nn.LSTM layer in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does the nn.LSTM layer in PyTorch do?

The nn.LSTM layer processes sequences of data by remembering information over time. It helps models learn patterns in sequences like sentences or time series.

beginner

What are the main inputs and outputs of an nn.LSTM layer?

Input: a sequence of data with shape (sequence_length, batch_size, input_size). Output: the hidden states for each time step and the final hidden and cell states.

intermediate

Why does nn.LSTM have both hidden state and cell state?

The hidden state carries short-term memory, while the cell state carries long-term memory. This helps the LSTM remember important information over many steps.

beginner

How do you initialize an nn.LSTM layer for input size 10 and hidden size 20?

Use nn.LSTM(input_size=10, hidden_size=20). This sets the input feature size to 10 and the hidden layer size to 20.

intermediate

What does setting batch_first=True do in nn.LSTM?

It changes the input and output shape to (batch_size, sequence_length, input_size), which can be easier to work with when batches come first.

What shape does nn.LSTM expect for its input by default?

A (input_size, sequence_length, batch_size)

B (batch_size, input_size, sequence_length)

C (batch_size, sequence_length, input_size)

D (sequence_length, batch_size, input_size)

By default, nn.LSTM expects input shaped as (sequence_length, batch_size, input_size).

What are the two states returned by nn.LSTM besides the output?

A hidden state and cell state

B input state and output state

C weight state and bias state

D activation state and dropout state

nn.LSTM returns hidden state and cell state to keep track of short-term and long-term memory.

What does the hidden_size parameter control in nn.LSTM?

A The batch size

B The number of features in the hidden state

C The length of the input sequence

D The number of layers

hidden_size sets how many features the hidden state will have.

If batch_first=True, what is the input shape for nn.LSTM?

A (batch_size, input_size, sequence_length)

B (sequence_length, batch_size, input_size)

C (batch_size, sequence_length, input_size)

D (input_size, batch_size, sequence_length)

Setting batch_first=True changes input shape to (batch_size, sequence_length, input_size).

Why is nn.LSTM better than a simple RNN for long sequences?

A Because it can remember information longer using cell state

B Because it uses convolution layers

C Because it has fewer parameters

D Because it does not use activation functions

nn.LSTM uses a cell state to keep long-term memory, helping with long sequences.

Explain how nn.LSTM processes a sequence of data step-by-step.

Think about how information flows through time steps and how memory is kept.

Describe the difference between hidden state and cell state in nn.LSTM and why both are important.

Consider how remembering recent vs. older information helps understanding sequences.

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