使用 Estimators API 训练模型

Python 中的 TensorFlow 入门

Isaiah Hull

Visiting Associate Professor of Finance, BI Norwegian Business School

什么是 Estimators API？

高层子模块
灵活性较低
强制最佳实践
更快部署
预置模型丰富

此图展示了 Estimators API 的结构及其与更低层 API 的关系。

¹ Image taken from https://www.tensorflow.org/guide/premade_estimators

模型设计与训练

定义特征列
加载并转换数据
定义估计器
训练模型

定义特征列

# Import tensorflow under its standard alias
import tensorflow as tf

# Define a numeric feature column
size = tf.feature_column.numeric_column("size")

# Define a categorical feature column
rooms = tf.feature_column.categorical_column_with_vocabulary_list("rooms",\
["1", "2", "3", "4", "5"])

定义特征列

# Create feature column list
features_list = [size, rooms]

# Define a matrix feature column
features_list = [tf.feature_column.numeric_column('image', shape=(784,))]

加载与转换数据

# Define input data function
def input_fn():
    # Define feature dictionary
    features = {"size": [1340, 1690, 2720], "rooms": [1, 3, 4]}
    # Define labels
    labels = [221900, 538000, 180000]
    return features, labels

定义并训练回归估计器

# Define a deep neural network regression
model0 = tf.estimator.DNNRegressor(feature_columns=feature_list,\
    hidden_units=[10, 6, 6, 3])

# Train the regression model
model0.train(input_fn, steps=20)

定义并训练深度神经网络

# Define a deep neural network classifier
model1 = tf.estimator.DNNClassifier(feature_columns=feature_list,\ 
   hidden_units=[32, 16, 8], n_classes=4)

# Train the classifier
model1.train(input_fn, steps=20)

https://www.tensorflow.org/guide/estimators

Vamos praticar!

Python 中的 TensorFlow 入门