ee1e8abd87
* feat(tools): add seed/solution restore script * chore(curriculum): remove empty sections' markers * chore(curriculum): add seed + solution to Chinese * chore: remove old formatter * fix: update getChallenges parse translated challenges separately, without reference to the source * chore(curriculum): add dashedName to English * chore(curriculum): add dashedName to Chinese * refactor: remove unused challenge property 'name' * fix: relax dashedName requirement * fix: stray tag Remove stray `pre` tag from challenge file. Signed-off-by: nhcarrigan <nhcarrigan@gmail.com> Co-authored-by: nhcarrigan <nhcarrigan@gmail.com>
63 lines
1.0 KiB
Markdown
63 lines
1.0 KiB
Markdown
---
|
|
id: 5e8f2f13c4cdbe86b5c72da1
|
|
title: 'Natural Language Processing With RNNs: Building the Model'
|
|
challengeType: 11
|
|
videoId: 32WBFS7lfsw
|
|
dashedName: natural-language-processing-with-rnns-building-the-model
|
|
---
|
|
|
|
# --question--
|
|
|
|
## --text--
|
|
|
|
Fill in the blanks below to complete the `build_model` function:
|
|
|
|
```py
|
|
def build_mode(vocab_size, embedding_dim, rnn_units, batch_size):
|
|
model = tf.keras.Sequential([
|
|
tf.keras.layers.Embedding(vocab_size,
|
|
embedding_dim,
|
|
batch_input_shape=[batch_size, None]),
|
|
tf.keras.layers.__A__(rnn_units,
|
|
return_sequences=__B__,
|
|
recurrent_initializer='glorot_uniform),
|
|
tf.keras.layers.Dense(__C__)
|
|
])
|
|
__D__
|
|
```
|
|
|
|
## --answers--
|
|
|
|
A: `ELU`
|
|
|
|
B: `True`
|
|
|
|
C: `vocab_size`
|
|
|
|
D: `return model`
|
|
|
|
---
|
|
|
|
A: `LSTM`
|
|
|
|
B: `False`
|
|
|
|
C: `batch_size`
|
|
|
|
D: `return model`
|
|
|
|
---
|
|
|
|
A: `LSTM`
|
|
|
|
B: `True`
|
|
|
|
C: `vocab_size`
|
|
|
|
D: `return model`
|
|
|
|
## --video-solution--
|
|
|
|
3
|
|
|