Transformer decoder in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a TransformerDecoderLayer with 8 attention heads.

PyTorch

import torch.nn as nn

decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=[1])

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

A2

B16

C4

D8

Attempts:

3 left

💡 Hint

Common Mistakes

Using a number of heads that does not divide d_model evenly.

Confusing nhead with number of layers.

The TransformerDecoderLayer requires the number of attention heads as nhead. 8 is a common choice for d_model=512.

2fill in blank

medium

Complete the code to pass the memory tensor to the TransformerDecoder.

PyTorch

import torch
import torch.nn as nn

memory = torch.rand(10, 32, 512)  # (sequence_length, batch_size, d_model)
decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
decoder = nn.TransformerDecoder(decoder_layer, num_layers=6)
output = decoder(tgt=torch.rand(20, 32, 512), memory=[1])

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

Amemory

Btgt

Coutput

Dsrc

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the target tensor instead of memory.

Passing an undefined variable.

The memory argument is the output from the encoder and must be passed to the decoder as the memory parameter.

3fill in blank

hard

Fix the error in the code by selecting the correct mask to prevent the decoder from attending to future tokens.

PyTorch

import torch
import torch.nn as nn

decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
decoder = nn.TransformerDecoder(decoder_layer, num_layers=6)
tgt = torch.rand(20, 32, 512)
memory = torch.rand(10, 32, 512)
size = tgt.size(0)
mask = torch.triu(torch.ones(size, size), diagonal=[1]).bool()
output = decoder(tgt, memory, tgt_mask=mask)

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

A0

B-1

C1

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using diagonal=0 which masks the current token as well.

Using negative diagonal which is invalid here.

The mask should block attention to future tokens by masking the upper triangle above the main diagonal, so diagonal=1 is correct.

4fill in blank

hard

Fill both blanks to create a TransformerDecoderLayer with dropout and ReLU activation.

PyTorch

import torch.nn as nn

decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8, dropout=[1], activation=[2])

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

A0.1

B0.5

C"relu"

D"gelu"

Attempts:

3 left

💡 Hint

Common Mistakes

Using dropout as an integer.

Passing activation without quotes.

A dropout of 0.1 is common, and ReLU activation is specified as the string "relu".

5fill in blank

hard

Fill all three blanks to create a TransformerDecoder, pass the target and memory, and apply the correct mask.

PyTorch

import torch
import torch.nn as nn

memory = torch.rand(15, 64, 256)
tgt = torch.rand(30, 64, 256)
decoder_layer = nn.TransformerDecoderLayer(d_model=256, nhead=4)
decoder = nn.TransformerDecoder(decoder_layer, num_layers=[1])
size = tgt.size(0)
mask = torch.triu(torch.ones(size, size), diagonal=[2]).bool()
output = decoder(tgt=[3], memory=memory, tgt_mask=mask)

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

A3

B1

Ctgt

D5

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong number of layers.

Setting mask diagonal to 0 or 2.

Passing memory as tgt.

The decoder has 5 layers, the mask diagonal is 1 to block future tokens, and tgt is passed as the target tensor.

Practice

1. What is the main role of the Transformer decoder in a sequence-to-sequence model?

easy

A. To reduce the dimensionality of input data

B. To encode input sequences into fixed-size vectors

C. To perform image classification tasks

D. To generate output tokens step-by-step using previous outputs and encoder info

Solution

1. Step 1: Understand the Transformer decoder purpose

   The Transformer decoder generates output sequences by attending to previous outputs and encoder outputs.

2. Step 2: Compare options with decoder role

   Only To generate output tokens step-by-step using previous outputs and encoder info describes generating output tokens step-by-step using previous outputs and encoder info, which matches the decoder's role.

3. Final Answer:

   To generate output tokens step-by-step using previous outputs and encoder info -> Option D

4. Quick Check:

   Decoder generates outputs stepwise = D [OK]

Hint: Decoder creates outputs using past outputs and encoder data [OK]

Common Mistakes:

• Confusing encoder and decoder roles
• Thinking decoder encodes inputs
• Assuming decoder reduces data size

2. Which of the following is the correct way to create a Transformer decoder layer in PyTorch?

easy

A. torch.nn.TransformerDecoderLayer(d_model=512, nhead=8)

B. torch.nn.TransformerEncoderLayer(d_model=512, nhead=8)

C. torch.nn.TransformerDecoder(d_model=512, nhead=8)

D. torch.nn.TransformerLayer(d_model=512, nhead=8)

Solution

1. Step 1: Identify the correct PyTorch class for a decoder layer

   PyTorch provides torch.nn.TransformerDecoderLayer to create a single decoder layer.

