2020-04-21 11:19:42 -04:00
|
|
|
---
|
|
|
|
id: 5e8f2f13c4cdbe86b5c72d98
|
2020-04-24 05:52:42 -05:00
|
|
|
title: Creating a Convolutional Neural Network
|
2020-04-21 11:19:42 -04:00
|
|
|
challengeType: 11
|
|
|
|
videoId: kfv0K8MtkIc
|
|
|
|
---
|
|
|
|
|
|
|
|
## Description
|
|
|
|
<section id='description'>
|
|
|
|
</section>
|
|
|
|
|
|
|
|
## Tests
|
|
|
|
<section id='tests'>
|
|
|
|
|
|
|
|
```yml
|
|
|
|
question:
|
2020-05-28 22:40:36 +09:00
|
|
|
text: |
|
2020-06-06 18:51:34 +09:00
|
|
|
Fill in the blanks below to complete the architecture for a convolutional neural network:
|
2020-05-28 22:40:36 +09:00
|
|
|
|
|
|
|
```py
|
|
|
|
model = models.__A__()
|
|
|
|
model.add(layers.__B__(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
|
|
|
|
model.add(layers.__C__(2, 2))
|
|
|
|
model.add(layers.__B__(64, (3, 3), activation='relu'))
|
|
|
|
model.add(layers.__C__(2, 2))
|
|
|
|
model.add(layers.__B__(32, (3, 3), activation='relu'))
|
|
|
|
model.add(layers.__C__(2, 2))
|
|
|
|
```
|
|
|
|
|
2020-04-21 11:19:42 -04:00
|
|
|
answers:
|
2020-05-28 22:40:36 +09:00
|
|
|
- |
|
|
|
|
A: `Sequential`
|
|
|
|
|
|
|
|
B: `add`
|
|
|
|
|
|
|
|
C: `Wrapper`
|
|
|
|
- |
|
|
|
|
A: `keras`
|
|
|
|
|
|
|
|
B: `Cropping2D`
|
|
|
|
|
|
|
|
C: `AlphaDropout`
|
|
|
|
- |
|
|
|
|
A: `Sequential`
|
|
|
|
|
|
|
|
B: `Conv2D`
|
|
|
|
|
|
|
|
C: `MaxPooling2D`
|
2020-04-21 11:19:42 -04:00
|
|
|
solution: 3
|
|
|
|
```
|
|
|
|
|
|
|
|
</section>
|
|
|
|
|