想象一个计算图。在这样的图中，我们需要一个输入节点来将数据传递到图中，这些节点应该在tensorflow中定义为占位符。

不要把Python想象成一个通用的程序。你可以写一个Python程序，做所有那些在其他答案中通过变量解释的事情，但对于张量流中的计算图，为了将数据输入到图中，你需要将这些点定义为占位符。

示例代码片段:

import numpy as np
import tensorflow as tf

### Model parameters ###
W = tf.Variable([.3], tf.float32)
b = tf.Variable([-.3], tf.float32)

### Model input and output ###
x = tf.placeholder(tf.float32)
linear_model = W * x + b
y = tf.placeholder(tf.float32)

### loss ###
loss = tf.reduce_sum(tf.square(linear_model - y)) # sum of the squares

### optimizer ###
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss)

### training data ###
x_train = [1,2,3,4]
y_train = [0,-1,-2,-3]

### training loop ###
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init) # reset values to wrong
for i in range(1000):
  sess.run(train, {x:x_train, y:y_train})

顾名思义，占位符是稍后提供一个值的承诺。

变量只是训练参数(W(矩阵)，b(偏差)，与您在日常编程中使用的正常变量相同，培训师在每次运行/步骤中更新/修改。

虽然占位符不需要任何初始值，当你创建x和y时，TF不分配任何内存，相反，当你在sesss .run()中使用feed_dict提供占位符时，TensorFlow将为它们分配适当大小的内存(x和y) -这种不受约束的特性允许我们提供任何大小和形状的数据。

简而言之:

Variable -是一个你希望训练器(例如GradientDescentOptimizer)在每一步之后更新的参数。

占位符演示-

a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b  # + provides a shortcut for tf.add(a, b)

执行:

print(sess.run(adder_node, {a: 3, b:4.5}))
print(sess.run(adder_node, {a: [1,3], b: [2, 4]}))

结果是输出

7.5
[ 3.  7.]

在第一种情况下，3和4.5将分别传递给a和b，然后传递给adder_node输出7。在第二种情况下，有一个提要列表，第一步1和2将被添加，接下来的3和4 (a和b)。

相关阅读:

特遣部队。占位符doc。 特遣部队。变量doc。 变量VS占位符。

对于TF V1:

常数是有初始值的，在计算中不会发生变化; 变量具有初值，在计算中可以变化;(对于参数来说很好) 占位符没有初始值，在计算中不会改变。(非常适合像预测实例这样的输入)

对于TF V2，同样，但他们试图隐藏占位符(图形模式不是首选)。

简而言之，使用tf。变量为可训练变量，如权重(W)和偏差(B)为您的模型。

weights = tf.Variable(
    tf.truncated_normal([IMAGE_PIXELS, hidden1_units],
                    stddev=1.0 / math.sqrt(float(IMAGE_PIXELS))), name='weights')

biases = tf.Variable(tf.zeros([hidden1_units]), name='biases')

特遣部队。占位符用于提供实际的训练示例。

images_placeholder = tf.placeholder(tf.float32, shape=(batch_size, IMAGE_PIXELS))
labels_placeholder = tf.placeholder(tf.int32, shape=(batch_size))

这是你在训练中输入训练示例的方式:

for step in xrange(FLAGS.max_steps):
    feed_dict = {
       images_placeholder: images_feed,
       labels_placeholder: labels_feed,
     }
    _, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)

你的助教。变量将被训练(修改)作为这个训练的结果。

详见https://www.tensorflow.org/versions/r0.7/tutorials/mnist/tf/index.html。(例子摘自网页。)

Think of Variable in tensorflow as a normal variables which we use in programming languages. We initialize variables, we can modify it later as well. Whereas placeholder doesn’t require initial value. Placeholder simply allocates block of memory for future use. Later, we can use feed_dict to feed the data into placeholder. By default, placeholder has an unconstrained shape, which allows you to feed tensors of different shapes in a session. You can make constrained shape by passing optional argument -shape, as I have done below.

x = tf.placeholder(tf.float32,(3,4))
y =  x + 2

sess = tf.Session()
print(sess.run(y)) # will cause an error

s = np.random.rand(3,4)
print(sess.run(y, feed_dict={x:s}))

在执行机器学习任务时，大多数时候我们不知道行数，但(让我们假设)我们知道特征或列的数量。在这种情况下，我们可以使用None。

x = tf.placeholder(tf.float32, shape=(None,4))

现在，在运行时，我们可以输入任意4列任意行数的矩阵。

此外，占位符用于输入数据(它们是一种我们用来为模型提供信息的变量)，其中变量是我们随时间训练的权重等参数。

除了其他人的答案，他们在Tensoflow网站上的MNIST教程中也解释得很好:

We describe these interacting operations by manipulating symbolic variables. Let's create one: x = tf.placeholder(tf.float32, [None, 784]), x isn't a specific value. It's a placeholder, a value that we'll input when we ask TensorFlow to run a computation. We want to be able to input any number of MNIST images, each flattened into a 784-dimensional vector. We represent this as a 2-D tensor of floating-point numbers, with a shape [None, 784]. (Here None means that a dimension can be of any length.) We also need the weights and biases for our model. We could imagine treating these like additional inputs, but TensorFlow has an even better way to handle it: Variable. A Variable is a modifiable tensor that lives in TensorFlow's graph of interacting operations. It can be used and even modified by the computation. For machine learning applications, one generally has the model parameters be Variables. W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([10])) We create these Variables by giving tf.Variable the initial value of the Variable: in this case, we initialize both W and b as tensors full of zeros. Since we are going to learn W and b, it doesn't matter very much what they initially are.