您必须为占位符张量'Placeholder_2'提供一个值，其中dtype为float和shape [？，10]

Question

我不知道为什么会出现这个问题，我已经检查了很多次，我有xs和ys喂feed_dict。那么，这个问题的原因是什么？如何修改代码以解决这些错误？以下是错误日志。

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder_2' with dtype float and shape [?,10]
[[node Placeholder_2 (defined at /home/jiayu/dropout.py:41)  = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]
[[{{node Mean_5/_55}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_271_Mean_5", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

此代码在ubuntu 16.04，tensorflow 1.12.0和python 3.6.8上运行。

from __future__ import print_function
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer

# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)

def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    # here to dropout
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.summary.histogram(layer_name + '/outputs', outputs)
    return outputs

# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1]))  # loss
tf.summary.scalar('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
merged = tf.summary.merge_all()
# summary writer goes in here
train_writer = tf.summary.FileWriter("logs/train", sess.graph)
test_writer = tf.summary.FileWriter("logs/test", sess.graph)

# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
    init = tf.initialize_all_variables()
else:
    init = tf.global_variables_initializer()

sess.run(init)
for i in range(500):
    # here to determine the keeping probability
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
    if i % 50 == 0:
        # record loss
        train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
        test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})
        train_writer.add_summary(train_result, i)
test_writer.add_summary(test_result, i)

正确的结果是张量板中的显示比例。

Answer 1

您不能多次运行该脚本，否则您将创建嵌套图

对于第一次运行，它将运行正常，没有任何错误。但是当您多次运行它时，将创建嵌套计算图。您可以在tensorboard中查看行为，在几次运行之后，计算图将变得越来越大，当您尝试评估更大的图时，额外的占位符根本不会将数据提供给它们并且它们将给出错误。

这是一个简单的解决方案。使用ft.reset_default_graph()并将其放在创建图形的位置之前

tf.reset_default_graph()
# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32, name='prob')
xs = tf.placeholder(tf.float32, [None, 64], name='x_input')  # 8x8
ys = tf.placeholder(tf.float32, [None, 10], name='y_input')
...

一些进一步阅读Remove nodes from graph or reset entire default graph