nn.LSTM layer in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of nn.LSTM with batch_first=True

Consider the following PyTorch code snippet using nn.LSTM with batch_first=True. What is the shape of the output tensor `out`?

PyTorch

import torch
import torch.nn as nn

lstm = nn.LSTM(input_size=10, hidden_size=20, num_layers=2, batch_first=True)
input_tensor = torch.randn(5, 7, 10)  # batch=5, seq_len=7, input_size=10
out, (h_n, c_n) = lstm(input_tensor)
print(out.shape)

A torch.Size([7, 5, 20])

B torch.Size([5, 20, 7])

C torch.Size([7, 20, 5])

D torch.Size([5, 7, 20])

💡 Hint

Remember that batch_first=True means the batch dimension is the first dimension in the input and output.

With batch_first=True, the input and output tensors have shape (batch_size, seq_len, hidden_size). Here batch_size=5, seq_len=7, hidden_size=20, so output shape is (5, 7, 20).

❓ Model Choice

intermediate

Choosing LSTM parameters for sequence classification

You want to build an LSTM model to classify sequences of length 15 with 8 features each into 3 classes. Which nn.LSTM configuration is correct to output a tensor suitable for classification after processing the entire sequence?

A nn.LSTM(input_size=3, hidden_size=8, num_layers=2, batch_first=True)

B nn.LSTM(input_size=15, hidden_size=3, num_layers=1, batch_first=False)

C nn.LSTM(input_size=8, hidden_size=16, num_layers=1, batch_first=True)

D nn.LSTM(input_size=8, hidden_size=15, num_layers=3, batch_first=False)

💡 Hint

Input size should match the feature dimension per time step.

The input_size must be 8 because each time step has 8 features. Batch_first=True is convenient for batch processing. Hidden size 16 is a reasonable choice. Other options mismatch input_size or batch_first setting.

❓ Hyperparameter

advanced

Effect of increasing num_layers in nn.LSTM

What is the main effect of increasing the num_layers parameter in nn.LSTM from 1 to 3?

A The LSTM will have 3 stacked layers, allowing it to learn more complex temporal patterns.

B The input size of the LSTM will automatically triple.

C The output tensor shape will change from 3D to 2D.

D The LSTM will process sequences in reverse order.

💡 Hint

Think about what stacking layers means in neural networks.

Increasing num_layers stacks multiple LSTM layers on top of each other, enabling the model to capture more complex features over time. It does not change input size or output tensor dimensions directly.

🔧 Debug

advanced

Identifying error in LSTM input shape

What error will this code raise when running the LSTM forward pass?

PyTorch

import torch
import torch.nn as nn

lstm = nn.LSTM(input_size=5, hidden_size=10, batch_first=True)
input_tensor = torch.randn(4, 6, 4)  # batch=4, seq_len=6, input_size=4
out, (h_n, c_n) = lstm(input_tensor)

A RuntimeError: input size mismatch. Expected input_size=5 but got 4.

B TypeError: LSTM input must be 2D tensor.

C ValueError: batch_first must be False for this input shape.

D No error, code runs successfully.

💡 Hint

Check the input tensor's last dimension against the LSTM's input_size.

The LSTM expects input tensors with last dimension equal to input_size=5, but input_tensor has last dimension 4, causing a RuntimeError.

❓ Metrics

expert

Interpreting LSTM hidden state shapes after forward pass

After running an nn.LSTM with num_layers=2, hidden_size=8, batch_first=True on input of shape (3, 10, 6), what is the shape of the hidden state tensor h_n?

A torch.Size([10, 3, 8])

B torch.Size([2, 3, 8])

C torch.Size([3, 10, 8])

D torch.Size([3, 2, 8])

💡 Hint

Hidden state shape is (num_layers, batch_size, hidden_size).

The hidden state h_n has shape (num_layers, batch_size, hidden_size). Here num_layers=2, batch_size=3, hidden_size=8, so shape is (2, 3, 8).

Practice

1. What is the primary purpose of the nn.LSTM layer in PyTorch?

easy

A. To process and remember information from sequences over time

B. To perform image classification using convolution

C. To reduce the dimensionality of data using PCA

D. To generate random numbers for initialization

Solution

1. Step 1: Understand the role of LSTM

   LSTM stands for Long Short-Term Memory, a type of recurrent neural network layer designed to handle sequence data and remember information over time.

2. Step 2: Match purpose with options

   Among the options, only processing and remembering sequence information matches the LSTM's purpose.

