Tensorflow summery合併錯誤：形狀[-1,784]具有負向尺寸

Question

我想獲得下面的神經網絡的訓練過程的摘要。

import tensorflow as tf 
import numpy as np 

from tensorflow.examples.tutorials.mnist import input_data 

mnist = input_data.read_data_sets(".\MNIST",one_hot=True) 

# Create the model 
def train_and_test(hidden1,hidden2, learning_rate, epochs, batch_size): 

    with tf.name_scope("first_layer"): 
     input_data = tf.placeholder(tf.float32, [batch_size, 784], name = "input") 
     weights1 = tf.Variable(
     tf.random_normal(shape =[784, hidden1],stddev=0.1),name = "weights") 
     bias = tf.Variable(tf.constant(0.0,shape =[hidden1]), name = "bias") 
     activation = tf.nn.relu(
     tf.matmul(input_data, weights1) + bias, name = "relu_act") 
     tf.summary.histogram("first_activation", activation) 

    with tf.name_scope("second_layer"): 
     weights2 = tf.Variable(
     tf.random_normal(shape =[hidden1, hidden2],stddev=0.1), 
     name = "weights") 
     bias2 = tf.Variable(tf.constant(0.0,shape =[hidden2]), name = "bias") 
     activation2 = tf.nn.relu(
     tf.matmul(activation, weights2) + bias2, name = "relu_act") 
     tf.summary.histogram("second_activation", activation2) 

    with tf.name_scope("output_layer"): 
     weights3 = tf.Variable(
      tf.random_normal(shape=[hidden2, 10],stddev=0.5), name = "weights") 
     bias3 = tf.Variable(tf.constant(1.0, shape =[10]), name = "bias") 
     output = tf.add(
     tf.matmul(activation2, weights3, name = "mul"), bias3, name = "output") 
     tf.summary.histogram("output_activation", output) 
    y_ = tf.placeholder(tf.float32, [batch_size, 10]) 

    with tf.name_scope("loss"): 
     cross_entropy = tf.reduce_mean(
     tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=output)) 
     tf.summary.scalar("cross_entropy", cross_entropy) 
    with tf.name_scope("train"): 
     train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy) 

    with tf.name_scope("tests"): 
     correct_prediction = tf.equal(tf.argmax(output, 1), tf.argmax(y_, 1)) 
     accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 

    summary_op = tf.summary.merge_all() 

    sess = tf.InteractiveSession() 
    writer = tf.summary.FileWriter("./data", sess.graph) 
    tf.global_variables_initializer().run() 

    # Train 
    for i in range(epochs): 
     batch_xs, batch_ys = mnist.train.next_batch(batch_size) 
     _, summary = sess.run([train_step,summary_op], feed_dict={input_data: batch_xs, y_: batch_ys}) 
    writer.add_summary(summary) 

    if i % 10 ==0: 
      test_xs, test_ys = mnist.train.next_batch(batch_size) 
      test_accuracy = sess.run(accuracy, feed_dict = {input_data : test_xs, y_ : test_ys}) 
    writer.close() 
    return test_accuracy 

if __name__ =="__main__": 
print(train_and_test(500, 200, 0.001, 10000, 100)) 

我正在用隨機的一批測試數據每10步測試模型。 問題出在總結作家。 for循環中的sess.run（）會引發以下錯誤。

Traceback (most recent call last): 

    File "<ipython-input-18-78c88c8e6471>", line 1, in <module> 
    runfile('C:/Users/Suman 
Nepal/Documents/Projects/MNISTtensorflow/mnist.py', wdir='C:/Users/Suman 
Nepal/Documents/Projects/MNISTtensorflow') 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site- 
packages\spyder\utils\site\sitecustomize.py", line 880, in runfile 
execfile(filename, namespace) 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site- 
packages\spyder\utils\site\sitecustomize.py", line 102, in execfile 
exec(compile(f.read(), filename, 'exec'), namespace) 

    File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 68, in <module> 
    print(train_and_test(500, 200, 0.001, 100, 100)) 

    File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 58, in train_and_test 
    _, summary = sess.run([train_step,summary_op], feed_dict={input_data: batch_xs, y_: batch_ys}) 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 789, in run 
    run_metadata_ptr) 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 997, in _run 
feed_dict_string, options, run_metadata) 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1132, in _do_run 
target_list, options, run_metadata) 

    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _do_call 
raise type(e)(node_def, op, message) 

