Sequence classification in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a simple sequence classification model using PyTorch's nn.Module.

PyTorch

import torch.nn as nn

class SequenceClassifier(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super().__init__()
        self.rnn = nn.LSTM(input_dim, hidden_dim, batch_first=True)
        self.fc = nn.Linear(hidden_dim, [1])

    def forward(self, x):
        _, (hidden, _) = self.rnn(x)
        out = self.fc(hidden[-1])
        return out

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

Abatch_size

Bhidden_dim

Cinput_dim

Doutput_dim

Attempts:

3 left

💡 Hint

Common Mistakes

Using hidden_dim instead of output_dim for the linear layer output size.

Confusing input_dim with output_dim.

The final linear layer should map from the hidden dimension to the output dimension, which represents the number of classes.

2fill in blank

medium

Complete the code to apply a softmax activation to the model output for classification probabilities.

PyTorch

import torch.nn.functional as F

outputs = model(inputs)
probabilities = F.[1](outputs, dim=1)

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

Asigmoid

Btanh

Csoftmax

Drelu

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid instead of softmax for multi-class outputs.

Forgetting to specify the dimension for softmax.

Softmax converts raw model outputs (logits) into probabilities that sum to 1 across classes.

3fill in blank

hard

Fix the error in the training loop by completing the missing optimizer step.

PyTorch

for inputs, labels in dataloader:
    optimizer.zero_grad()
    outputs = model(inputs)
    loss = criterion(outputs, labels)
    loss.backward()
    [1]

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

Aoptimizer.step()

Bmodel.step()

Closs.step()

Dcriterion.step()

Attempts:

3 left

💡 Hint

Common Mistakes

Calling step() on loss or model instead of optimizer.

Forgetting to call optimizer.step() causing no training progress.

After computing gradients with loss.backward(), optimizer.step() updates the model parameters.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each word to its length only if the length is greater than 3.

PyTorch

words = ['apple', 'cat', 'banana', 'dog']
lengths = {word: [1] for word in words if [2]

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

Alen(word)

Blen(word) > 3

Cword > 3

Dword.length

Attempts:

3 left

💡 Hint

Common Mistakes

Using word > 3 which compares string to int and causes error.

Using word.length which is not valid in Python.

We map each word to its length using len(word), and filter words with length greater than 3 using len(word) > 3.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each word in words to its uppercase form only if the word length is less than 5.

PyTorch

words = ['apple', 'cat', 'banana', 'dog']
result = { [1]: [2] for [3] in words if len([3]) < 5 }

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

Aword

Bword.upper()

Dwords

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'words' instead of 'word' in the for loop.

Using the wrong variable name causing NameError.

We use 'word' as the key, 'word.upper()' as the value, and iterate with 'for word in words'.