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.