InvalidArgumentError: Shape [-1,784] has negative dimensions 
[[Node: first_layer_5/input = Placeholder[dtype=DT_FLOAT, shape=[?,784], _device="/job:localhost/replica:0/task:0/cpu:0"]()]] 

Caused by op 'first_layer_5/input', defined at: 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 231, in <module> 
main() 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 227, in main 
kernel.start() 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 477, in start 
ioloop.IOLoop.instance().start() 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start 
super(ZMQIOLoop, self).start() 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start 
handler_func(fd_obj, events) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper 
return fn(*args, **kwargs) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events 
self._handle_recv() 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv 
self._run_callback(callback, msg) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback 
callback(*args, **kwargs) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper 
return fn(*args, **kwargs) 
File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher 
return self.dispatch_shell(stream, msg) 
File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 235, in dispatch_shell 
handler(stream, idents, msg) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request 
user_expressions, allow_stdin) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute 
res = shell.run_cell(code, store_history=store_history, silent=silent) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 533, in run_cell 
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell 
interactivity=interactivity, compiler=compiler, result=result) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2827, in run_ast_nodes 
if self.run_code(code, result): 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code 
exec(code_obj, self.user_global_ns, self.user_ns) 
    File "<ipython-input-8-78c88c8e6471>", line 1, in <module> 
runfile('C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py', wdir='C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow') 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile 
execfile(filename, namespace) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile 
exec(compile(f.read(), filename, 'exec'), namespace) 
    File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 86, in <module> 
    File "C:/Users/Suman Nepal/Documents/Projects/MNISTtensorflow/mnist.py", line 12, in train_and_test 
    input_data = tf.placeholder(tf.float32, [None, 784], name = "input") 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py", line 1530, in placeholder 
return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 1954, in _placeholder 
name=name) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op 
op_def=op_def) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2506, in create_op 
original_op=self._default_original_op, op_def=op_def) 
    File "C:\Users\Suman Nepal\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1269, in __init__ 
self._traceback = _extract_stack() 

InvalidArgumentError (see above for traceback): Shape [-1,784] has negative dimensions 
    [[Node: first_layer_5/input = Placeholder[dtype=DT_FLOAT, shape=[?,784], _device="/job:localhost/replica:0/task:0/cpu:0"]()]] 

如果我刪除了所有摘要編寫者和摘要，模型運行良好。 你能幫我在這裏發現問題嗎？我試圖操縱張量的形狀，但沒有得到。

Answer 1

我也有這個問題。搜索基本共識是檢查代碼中其他位置的問題。

什麼修復它對我來說是我在做一個sess.run(summary_op)沒有餵養我的佔位數據。

Tensorflow對於佔位符似乎有點奇怪，如果您試圖評估獨立於它們的圖形的一部分，他們通常不會介意不餵它們。儘管如此，它的確如此。

Answer 2

從刪除答案的一個評論，從原來的海報：

其實我with tf.Graph() as g下建立一個神經網絡。我刪除了交互式會話並開始會話。它解決了這個問題。

圖表g沒有標記爲默認的曲線圖那樣，因此，會議（tf.InteractiveSession在原始代碼中）將使用另一個圖形代替。

請注意，由於相同的錯誤消息，我偶然發現了這裏。在我的情況下，我不小心像這樣：

input_data = tf.placeholder(tf.float32, shape=(None, 50)) 
input_data = tf.tanh(input_data) 
session.run(..., feed_dict={input_data: ...}) 

即，我沒有提供佔位符。看起來，其他一些張量操作可能會導致這個令人困惑的錯誤，因爲內部未定義的維度表示爲-1。

Answer 3

這可能與InteractiveSession初始化有關。

我在開始時初始化它，然後工作 - 然後初始化會話中的全局變量。

我無法重現舊代碼的錯誤，這使得它不可預知或緩存設置在某處。

import tensorflow as tf 
sess = tf.InteractiveSession() 


from tensorflow.examples.tutorials.mnist import input_data 

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) 

x = tf.placeholder(tf.float32, [None, 784]) 

W = tf.Variable(tf.zeros([784,10])) 

b = tf.Variable(tf.zeros([10])) 

y = tf.nn.softmax(tf.matmul(x, W)+b) 

y_ = tf.placeholder(tf.float32, [None,10]) 



cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1])) 
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(cross_entropy) 
sess.run(tf.global_variables_initializer()) 


for _ in range(1000): 
    batch_xs, batch_ys = mnist.train.next_batch(100) 
    #print batch_xs.shape, batch_ys.shape 
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})