FCN (Fully Convolutional Network) in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the necessary PyTorch module for building an FCN model.

Computer Vision

import torch.nn as [1]

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

Adata

Boptim

Cutils

Dnn

Attempts:

3 left

💡 Hint

Common Mistakes

Importing the optimizer module instead of the neural network module.

Using 'utils' which is unrelated to layers.

The nn module in PyTorch contains layers and functions to build neural networks, including FCNs.

2fill in blank

medium

Complete the code to define a convolutional layer with 3 input channels and 64 output channels.

Computer Vision

conv_layer = nn.Conv2d([1], 64, kernel_size=3, padding=1)

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

A3

B1

C64

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using the number of output channels as input channels.

Confusing kernel size with input channels.

The input channels for a color image are usually 3 (RGB), so the first argument is 3.

3fill in blank

hard

Fix the error in the forward method by completing the code to apply the final convolutional layer to the input.

Computer Vision

def forward(self, x):
    x = self.conv_final([1])
    return x

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

Aself

Bx

Cconv_final

Dinput

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the layer itself instead of the input tensor.

Using an undefined variable like 'input'.

The input tensor to the layer is x, so we pass x to self.conv_final.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each class index to its predicted pixel count in the segmentation output.

Computer Vision

pixel_counts = {cls: (pred == [1]).sum().item() for cls in range([2])}

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

Acls

Bpred

Cnum_classes

Doutput

Attempts:

3 left

💡 Hint

Common Mistakes

Comparing with the prediction tensor instead of the class index.

Using the wrong variable for the range.

We compare the prediction tensor pred to each class index cls and count pixels. The range is over num_classes.

5fill in blank

hard

Fill all three blanks to complete the training loop snippet that computes the loss, backpropagates, and updates the model parameters.

Computer Vision

optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, [1])
loss.[2]()
optimizer.[3]()

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

Alabels

Bbackward

Cstep

Dinputs

Attempts:

3 left

💡 Hint

Common Mistakes

Using inputs instead of labels for loss calculation.

Forgetting to zero gradients before backward pass.

Calling wrong methods on loss or optimizer.

The loss is computed comparing outputs to labels. Then loss.backward() computes gradients, and optimizer.step() updates weights.

Practice

1. What is the main advantage of a Fully Convolutional Network (FCN) compared to a traditional CNN for image tasks?

easy

A. It can label every pixel in the image, preserving spatial information.

B. It uses fully connected layers to improve classification accuracy.

C. It reduces the image size to a single vector for faster processing.

D. It only works with grayscale images for simplicity.

Solution

1. Step 1: Understand FCN structure

   FCNs replace fully connected layers with convolution layers to keep spatial info.

2. Step 2: Compare with traditional CNNs

   Traditional CNNs use fully connected layers that lose pixel location details, FCNs keep pixel-wise info.

3. Final Answer:

   It can label every pixel in the image, preserving spatial information. -> Option A

4. Quick Check:

   FCN labels pixels = B [OK]

Hint: FCNs keep pixel info; CNNs lose it with fully connected layers [OK]

Common Mistakes:

• Thinking FCNs use fully connected layers
• Assuming FCNs reduce image to vector
• Believing FCNs only work on grayscale

2. Which of the following is the correct way to replace a fully connected layer with a convolutional layer in an FCN?

easy

A. nn.Linear(in_features, out_features)

B. nn.ReLU()

C. nn.Conv2d(in_channels, out_channels, kernel_size=1)

D. nn.MaxPool2d(kernel_size=2)

Solution

1. Step 1: Identify layer types

   Fully connected layers are replaced by 1x1 convolution layers to keep spatial size.

2. Step 2: Match correct PyTorch layer

   nn.Conv2d with kernel size 1 acts like a fully connected layer per pixel.

3. Final Answer:

   nn.Conv2d(in_channels, out_channels, kernel_size=1) -> Option C

4. Quick Check:

   1x1 conv replaces FC layer = D [OK]

Hint: Use 1x1 conv to replace fully connected layers [OK]

Common Mistakes:

• Choosing nn.Linear which is fully connected
• Confusing pooling or activation layers as replacements
• Using wrong kernel sizes

3. Given this PyTorch FCN snippet, what is the output shape if the input is (1, 3, 64, 64)?

import torch
import torch.nn as nn

class SimpleFCN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        self.conv2 = nn.Conv2d(16, 2, 1)
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        return x

model = SimpleFCN()
input_tensor = torch.randn(1, 3, 64, 64)
output = model(input_tensor)
print(output.shape)

medium

A. (1, 2, 64, 64)

B. (1, 2, 62, 62)

C. (1, 16, 64, 64)

D. (1, 3, 64, 64)

Solution

1. Step 1: Analyze first conv layer

   Conv2d(3,16,3,padding=1) keeps spatial size 64x64, output shape (1,16,64,64).

2. Step 2: Analyze second conv layer

   Conv2d(16,2,1) with kernel size 1 keeps spatial size, output shape (1,2,64,64).

3. Final Answer:

   (1, 2, 64, 64) -> Option A

4. Quick Check:

   Padding keeps size; 1x1 conv keeps size = A [OK]

Hint: Padding keeps size; 1x1 conv keeps spatial dims [OK]

Common Mistakes:

• Ignoring padding effect on size
• Assuming kernel 3 reduces size without padding
• Confusing channel and spatial dimensions

4. You have an FCN model but the output size is smaller than the input image size. What is the most likely cause?

medium

A. Using 1x1 convolution layers increases spatial size.

B. Using convolution layers without padding reduces spatial size.

C. Using fully connected layers preserves spatial size.

D. Using batch normalization layers reduces spatial size.

Solution

1. Step 1: Understand convolution padding effect

   Convolution without padding shrinks spatial dimensions because kernel slides inside image.

2. Step 2: Identify cause of smaller output

   If output is smaller, likely padding is missing in conv layers causing shrinkage.

3. Final Answer:

   Using convolution layers without padding reduces spatial size. -> Option B

4. Quick Check:

   No padding shrinks output = A [OK]

Hint: No padding in conv layers shrinks output size [OK]

Common Mistakes:

• Thinking 1x1 conv changes size
• Believing batch norm affects size
• Assuming fully connected layers keep spatial size

5. You want to build an FCN for semantic segmentation on 128x128 images with 3 classes. Which architecture choice will produce output matching input size with class scores per pixel?

hard

A. Use fully connected layers after conv layers to classify whole image.

B. Use conv layers without padding and max pooling layers to reduce size.

C. Use conv layers with stride=2 and no upsampling layers.

D. Use conv layers with padding=1 and 1x1 conv at end, no pooling layers.

Solution

1. Step 1: Maintain spatial size

   Padding=1 with kernel size 3 keeps spatial size; no pooling avoids shrinking.

2. Step 2: Output class scores per pixel

   Use 1x1 conv with out_channels=3 to get class scores per pixel matching input size.

3. Final Answer:

   Use conv layers with padding=1 and 1x1 conv at end, no pooling layers. -> Option D

4. Quick Check:

   Padding + 1x1 conv = pixel-wise classes = C [OK]

Hint: Keep padding and no pooling for same size output [OK]

Common Mistakes:

• Using pooling reduces output size
• Using fully connected layers loses pixel info
• Using stride>1 without upsampling shrinks output