3. Final Answer:

   To process and remember information from sequences over time -> Option A

4. Quick Check:

   LSTM purpose = sequence memory [OK]

Hint: LSTM = sequence memory layer, not image or random [OK]

Common Mistakes:

• Confusing LSTM with convolutional layers
• Thinking LSTM reduces data dimension like PCA
• Assuming LSTM generates random numbers

2. Which of the following is the correct way to create an LSTM layer in PyTorch with input size 10 and hidden size 20?

easy

A. nn.LSTM(input=10, hidden=20)

B. nn.LSTM(20, 10)

C. nn.LSTM(10, 20)

D. nn.LSTM(hidden_size=10, input_size=20)

Solution

1. Step 1: Recall nn.LSTM constructor parameters

   The first argument is input_size (features per input), the second is hidden_size (features in hidden state).

2. Step 2: Match correct syntax

   nn.LSTM(10, 20) uses nn.LSTM(10, 20) which correctly sets input_size=10 and hidden_size=20.

3. Final Answer:

   nn.LSTM(10, 20) -> Option C

4. Quick Check:

   Constructor order = input_size, hidden_size [OK]

Hint: First arg input size, second hidden size in nn.LSTM() [OK]

Common Mistakes:

• Swapping input_size and hidden_size
• Using wrong keyword arguments
• Confusing parameter names

3. Given the code below, what is the shape of output after running the LSTM?

import torch
import torch.nn as nn
lstm = nn.LSTM(input_size=5, hidden_size=3, num_layers=1)
inputs = torch.randn(4, 2, 5)  # seq_len=4, batch=2, input_size=5
output, (hn, cn) = lstm(inputs)

medium

A. (4, 2, 3)

B. (2, 4, 3)

C. (4, 3, 2)

D. (2, 3, 4)

Solution

1. Step 1: Understand LSTM input and output shapes

   The input shape is (seq_len, batch, input_size). The output shape is (seq_len, batch, hidden_size).

2. Step 2: Apply given dimensions

   Input shape is (4, 2, 5), hidden_size=3, so output shape is (4, 2, 3).

3. Final Answer:

   (4, 2, 3) -> Option A

4. Quick Check:

   Output shape = (seq_len, batch, hidden_size) [OK]

Hint: Output shape matches (seq_len, batch, hidden_size) [OK]

Common Mistakes:

• Mixing batch and sequence dimensions
• Confusing input_size with hidden_size
• Assuming output shape swaps batch and seq_len

4. What is wrong with this code snippet that tries to create an LSTM layer?

import torch.nn as nn
lstm = nn.LSTM(10)

medium

A. The input size must be a tuple, not an integer

B. It misses the hidden_size argument, causing an error

C. LSTM requires a batch size argument at creation

D. The code is correct and runs without error

Solution

1. Step 1: Check nn.LSTM constructor requirements

   nn.LSTM requires at least two positional arguments: input_size and hidden_size.

2. Step 2: Identify missing argument

   The code only provides input_size=10, missing hidden_size, so it will raise a TypeError.

3. Final Answer:

   It misses the hidden_size argument, causing an error -> Option B

4. Quick Check:

   nn.LSTM needs input_size and hidden_size [OK]

Hint: nn.LSTM needs two sizes: input and hidden [OK]

Common Mistakes:

• Thinking batch size is needed at layer creation
• Assuming input_size can be a tuple
• Believing code runs without error

5. You want to build a model that processes sequences of length 6 with 8 features each. You want the LSTM to output a sequence with 12 features per time step. Which of the following LSTM layer initializations is correct to achieve this?

hard

A. nn.LSTM(input_size=12, hidden_size=8)

B. nn.LSTM(input_size=8, hidden_size=6)

C. nn.LSTM(input_size=6, hidden_size=8)

D. nn.LSTM(input_size=8, hidden_size=12)

Solution

1. Step 1: Identify input_size and hidden_size meanings

   input_size is the number of features per time step in the input sequence. hidden_size is the number of features in the output per time step.

2. Step 2: Match given sequence and desired output

   Input sequences have 8 features, so input_size=8. Desired output features per time step is 12, so hidden_size=12.

3. Final Answer:

   nn.LSTM(input_size=8, hidden_size=12) -> Option D

4. Quick Check:

   Input features = 8, output features = 12 [OK]

Hint: Input size = input features, hidden size = output features [OK]

Common Mistakes:

• Confusing sequence length with input_size
• Swapping input_size and hidden_size
• Using sequence length as hidden_size