Python3.x 为什么 TensorFlow 的 `tf.data` 包会减慢我的代码速度

我正在学习使用TensorFlow的tf.data API，我发现它大大降低了我的代码速度，以每个历元的时间来衡量.我想，这与它应该做的正好相反.我写了一个简单的线性回归程序来测试它.

Tl;Dr:如果你使用的是整批训练，那么使用tf.data000个训练数据，tf.data个历元的时间会减少大约10倍.如果使用较小的批次，情况会更糟.500个训练数据的情况正好相反.

My question:发生了什么事？我的实现有缺陷吗？我读过的其他资料有tf.data种，速度提高了约30%.

import tensorflow as tf 
import numpy as np
import timeit

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
tf.logging.set_verbosity(tf.logging.ERROR)

n_epochs = 10
input_dimensions_list = [10]

def function_to_approximate(x):
    return np.dot(x, random_covector).astype(np.float32) + np.float32(.01) * np.random.randn(1,1).astype(np.float32)

def regress_without_tfData(n_epochs, input_dimension, training_inputs, training_labels):
    tf.reset_default_graph()
    weights = tf.get_variable("weights", initializer=np.random.randn(input_dimension, 1).astype(np.float32))

    X = tf.placeholder(tf.float32, shape=(None, input_dimension), name='X')
    Y = tf.placeholder(tf.float32, shape=(None, 1), name='Y')
    prediction = tf.matmul(X,weights)
    loss = tf.reduce_mean(tf.square(tf.subtract(prediction, Y)))
    loss_op = tf.train.AdamOptimizer(.01).minimize(loss)

    init = tf.global_variables_initializer()

    with tf.Session() as sess:
        sess.run(init)
        for _ in range(n_epochs):
            sess.run(loss_op, feed_dict={X: training_inputs, Y:training_labels})

def regress_with_tfData(n_epochs, input_dimension, training_inputs, training_labels, batch_size):
    tf.reset_default_graph()
    weights = tf.get_variable("weights", initializer=np.random.randn(input_dimension, 1).astype(np.float32))

    X,Y = data_set.make_one_shot_iterator().get_next()

    prediction = tf.matmul(X, weights)
    loss = tf.reduce_mean(tf.square(tf.subtract(prediction, Y)))
    loss_op = tf.train.AdamOptimizer(.01).minimize(loss)

    init = tf.global_variables_initializer()

    with tf.Session() as sess:
        sess.run(init)
        while True:
            try: 
                sess.run(loss_op)
            except tf.errors.OutOfRangeError:
                break

for input_dimension in input_dimensions_list:
    for data_size in [500, 100000]:

        training_inputs = np.random.randn(data_size, input_dimension).astype(np.float32)
        random_covector = np.random.randint(-5, 5, size=(input_dimension, 1))
        training_labels = function_to_approximate(training_inputs)

        print("Not using tf.data, with data size "
        "{}, input dimension {} and training with "
        "a full batch, it took an average of "
        "{} seconds to run {} epochs.\n".
            format(
                data_size,
                input_dimension,
                timeit.timeit(
                    lambda: regress_without_tfData(
                        n_epochs, input_dimension, 
                        training_inputs, training_labels
                    ), 
                    number=3
                ),
                n_epochs))

for input_dimension in input_dimensions_list:
    for data_size, batch_size in [(500, 50), (500, 500), (100000, 50), (100000, 100000)]:

        training_inputs = np.random.randn(data_size, input_dimension).astype(np.float32)
        random_covector = np.random.randint(-5, 5, size=(input_dimension, 1))
        training_labels = function_to_approximate(training_inputs)

        data_set = tf.data.Dataset.from_tensor_slices((training_inputs, training_labels))
        data_set = data_set.repeat(n_epochs)
        data_set = data_set.batch(batch_size)

        print("Using tf.data, with data size "
        "{}, and input dimension {}, and training with "
        "batch size {}, it took an average of {} seconds "
        "to run {} epochs.\n".
            format(
                data_size,
                input_dimension,
                batch_size,
                timeit.timeit(
                    lambda: regress_with_tfData(
                        n_epochs, input_dimension, 
                        training_inputs, training_labels, 
                        batch_size
                    ),
                    number=3
                )/3,
                n_epochs
            ))

这对我来说是:

不使用tf.数据，数据大小为500，输入维度10和培训

不使用tf.数据，数据大小为100000，输入维度10和

使用tf.数据，数据大小为500，输入维度为10，以及

使用tf.数据，数据大小为500，输入维度为10，以及

使用tf.数据，数据大小为100000，输入维度为10，以及

使用tf.数据，数据大小为100000，输入维度为10，以及

弗雷德·古思指出了一个重要的问题.不过，这对结果影响不大.