2. Step 2: Check options for correct class and parameters

   torch.nn.TransformerDecoderLayer(d_model=512, nhead=8) uses torch.nn.TransformerDecoderLayer with correct parameters. Others are either encoder layers or invalid classes.

3. Final Answer:

   torch.nn.TransformerDecoderLayer(d_model=512, nhead=8) -> Option A

4. Quick Check:

   Decoder layer class is TransformerDecoderLayer = A [OK]

Hint: Decoder layer class ends with 'DecoderLayer' in PyTorch [OK]

Common Mistakes:

• Using EncoderLayer instead of DecoderLayer
• Trying to instantiate TransformerDecoder directly
• Using non-existent class names

3. Given the code below, what is the shape of the output tensor?

import torch
from torch.nn import TransformerDecoder, TransformerDecoderLayer

layer = TransformerDecoderLayer(d_model=256, nhead=8)
decoder = TransformerDecoder(layer, num_layers=3)

memory = torch.rand(10, 32, 256)  # (source_seq_len, batch_size, d_model)
tgt = torch.rand(20, 32, 256)     # (target_seq_len, batch_size, d_model)

output = decoder(tgt, memory)

medium

A. (32, 20, 256)

B. (10, 32, 256)

C. (20, 32, 256)

D. (20, 256, 32)

Solution

1. Step 1: Understand input and output shapes for TransformerDecoder

   The decoder input shape is (target_seq_len, batch_size, d_model). The output shape matches the target input shape.

2. Step 2: Check given shapes and output

   Target input 'tgt' has shape (20, 32, 256), so output will have the same shape.

3. Final Answer:

   (20, 32, 256) -> Option C

4. Quick Check:

   Output shape matches target input shape = C [OK]

Hint: Output shape matches target input shape in decoder [OK]

Common Mistakes:

• Confusing source and target sequence lengths
• Mixing batch size and feature dimensions
• Assuming output shape changes after decoding

4. What is wrong with this PyTorch Transformer decoder usage?

import torch
from torch.nn import TransformerDecoder, TransformerDecoderLayer

layer = TransformerDecoderLayer(d_model=128, nhead=4)
decoder = TransformerDecoder(layer, num_layers=2)

memory = torch.rand(15, 16, 128)
tgt = torch.rand(15, 16, 64)  # Incorrect feature size

output = decoder(tgt, memory)

medium

A. The memory tensor has wrong batch size

B. The target tensor 'tgt' has wrong feature dimension

C. The number of decoder layers is too low

D. The nhead parameter should be equal to batch size

Solution

1. Step 1: Check feature dimensions of inputs

   The decoder expects target and memory tensors to have the same feature dimension (d_model=128).

2. Step 2: Identify mismatch in target tensor

   Target tensor 'tgt' has feature size 64, which does not match d_model=128, causing an error.

3. Final Answer:

   The target tensor 'tgt' has wrong feature dimension -> Option B

4. Quick Check:

   Feature size mismatch in target tensor = A [OK]

Hint: Check if target and memory feature sizes match d_model [OK]

Common Mistakes:

• Ignoring feature dimension mismatch
• Assuming batch size must match nhead
• Thinking number of layers causes this error

5. You want to build a Transformer decoder that generates text step-by-step using previous outputs and encoder memory. Which of the following is the best approach to implement the decoder's forward pass in PyTorch?

hard

A. Use a TransformerDecoder with masked target input to prevent attending to future tokens

B. Use a TransformerDecoder without masking so it sees all target tokens

C. Use only a TransformerEncoder for generation

D. Use a TransformerDecoder but feed the entire output sequence at once without masking

Solution

1. Step 1: Understand the need for masking in decoding

   During generation, the decoder must not look at future tokens to avoid cheating, so masking is required.

2. Step 2: Identify correct usage in PyTorch

   Using TransformerDecoder with a mask on target input prevents attending to future tokens, enabling step-by-step generation.

3. Final Answer:

   Use a TransformerDecoder with masked target input to prevent attending to future tokens -> Option A

4. Quick Check:

   Mask future tokens in decoder input = B [OK]

Hint: Mask future tokens in decoder input for stepwise generation [OK]

Common Mistakes:

• Not using masks and allowing future token attention
• Using encoder only for generation
• Feeding full output sequence without masking