python – TensorFlow“tf.estimator Quickstart”示例不会产生与教程相同的输出

我刚开始用TensorFlow和Python练习.我复制并执行了TensorFlow网站tf.estimator Quickstart页面中的代码：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import urllib

import numpy as np
import tensorflow as tf

# Data sets
IRIS_TRAINING = "iris_training.csv"
IRIS_TRAINING_URL = "http://download.tensorflow.org/data/iris_training.csv"

IRIS_TEST = "iris_test.csv"
IRIS_TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"


def main():
    # If the training and test sets aren't stored locally, download them.
    if not os.path.exists(IRIS_TRAINING):
        raw = urllib.urlopen(IRIS_TRAINING_URL).read()
        with open(IRIS_TRAINING, "w") as f:
            f.write(raw)

    if not os.path.exists(IRIS_TEST):
        raw = urllib.urlopen(IRIS_TEST_URL).read()
        with open(IRIS_TEST, "w") as f:
            f.write(raw)

    # Load datasets.
    training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TRAINING,
        target_dtype=np.int,
        features_dtype=np.float32)
    test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
        filename=IRIS_TEST,
        target_dtype=np.int,
        features_dtype=np.float32)

    # Specify that all features have real-value data
    feature_columns = [tf.feature_column.numeric_column("x", shape=[4])]

    # Build 3 layer DNN with 10, 20, 10 units respectively.
    classifier = tf.estimator.DNNClassifier(feature_columns=feature_columns,
                                            hidden_units=[10, 20, 10],
                                            n_classes=3,
                                            model_dir="/tmp/iris_model")
    # Define the training inputs
    train_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": np.array(training_set.data)},
        y=np.array(training_set.target),
        num_epochs=None,
        shuffle=True)

    # Train model.
    classifier.train(input_fn=train_input_fn, steps=2000)

    # Define the test inputs
    test_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": np.array(test_set.data)},
        y=np.array(test_set.target),
        num_epochs=1,
        shuffle=False)

    # Evaluate accuracy.
    accuracy_score = classifier.evaluate(input_fn=test_input_fn)["accuracy"]

    print("\nTest Accuracy: {0:f}\n".format(accuracy_score))

    # Classify two new flower samples.
    new_samples = np.array(
        [[6.4, 3.2, 4.5, 1.5],
         [5.8, 3.1, 5.0, 1.7]], dtype=np.float32)
    predict_input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"x": new_samples},
        num_epochs=1,
        shuffle=False)

    predictions = list(classifier.predict(input_fn=predict_input_fn))
    predicted_classes = [p["classes"] for p in predictions]

    print(
        "New Samples, Class Predictions:    {}\n"
            .format(predicted_classes))


if __name__ == "__main__":
    main()

根据教程,输出应该是

Test Accuracy: 0.966667

New Samples, Class Predictions: [1 2]

我的问题是我执行源代码给出的输出是

Test Accuracy: 0.966667

New Samples, Class Predictions: [array([b’1′], dtype=object), array([b’1′], dtype=object)]

不幸的是,我对TensorFlow或Python的经验不足以了解问题所在.我可以做的唯一猜测是一些兼容性问题,但我在TensorFlow网站上的tutorial之后安装了Python 3.5 for Windows.

解决方法:

因为这里的predict_classes是一个dtype对象的数组.

您可以尝试使用np.concatenate(predict_classes).astype(np.int)将对象转换为int.