nn.RNN layer in PyTorch - Model Pipeline Trace

Model Pipeline - nn.RNN layer

This pipeline shows how a simple Recurrent Neural Network (RNN) layer processes sequential data to learn patterns over time steps. It starts with input sequences, transforms them through the RNN layer, trains the model to reduce error, and finally makes predictions on new sequences.

Data Flow - 3 Stages

1Input Data

1000 sequences x 10 time steps x 5 features→Raw sequential data representing 1000 samples, each with 10 time steps and 5 features per step→1000 sequences x 10 time steps x 5 features

[[0.1, 0.2, 0.3, 0.4, 0.5], ..., [0.5, 0.4, 0.3, 0.2, 0.1]] for 10 time steps

↓

2RNN Layer

1000 sequences x 10 time steps x 5 features→Processes input sequences through nn.RNN with hidden size 8, producing hidden states for each time step→1000 sequences x 10 time steps x 8 features

Hidden states like [[0.01, 0.02, ..., 0.08], ..., [0.05, 0.04, ..., 0.01]] for 10 time steps

↓

3Output Layer

1000 sequences x 10 time steps x 8 features→Takes last hidden state and applies a linear layer to predict output class→1000 sequences x 3 classes

[0.2, 0.5, 0.3] representing class probabilities

Training Trace - Epoch by Epoch

Loss
1.2 |*****
0.9 |****
0.7 |***
0.5 |**
0.4 |*

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Initial training with high loss and low accuracy
2	0.9	0.60	Loss decreased, accuracy improved
3	0.7	0.72	Model learning meaningful patterns
4	0.5	0.80	Good convergence, loss continues to drop
5	0.4	0.85	Training stabilizes with high accuracy

Prediction Trace - 5 Layers

Layer 1: Input Sequence

Layer 2: RNN Layer

Layer 3: Last Hidden State Extraction

Layer 4: Linear Layer

Layer 5: Softmax Activation

Model Quiz - 3 Questions

What shape does the RNN layer output if input is (1000, 10, 5) and hidden size is 8?

A (1000, 8, 10)

B (1000, 10, 8)

C (1000, 5, 8)

D (10, 1000, 8)

Key Insight

The nn.RNN layer processes sequential data step-by-step, updating a hidden state that captures information from all previous time steps. Using the last hidden state allows the model to summarize the entire sequence for tasks like classification. Training shows loss decreasing and accuracy increasing, indicating the model learns meaningful sequence patterns.

Practice

1. What does the nn.RNN layer in PyTorch primarily do?

easy

A. Processes sequences step by step, keeping track of past information

B. Sorts input data in ascending order

C. Generates random numbers for initialization

D. Performs matrix multiplication without memory

Solution

1. Step 1: Understand the purpose of RNN

   The RNN layer is designed to handle sequential data by processing one step at a time and remembering previous steps.

2. Step 2: Compare options with RNN behavior

   Only Processes sequences step by step, keeping track of past information describes this behavior correctly; others describe unrelated functions.

3. Final Answer:

   Processes sequences step by step, keeping track of past information -> Option A

4. Quick Check:

   RNN remembers past inputs = A [OK]

Hint: RNNs remember past steps in sequences [OK]

Common Mistakes:

• Thinking RNN sorts data
• Confusing RNN with random number generators
• Assuming RNN does simple matrix multiplication only

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

easy

A. nn.RNN(20, 10)

B. nn.RNN(10)

C. nn.RNN(input_size=10, hidden_size=20)

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

Solution

1. Step 1: Recall nn.RNN constructor parameters

   The constructor requires input_size first, then hidden_size, e.g., nn.RNN(input_size=10, hidden_size=20).

2. Step 2: Check each option

   Only nn.RNN(input_size=10, hidden_size=20) matches the correct parameter order and names; the others reverse sizes, omit hidden_size, or swap parameters.

3. Final Answer:

   nn.RNN(input_size=10, hidden_size=20) -> Option C

4. Quick Check:

   Input size first, hidden size second = D [OK]

Hint: Remember: input_size before hidden_size in nn.RNN [OK]

Common Mistakes:

• Swapping input_size and hidden_size
• Omitting hidden_size parameter
• Using positional args in wrong order

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

import torch
import torch.nn as nn
rnn = nn.RNN(input_size=5, hidden_size=3, batch_first=True)
input = torch.randn(4, 7, 5)  # batch=4, seq_len=7, input_size=5
output, hn = rnn(input)

medium

A. (7, 4, 3)

B. (3, 4, 7)

C. (4, 3, 7)

D. (4, 7, 3)

Solution

1. Step 1: Understand batch_first=True effect

   With batch_first=True, input shape is (batch, seq_len, input_size), so output shape is (batch, seq_len, hidden_size).

2. Step 2: Apply shapes to given input

   Input shape is (4, 7, 5), so output shape is (4, 7, 3) because hidden_size=3.

3. Final Answer:

   (4, 7, 3) -> Option D

4. Quick Check:

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

Hint: batch_first=True means batch is first dimension [OK]

Common Mistakes:

• Confusing batch and sequence length order
• Ignoring batch_first parameter
• Mixing hidden_size with input_size in output shape

4. What is wrong with this code snippet using nn.RNN?

rnn = nn.RNN(input_size=8, hidden_size=4)
input = torch.randn(3, 5, 10)  # batch=3, seq_len=5, input_size=10
output, hn = rnn(input)

medium

A. RNN requires input to be 2D tensor

B. Input size does not match the RNN's input_size parameter

C. Batch size should be last dimension

D. Hidden size must be equal to input size

Solution

1. Step 1: Check input_size parameter vs input tensor

   The RNN expects input_size=8, but input tensor's last dimension is 10, causing mismatch.

2. Step 2: Validate tensor shape requirements

   Input shape (3, 5, 10) means batch=3, seq_len=5, input_size=10, which conflicts with RNN's input_size=8.

3. Final Answer:

   Input size does not match the RNN's input_size parameter -> Option B

4. Quick Check:

   Input last dim must match input_size = C [OK]

Hint: Input last dimension must match RNN input_size [OK]

Common Mistakes:

• Ignoring input_size mismatch
• Thinking batch size is last dimension
• Assuming RNN input is 2D tensor

5. You want to process a batch of sequences with varying lengths using nn.RNN. Which approach correctly handles this in PyTorch?

hard

A. Pad sequences to the same length and use pack_padded_sequence before the RNN

B. Feed sequences directly without padding or packing

C. Use a for loop to process each sequence separately without padding

D. Set hidden_size equal to the longest sequence length

Solution

1. Step 1: Understand handling variable-length sequences

   PyTorch recommends padding sequences to equal length and using pack_padded_sequence to inform RNN about actual lengths.

2. Step 2: Evaluate options for best practice

   Pad sequences to the same length and use pack_padded_sequence before the RNN correctly describes this approach. Options B and C ignore padding/packing, causing errors or inefficiency. Set hidden_size equal to the longest sequence length is unrelated to sequence length handling.

3. Final Answer:

   Pad sequences to the same length and use pack_padded_sequence before the RNN -> Option A

4. Quick Check:

   Use padding + pack_padded_sequence for variable lengths = A [OK]

Hint: Pad and pack sequences before RNN for variable lengths [OK]

Common Mistakes:

• Feeding raw variable-length sequences directly
• Ignoring packing after padding
• Misusing hidden_size for sequence length