机器学习基本过程（之二）

使用 Estimator 构建模型 

 

1. 定义模型

   classifier = tf.estimator.Estimator(
       model_fn=my_model,
       params={
           '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,
       })

编写模型函数my_model.

def my_model(features, labels, mode, params):
    """DNN with three hidden layers and learning_rate=0.1."""
    # Create three fully connected layers.
    net = tf.feature_column.input_layer(features, params['feature_columns'])
    for units in params['hidden_units']:
        net = tf.layers.dense(net, units=units, activation=tf.nn.relu)

    # Compute logits (1 per class).
    logits = tf.layers.dense(net, params['n_classes'], activation=None)

    # Compute predictions.
    predicted_classes = tf.argmax(logits, 1)
    if mode == tf.estimator.ModeKeys.PREDICT:
        predictions = {
            'class_ids': predicted_classes[:, tf.newaxis],
            'probabilities': tf.nn.softmax(logits),
            'logits': logits,
        }
        return tf.estimator.EstimatorSpec(mode, predictions=predictions)

    # Compute loss.
    loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)

    # Compute evaluation metrics.
    accuracy = tf.metrics.accuracy(labels=labels,
                                   predictions=predicted_classes,
                                   name='acc_op')
    metrics = {'accuracy': accuracy}
    tf.summary.scalar('accuracy', accuracy[1])

    if mode == tf.estimator.ModeKeys.EVAL:
        return tf.estimator.EstimatorSpec(
            mode, loss=loss, eval_metric_ops=metrics)

    # Create training op.
    assert mode == tf.estimator.ModeKeys.TRAIN

    optimizer = tf.train.AdagradOptimizer(learning_rate=0.1)
    train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)

我们要使用的模型函数具有以下调用签名：

def my_model_fn(
   features, # This is batch_features from input_fn
   labels,   # This is batch_labels from input_fn
   mode,     # An instance of tf.estimator.ModeKeys
   params):  # Additional configuration

模型函数在Estimator 调用train,evaluate和predict方法时会被调用。调用时的4个实参值，前两个参数是输入特征和标签，由输入函数传入，model参数区分在那个阶段调用模型函数，如在train时，model的值为tf.estimator.ModeKeys.TRAIN。 params参数值是一个map对象，在构造Estimator 对象时，由构造方法传入，如例子中指定各隐藏曾节点数。

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

    # 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))

    # 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,
                                                labels=None,
        batch_size=args.batch_size))

基本的深度神经网络模型必须定义下列三个部分：

1. 一个输入层

       # Use `input_layer` to apply the feature columns.
       net = tf.feature_column.input_layer(features, params['feature_columns'])
   

2. 一个或多个隐藏层

       # Build the hidden layers, sized according to the 'hidden_units' param.
       for units in params['hidden_units']:
           net = tf.layers.dense(net, units=units, activation=tf.nn.relu)
   

3. 一个输出层

       # Compute logits (1 per class).
       logits = tf.layers.dense(net, params['n_classes'], activation=None)
   

4. 训练模型 

5. 预测