범주형 임베딩
Keras로 배우는 Advanced Deep Learning
Zach Deane Mayer
Data Scientist
범주형 임베딩
- 입력: 정수
- 출력: 부동소수점
- 참고: 차원 증가 — 출력 레이어에서 2D로 평탄화
입력
input_tensor = Input(shape=(1,))
임베딩 레이어
from tensorflow.keras.layers import Embedding
input_tensor = Input(shape=(1,))
n_teams = 10887
embed_layer = Embedding(input_dim=n_teams,
input_length=1,
output_dim=1,
name='Team-Strength-Lookup')
embed_tensor = embed_layer(input_tensor)
평탄화
from tensorflow.keras.layers import Flatten
flatten_tensor = Flatten()(embed_tensor)
전체 통합
input_tensor = Input(shape=(1,))
n_teams = 10887
embed_layer = Embedding(input_dim=n_teams,
input_length=1,
output_dim=1,
name='Team-Strength-Lookup')
embed_tensor = embed_layer(input_tensor)
flatten_tensor = Flatten()(embed_tensor)
model = Model(input_tensor, flatten_tensor)
