Hidden state management in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the shape of the hidden state after one forward pass?

Consider the following PyTorch code snippet using an LSTM layer. What will be the shape of the hidden state h_n after running the forward pass?

PyTorch

import torch
import torch.nn as nn

lstm = nn.LSTM(input_size=10, hidden_size=20, num_layers=2)
inputs = torch.randn(5, 3, 10)  # seq_len=5, batch=3, input_size=10
output, (h_n, c_n) = lstm(inputs)

# What is h_n.shape?

A (3, 20)

B (5, 3, 20)

C (2, 3, 20)

D (3, 2, 20)

💡 Hint

Remember the hidden state shape is (num_layers, batch_size, hidden_size).

The hidden state h_n of an LSTM has shape (num_layers, batch_size, hidden_size). Here, num_layers=2, batch_size=3, hidden_size=20, so the shape is (2, 3, 20).

🧠 Conceptual

intermediate

Why do we detach hidden states in RNN training?

In training recurrent neural networks, why is it important to detach the hidden state from the computation graph between batches?

A To convert the hidden state to a numpy array

B To increase the size of the hidden state tensor

C To reset the model weights to initial values

D To prevent backpropagation through the entire history and save memory

💡 Hint

Think about how backpropagation works through time in RNNs.

Detaching the hidden state stops gradients from flowing back through all previous batches, which prevents excessive memory use and long backpropagation chains.

🔧 Debug

advanced

Identify the error in hidden state initialization

What is wrong with the following code snippet for initializing hidden states in a GRU model?

PyTorch

import torch
import torch.nn as nn

gru = nn.GRU(input_size=8, hidden_size=16, num_layers=1)
batch_size = 4
h0 = torch.zeros(1, batch_size, 16)  # Intended hidden state
inputs = torch.randn(10, batch_size, 8)
output, hn = gru(inputs, h0)

A h0 should have shape (num_layers, batch_size, hidden_size), not (batch_size, hidden_size)

B h0 should be initialized with ones, not zeros

C inputs should have batch_size as first dimension, not second

D GRU requires hidden state to be on CPU, not default device

💡 Hint

Check the expected shape of the initial hidden state for GRU layers.

The initial hidden state h0 must have shape (num_layers, batch_size, hidden_size). Here, it is missing the num_layers dimension.

❓ Hyperparameter

advanced

Effect of hidden state size on model capacity

Increasing the hidden state size in an RNN model primarily affects which of the following?

A The number of input features processed per time step

B The model's ability to capture more complex patterns by increasing capacity

C The length of input sequences the model can handle

D The batch size used during training

💡 Hint

Think about what hidden state size controls in an RNN.

The hidden state size controls the dimensionality of the internal memory, allowing the model to represent more complex information.

❓ Metrics

expert

Interpreting hidden state outputs for sequence classification

In a sequence classification task using an LSTM, which hidden state output is typically used as the representation for the entire sequence?

A The last hidden state of the top LSTM layer (h_n at last time step)

B The average of all hidden states across all time steps

C The first hidden state of the bottom LSTM layer

D The cell state (c_n) of the first LSTM layer

💡 Hint

Consider which hidden state summarizes the sequence information after processing.

The last hidden state of the top LSTM layer is commonly used as the fixed-size vector representing the entire input sequence for classification.

Practice

1. What is the main purpose of the hidden state in a PyTorch RNN model?

easy

A. To store information from previous time steps in a sequence

B. To initialize the model weights randomly

C. To store the final output of the model

D. To reset the model after each batch

Solution

1. Step 1: Understand the role of hidden state in sequence models

   The hidden state keeps track of information from previous inputs in a sequence, allowing the model to remember context.

2. Step 2: Differentiate hidden state from other components

   Model weights are parameters, outputs are results, and resetting is a process, none of which describe the hidden state's role.

3. Final Answer:

   To store information from previous time steps in a sequence -> Option A

4. Quick Check:

   Hidden state = stores past info [OK]

Hint: Hidden state remembers past inputs in sequences [OK]

Common Mistakes:

• Confusing hidden state with model weights
• Thinking hidden state stores final output
• Assuming hidden state resets model

2. Which of the following is the correct way to initialize a hidden state for an RNN with batch size 4 and hidden size 10 in PyTorch?

easy

A. torch.zeros(1, 4, 10)

B. torch.zeros(4, 10)

C. torch.zeros(4, 1, 10)

D. torch.zeros(10, 4)

Solution

1. Step 1: Recall RNN hidden state shape requirements

   For PyTorch RNN, hidden state shape is (num_layers * num_directions, batch_size, hidden_size). Assuming 1 layer and unidirectional, shape is (1, 4, 10).

