如何使用tensorflow feature_列作为keras模型的输入

Tensorflow对于非数值特征处理非常有用。然而，当前的API文档更多地是关于使用tensorflow估计器的feature_列。是否有可能使用feature_列进行分类特征表示，然后基于tf.keras构建模型

我找到的唯一参考是下面的教程。它显示了如何将要素列馈送到Keras顺序模型：

代码片段如下所示：

from tensorflow.python.feature_column import feature_column_v2 as fc

feature_columns = [fc.embedding_column(ccv, dimension=3), ...]
feature_layer = fc.FeatureLayer(feature_columns)
model = tf.keras.Sequential([
    feature_layer,
    tf.keras.layers.Dense(128, activation=tf.nn.relu),
    tf.keras.layers.Dense(64, activation=tf.nn.relu),
    tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)
])
...
model.fit(dataset, steps_per_epoch=8) # dataset is created from tensorflow Dataset API

问题是如何使用带有keras功能模型API的定制模型。我尝试了以下方法，但没有成功（tensorflow 1.12版）

错误日志：

ValueError: Input tensors to a Model must come from `tf.layers.Input`. Received: Tensor("feature_layer/concat:0", shape=(4, 3), dtype=float32) (missing previous layer metadata).

我不知道如何将特征列转换为keras模型的输入。

使用此函数，此api文档有一个示例。

---

您可以将featur_列转换为Tensor，然后将其用于Mode（）

我最近在TensorFlow 2.0 alpha版本中阅读过。它有使用Keras和featurecolumnapi的例子。不确定TF2.0是否是您将要使用的

如果您使用tensorflow数据集API，该代码可能会很好

featurlayer = keras.layers.DenseFeatures(feature_columns=feature_columns)
train_dataset = train_dataset.map(lambda x, y: (featurlayer(x), y))
test_dataset = test_dataset.map(lambda x, y: (featurlayer(x), y))

model.fit(train_dataset, epochs=, steps_per_epoch=, # all_data/batch_num = 
     validation_data=test_dataset,
     validation_steps=)

---

您想要的行为可以实现，并且它能够将

tf.feature\u column

和

keras函数API

结合起来。事实上，TF文档中没有提到

这至少在TF2.0.0-beta1中起作用，但在以后的版本中可能会被更改甚至简化

请检查TensorFlow github存储库中的问题。在那里，您可以找到有关

tf.feature\u列

和

Keras函数API

的有用注释

因为您询问一般方法，所以我将从上面的链接复制带有示例的代码段更新：下面的代码应该可以工作

from __future__ import absolute_import, division, print_function

import numpy as np
import pandas as pd

#!pip install tensorflow==2.0.0-alpha0
import tensorflow as tf

from tensorflow import feature_column
from tensorflow import keras
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split

csv_file = tf.keras.utils.get_file('heart.csv', 'https://storage.googleapis.com/download.tensorflow.org/data/heart.csv')
dataframe = pd.read_csv(csv_file, nrows = 10000)
dataframe.head()

train, test = train_test_split(dataframe, test_size=0.2)
train, val = train_test_split(train, test_size=0.2)
print(len(train), 'train examples')
print(len(val), 'validation examples')
print(len(test), 'test examples')

# Define method to create tf.data dataset from Pandas Dataframe
# This worked with tf 2.0 but does not work with tf 2.2
def df_to_dataset_tf_2_0(dataframe, label_column, shuffle=True, batch_size=32):
    dataframe = dataframe.copy()
    #labels = dataframe.pop(label_column)
    labels = dataframe[label_column]

    ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
    if shuffle:
        ds = ds.shuffle(buffer_size=len(dataframe))
    ds = ds.batch(batch_size)
    return ds

def df_to_dataset(dataframe, label_column, shuffle=True, batch_size=32):
    dataframe = dataframe.copy()
    labels = dataframe.pop(label_column)
    #labels = dataframe[label_column]

    ds = tf.data.Dataset.from_tensor_slices((dataframe.to_dict(orient='list'), labels))
    if shuffle:
        ds = ds.shuffle(buffer_size=len(dataframe))
    ds = ds.batch(batch_size)
    return ds


batch_size = 5 # A small batch sized is used for demonstration purposes
train_ds = df_to_dataset(train, label_column = 'target', batch_size=batch_size)
val_ds = df_to_dataset(val,label_column = 'target',  shuffle=False, batch_size=batch_size)
test_ds = df_to_dataset(test, label_column = 'target', shuffle=False, batch_size=batch_size)

age = feature_column.numeric_column("age")

feature_columns = []
feature_layer_inputs = {}

# numeric cols
for header in ['age', 'trestbps', 'chol', 'thalach', 'oldpeak', 'slope', 'ca']:
  feature_columns.append(feature_column.numeric_column(header))
  feature_layer_inputs[header] = tf.keras.Input(shape=(1,), name=header)

# bucketized cols
age_buckets = feature_column.bucketized_column(age, boundaries=[18, 25, 30, 35])
feature_columns.append(age_buckets)

# indicator cols
thal = feature_column.categorical_column_with_vocabulary_list(
      'thal', ['fixed', 'normal', 'reversible'])
thal_one_hot = feature_column.indicator_column(thal)
feature_columns.append(thal_one_hot)
feature_layer_inputs['thal'] = tf.keras.Input(shape=(1,), name='thal', dtype=tf.string)

# embedding cols
thal_embedding = feature_column.embedding_column(thal, dimension=8)
feature_columns.append(thal_embedding)

