Estimator是tf.estimator.Estimator的派生类。Tensorflow已经提供预置的Estimator，比如LinearRegressor。

若要使用预置的Estimators，需要完成下面的任务：

• 创建1个或多个input函数

• 定义model特征列

• 实例化Estimator，设定特征列和参数

• 通过Estimator调用多个方法

创建input函数

input函数返回下面两种tuple：

• feature：特征列

• label：标签值

def input_evaluation_set():
    features = {'SepalLength': np.array([6.4, 5.0]),
                'SepalWidth':  np.array([2.8, 2.3]),
                'PetalLength': np.array([5.6, 3.3]),
                'PetalWidth':  np.array([2.2, 1.0])}
    labels = np.array([2, 1])
    return features, labels

虽然可以像上面那样创建input函数，但是推荐使用Tensorflow Dataset API。

通过dataset api创建input函数

def train_input_fn(features, labels, batch_size):
    """An input function for training"""
    # Convert the inputs to a Dataset.
    dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))

    # Shuffle, repeat, and batch the examples.
    dataset = dataset.shuffle(1000).repeat().batch(batch_size)

    # Build the Iterator, and return the read end of the pipeline.
    return dataset.make_one_shot_iterator().get_next()

定义特征列

对于Iris来说，4个特征列都是数值型

# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
    my_feature_columns.append(tf.feature_column.numeric_column(key=key))

实例化Estimator

Iris是经典的分类问题，Tensorflow提供众多的分类的Estimator，比如

• tf.estimator.DNNClassifier

• tf.estimator.DNNLinearCombinedClassifier

• tf.estimator.LinearClassifier

现在以tf.estimator.DNNClassifier创建Estimator

# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.DNNClassifier(
    feature_columns=my_feature_columns,
    # Two hidden layers of 10 nodes each.
    hidden_units=[10, 10],
    # The model must choose between 3 classes.
    n_classes=3)

训练，评估，预测

训练模型

# Train the Model.
classifier.train(
    input_fn=lambda:iris_data.train_input_fn(train_x, train_y, args.batch_size),
    steps=args.train_steps)

评估模型

# Evaluate the model.
eval_result = classifier.evaluate(
    input_fn=lambda:iris_data.eval_input_fn(test_x, test_y, args.batch_size))

print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))

预测

# Generate predictions from the model
expected = ['Setosa', 'Versicolor', 'Virginica']
predict_x = {
    'SepalLength': [5.1, 5.9, 6.9],
    'SepalWidth': [3.3, 3.0, 3.1],
    'PetalLength': [1.7, 4.2, 5.4],
    'PetalWidth': [0.5, 1.5, 2.1],
}

predictions = classifier.predict(
    input_fn=lambda:iris_data.eval_input_fn(predict_x,
                                            batch_size=args.batch_size))

predict方法返回Python iterable

for pred_dict, expec in zip(predictions, expected):
    template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')

    class_id = pred_dict['class_ids'][0]
    probability = pred_dict['probabilities'][class_id]

    print(template.format(iris_data.SPECIES[class_id],
                          100 * probability, expec))