d

   Output size = floor((Input + 2*padding - kernel_size)/stride) + 1. We want output = input = 28, stride=1, kernel=5.

2. Step 2: Solve for padding

   28 = (28 + 2*padding - 5) + 1 -> 28 = 24 + 2*padding -> 2*padding = 4 -> padding = 2.

3. Final Answer:

   Padding = 2 -> Option A

4. Quick Check:

   Padding 2 keeps size with 5x5 kernel [OK]

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

Common Mistakes:

• Using zero padding and expecting same size
• Choosing padding less than 2 for 5x5 kernel
• Confusing stride effect with padding