# crossed cols
crossed_feature = feature_column.crossed_column([age_buckets, thal], hash_bucket_size=1000)
crossed_feature = feature_column.indicator_column(crossed_feature)
feature_columns.append(crossed_feature)



feature_layer = tf.keras.layers.DenseFeatures(feature_columns)
feature_layer_outputs = feature_layer(feature_layer_inputs)

x = layers.Dense(128, activation='relu')(feature_layer_outputs)
x = layers.Dense(64, activation='relu')(x)

baggage_pred = layers.Dense(1, activation='sigmoid')(x)

model = keras.Model(inputs=[v for v in feature_layer_inputs.values()], outputs=baggage_pred)

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

model.fit(train_ds)

---

这是正确的答案，我在TF1.13下测试了它。它应该获得更多的选票。但是您需要使用tensorflow.python.feature\u column import feature\u column\u v2中的

，作为fc dense\u features=fc.DenseFeatures（columns）

现在应该可以使用了。诀窍是将输入设置为输入层列表，如下所示[feature_layer_Inputs.values（）]中的v代表v。谢谢！我曾试图将

DenseFeatures

预先添加到一个现有的

Sequential

模型中，但最终它只能在功能性

模型中使用这两种方法，并且
inputs=feature\u layer\u inputs
。为什么这一行的输入形状=1:
feature\u layer\u inputs['thal']=tf.keras.Input（shape=（1，），name='thal'，dtype=tf.string）
@HARSHNILESHPATHAK，“thal”列的示例说明了
字符串
值的预处理。这意味着输入数据集的每个记录在'thal'列中只包含一个字符串值，这就是为什么我们要求
tf.keras.input（）
使用shape=（1，）。然后输入层将该字符串值传递给
DenseFeatures（feature\u columns）
层中定义的feature\u列。每个特征列根据其自身的逻辑扩展形状。与“thal”一样，这里显示的
thal\u-one\u-hot
和
thal\u-embedding
@prog\u-guy，不，
thal\u-one\u-hot
和
thal\u-embedding
只是将不同类型的
功能列的示例分开
from __future__ import absolute_import, division, print_function

import numpy as np
import pandas as pd

#!pip install tensorflow==2.0.0-alpha0
import tensorflow as tf

from tensorflow import feature_column
from tensorflow import keras
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split

csv_file = tf.keras.utils.get_file('heart.csv', 'https://storage.googleapis.com/download.tensorflow.org/data/heart.csv')
dataframe = pd.read_csv(csv_file, nrows = 10000)
dataframe.head()

train, test = train_test_split(dataframe, test_size=0.2)
train, val = train_test_split(train, test_size=0.2)
print(len(train), 'train examples')
print(len(val), 'validation examples')
print(len(test), 'test examples')

# Define method to create tf.data dataset from Pandas Dataframe
# This worked with tf 2.0 but does not work with tf 2.2
def df_to_dataset_tf_2_0(dataframe, label_column, shuffle=True, batch_size=32):
    dataframe = dataframe.copy()
    #labels = dataframe.pop(label_column)
    labels = dataframe[label_column]

    ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
    if shuffle:
        ds = ds.shuffle(buffer_size=len(dataframe))
    ds = ds.batch(batch_size)
    return ds

def df_to_dataset(dataframe, label_column, shuffle=True, batch_size=32):
    dataframe = dataframe.copy()
    labels = dataframe.pop(label_column)
    #labels = dataframe[label_column]

    ds = tf.data.Dataset.from_tensor_slices((dataframe.to_dict(orient='list'), labels))
    if shuffle:
        ds = ds.shuffle(buffer_size=len(dataframe))
    ds = ds.batch(batch_size)
    return ds


batch_size = 5 # A small batch sized is used for demonstration purposes
train_ds = df_to_dataset(train, label_column = 'target', batch_size=batch_size)
val_ds = df_to_dataset(val,label_column = 'target',  shuffle=False, batch_size=batch_size)
test_ds = df_to_dataset(test, label_column = 'target', shuffle=False, batch_size=batch_size)

age = feature_column.numeric_column("age")

feature_columns = []
feature_layer_inputs = {}

# numeric cols
for header in ['age', 'trestbps', 'chol', 'thalach', 'oldpeak', 'slope', 'ca']:
  feature_columns.append(feature_column.numeric_column(header))
  feature_layer_inputs[header] = tf.keras.Input(shape=(1,), name=header)

# bucketized cols
age_buckets = feature_column.bucketized_column(age, boundaries=[18, 25, 30, 35])
feature_columns.append(age_buckets)

# indicator cols
thal = feature_column.categorical_column_with_vocabulary_list(
      'thal', ['fixed', 'normal', 'reversible'])
thal_one_hot = feature_column.indicator_column(thal)
feature_columns.append(thal_one_hot)
feature_layer_inputs['thal'] = tf.keras.Input(shape=(1,), name='thal', dtype=tf.string)

# embedding cols
thal_embedding = feature_column.embedding_column(thal, dimension=8)
feature_columns.append(thal_embedding)

# crossed cols
crossed_feature = feature_column.crossed_column([age_buckets, thal], hash_bucket_size=1000)
crossed_feature = feature_column.indicator_column(crossed_feature)
feature_columns.append(crossed_feature)



feature_layer = tf.keras.layers.DenseFeatures(feature_columns)
feature_layer_outputs = feature_layer(feature_layer_inputs)

x = layers.Dense(128, activation='relu')(feature_layer_outputs)
x = layers.Dense(64, activation='relu')(x)

baggage_pred = layers.Dense(1, activation='sigmoid')(x)

model = keras.Model(inputs=[v for v in feature_layer_inputs.values()], outputs=baggage_pred)

model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])

model.fit(train_ds)