Sequence-to-sequence basics in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create an embedding layer for the encoder input.

TensorFlow

encoder_embedding = tf.keras.layers.Embedding(input_dim=10000, output_dim=[1])(encoder_inputs)

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

A128

B64

C256

D512

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing too small or too large embedding size without reason.

The embedding layer converts integer input tokens into dense vectors of fixed size. Here, 128 is a common embedding dimension.

2fill in blank

medium

Complete the code to define the encoder LSTM layer with 256 units.

TensorFlow

encoder_lstm = tf.keras.layers.LSTM([1], return_state=True)

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

A64

B256

C512

D128

Attempts:

3 left

💡 Hint

Common Mistakes

Using a number too small to capture sequence complexity.

The encoder LSTM layer uses 256 units to capture sequence information effectively.

3fill in blank

hard

Fix the error in the decoder LSTM call to use the encoder states as initial state.

TensorFlow

decoder_outputs, _, _ = decoder_lstm(decoder_embedding, initial_state=[1])

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

Aencoder_states

Bdecoder_states

Cencoder_outputs

Ddecoder_embedding

Attempts:

3 left

💡 Hint

Common Mistakes

Passing encoder_outputs instead of encoder_states.

The decoder LSTM must start with the encoder's final states to generate correct output sequences.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths only if length is greater than 3.

TensorFlow

word_lengths = {word: [1] for word in words if [2]

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

Alen(word)

Blen(word) > 3

Cword.startswith('a')

Dword.isalpha()

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong condition or value in comprehension.

The dictionary comprehension maps each word to its length only if the length is greater than 3.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps uppercase words to their lengths if length is less than 5.

TensorFlow

result = [1]: [2] for word in words if [3]

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

Aword.upper()

Blen(word)

Clen(word) < 5

Dword.lower()

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up keys and values or wrong condition.

The comprehension maps each word in uppercase to its length only if the length is less than 5.

Practice

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

easy

A. To calculate the loss during training

B. To process the input sequence and create a summary representation

C. To generate the output sequence directly

D. To shuffle the input data randomly

Solution

1. Step 1: Understand the encoder's function

   The encoder reads the input sequence and compresses its information into a fixed-size context vector.

2. Step 2: Differentiate encoder from decoder

   The decoder uses this context vector to generate the output sequence, so the encoder does not generate output directly.

3. Final Answer:

   To process the input sequence and create a summary representation -> Option B

4. Quick Check:

   Encoder = input summary [OK]

Hint: Encoder summarizes input; decoder creates output [OK]

Common Mistakes:

• Confusing encoder with decoder
• Thinking encoder generates output sequence
• Assuming encoder shuffles data

2. Which TensorFlow layer is commonly used to build the encoder and decoder in sequence-to-sequence models?

easy

A. Dense

B. Dropout

C. LSTM

D. Conv2D

Solution

1. Step 1: Identify sequence processing layers

   LSTM layers are designed to handle sequences by remembering information over time steps.

2. Step 2: Exclude other layers

   Dense layers are fully connected but not specialized for sequences; Conv2D is for images; Dropout is for regularization.

3. Final Answer:

   LSTM -> Option C

4. Quick Check:

   LSTM = sequence layer [OK]

Hint: LSTM handles sequences best in TensorFlow [OK]

Common Mistakes:

• Choosing Dense for sequence memory
• Confusing Conv2D with sequence layers
• Using Dropout as main sequence layer

3. What will be the output shape of the decoder LSTM(128, return_sequences=True) layer if the input shape is (batch_size, 10, 64)?

medium

A. (batch_size, 10, 128)

B. (batch_size, 128)

C. (batch_size, 10, 64)

D. (batch_size, 64)

Solution

1. Step 1: Understand LSTM output with return_sequences=True

   When return_sequences=True, LSTM returns output for each time step, so output shape is (batch_size, time_steps, units).

2. Step 2: Match units and input shape

   The LSTM has 128 units and input time steps are 10, output shape is (batch_size, 10, 128).

3. Final Answer:

   (batch_size, 10, 128) -> Option A

4. Quick Check:

   return_sequences=True keeps time steps [OK]

Hint: return_sequences=True keeps time steps in output [OK]

Common Mistakes:

• Ignoring return_sequences effect
• Confusing units with input feature size
• Assuming output shape drops time steps

4. Identify the error in this TensorFlow sequence-to-sequence decoder snippet:

decoder_lstm = tf.keras.layers.LSTM(64, return_sequences=True, return_state=True)
outputs, state_h = decoder_lstm(decoder_inputs, initial_state=encoder_states)

medium

A. initial_state should be None

B. LSTM units should be 128, not 64

C. return_sequences should be False for decoder

D. Missing unpacking of the second state variable

Solution

1. Step 1: Check LSTM return values

   When return_state=True, LSTM returns three outputs: output, state_h, and state_c.

2. Step 2: Verify unpacking variables

   The code unpacks only two variables, missing the cell state (state_c), causing an error.

3. Final Answer:

   Missing unpacking of the second state variable -> Option D

4. Quick Check:

   return_state=True returns 3 outputs [OK]

Hint: return_state=True returns 3 outputs; unpack all [OK]

Common Mistakes:

• Unpacking only two outputs instead of three
• Changing units without reason
• Misusing return_sequences parameter

5. You want to build a sequence-to-sequence model in TensorFlow to translate sentences. Which approach correctly connects encoder and decoder?

hard

A. Use encoder LSTM to get states, then pass these states as initial_state to decoder LSTM

B. Feed decoder inputs directly to encoder without states

C. Use two separate LSTMs without sharing states or outputs

D. Only use Dense layers for both encoder and decoder

Solution

1. Step 1: Understand encoder-decoder connection

   The encoder processes input and produces states that summarize the input sequence.

2. Step 2: Use encoder states to initialize decoder

   Passing encoder states as initial_state to decoder LSTM allows the decoder to start generating output based on input context.

3. Final Answer:

   Use encoder LSTM to get states, then pass these states as initial_state to decoder LSTM -> Option A

4. Quick Check:

   Encoder states initialize decoder [OK]

Hint: Pass encoder states to decoder initial_state [OK]

Common Mistakes:

• Ignoring encoder states in decoder
• Feeding decoder inputs to encoder
• Using only Dense layers for sequences