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.