2. Step 2: Match options to correct shape

   torch.zeros(1, 4, 10) matches (1, 4, 10). Others have incorrect dimensions.

3. Final Answer:

   torch.zeros(1, 4, 10) -> Option A

4. Quick Check:

   Hidden state shape = (layers, batch, hidden) [OK]

Hint: Hidden state shape = (layers, batch, hidden) [OK]

Common Mistakes:

• Using batch size as first dimension
• Ignoring number of layers dimension
• Swapping hidden size and batch size

3. Given the code below, what will be the shape of output after running the RNN?

rnn = torch.nn.RNN(input_size=5, hidden_size=3, batch_first=True)
inputs = torch.randn(2, 4, 5)  # batch=2, seq_len=4, input_size=5
h0 = torch.zeros(1, 2, 3)
output, hn = rnn(inputs, h0)

medium

A. torch.Size([2, 3, 4])

B. torch.Size([2, 4, 3])

C. torch.Size([4, 2, 3])

D. torch.Size([1, 2, 3])

Solution

1. Step 1: Understand RNN output shape with batch_first=True

   Output shape is (batch_size, seq_len, hidden_size). Here batch=2, seq_len=4, hidden=3.

2. Step 2: Match output shape to options

   torch.Size([2, 4, 3]) matches (2, 4, 3). Others have incorrect dimension orders or sizes.

3. Final Answer:

   torch.Size([2, 4, 3]) -> Option B

4. Quick Check:

   Output shape = (batch, seq, hidden) [OK]

Hint: With batch_first=True, output shape is (batch, seq_len, hidden) [OK]

Common Mistakes:

• Confusing batch and sequence dimensions
• Ignoring batch_first=True effect
• Mixing hidden size with sequence length

4. Identify the error in the following code snippet for managing hidden state in an RNN:

rnn = torch.nn.RNN(5, 3)
inputs = torch.randn(1, 2, 5)
h0 = torch.zeros(1, 1, 3)
output, hn = rnn(inputs, h0)

medium

A. The RNN layer is missing batch_first=True

B. The input tensor shape is incorrect for batch_first=False

C. The hidden size does not match input size

D. The hidden state shape does not match batch size

Solution

1. Step 1: Check input and hidden state shapes

   Input shape is (seq_len=1, batch=2, input_size=5). Hidden state shape is (num_layers=1, batch=1, hidden_size=3).

2. Step 2: Identify mismatch in batch size

   Hidden state batch size is 1 but input batch size is 2, causing mismatch error.

3. Final Answer:

   The hidden state shape does not match batch size -> Option D

4. Quick Check:

   Hidden batch size must match input batch size [OK]

Hint: Hidden state batch size must match input batch size [OK]

Common Mistakes:

• Ignoring batch size dimension in hidden state
• Assuming input shape is batch_first by default
• Mixing hidden size with input size

5. You want to process a sequence in batches using an RNN and keep the hidden state between batches to maintain context. Which approach correctly manages the hidden state across batches?

hard

A. Initialize hidden state once before all batches and reuse it without detaching

B. Initialize hidden state as zeros before each batch

C. Pass the hidden state from the previous batch to the next batch after detaching it from the computation graph

D. Reset hidden state to None before each batch

Solution

1. Step 1: Understand hidden state persistence across batches

   To keep context, hidden state must be passed from one batch to the next.

2. Step 2: Avoid backpropagation through entire history

   Detaching hidden state from the computation graph prevents gradients from flowing through all previous batches, avoiding memory issues.

3. Final Answer:

   Pass the hidden state from the previous batch to the next batch after detaching it from the computation graph -> Option C

4. Quick Check:

   Detach hidden state to keep context safely [OK]

Hint: Detach hidden state before next batch to keep context [OK]

Common Mistakes:

• Reusing hidden state without detaching causes memory errors
• Resetting hidden state each batch loses context
• Not passing hidden state between batches