类别嵌入

使用 Keras 的高级深度学习

Zach Deane Mayer

Data Scientist

类别嵌入

输入：整数
输出：浮点数
注意：维度升高；输出层再展平回 2D

输入

input_tensor = Input(shape=(1,))

Embedding 层

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)

展平

from tensorflow.keras.layers import Flatten
flatten_tensor = Flatten()(embed_tensor)

整合到一起

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)

让我们来练习！

使用 Keras 的高级深度学习