运行tensorflow教程时负维错误

Question

我刚刚完成了初学者的TensorFlow MNIST教程。我在Python3上运行最新版本的TensorFlow (本地安装)。

我的代码如下，基本上是从教程中逐字摘录的：

import tensorflow as tf
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
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.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y)
sess= tf.InteractiveSession()
init = tf.global_variables_initializer()
sess.run(init)
train_step = tf.train.GradientDescentOptimizer(.05).minimize(cross_entropy)
for i in range(1000):
batch_x,batch_y = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={x:batch_x,y:batch_y})

我想可能是python3的问题。因此，我尝试在python2.7版本的张量流中运行相同的代码。什么都没变。

---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1138     try:
-> 1139       return fn(*args)
   1140     except errors.OpError as e:

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1120                                  feed_dict, fetch_list, target_list,
-> 1121                                  status, run_metadata)
   1122 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py in __exit__(self, type, value, traceback)
     88             try:
---> 89                 next(self.gen)
     90             except StopIteration:

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
    465           compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466           pywrap_tensorflow.TF_GetCode(status))
    467   finally:

InvalidArgumentError: Shape [-1,10] has negative dimensions
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-10-89eb8cf9286c> in <module>()
      1 for _ in range(1000):
      2     batch_x,batch_y = mnist.train.next_batch(100)
----> 3     sess.run(train_step,feed_dict={x:batch_x,y:batch_y})

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    787     try:
    788       result = self._run(None, fetches, feed_dict, options_ptr,
--> 789                          run_metadata_ptr)
    790       if run_metadata:
    791         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
    995     if final_fetches or final_targets:
    996       results = self._do_run(handle, final_targets, final_fetches,
--> 997                              feed_dict_string, options, run_metadata)
    998     else:
    999       results = []

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1130     if handle is None:
   1131       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1132                            target_list, options, run_metadata)
   1133     else:
   1134       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1150         except KeyError:
   1151           pass
-> 1152       raise type(e)(node_def, op, message)
   1153 
   1154   def _extend_graph(self):

InvalidArgumentError: Shape [-1,10] has negative dimensions
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op 'Placeholder_1', defined at:
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 477, in start
    ioloop.IOLoop.instance().start()
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/zmq/eventloop/ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tornado/ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
    handler(stream, idents, msg)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2698, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2802, in run_ast_nodes
    if self.run_code(code, result):
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2862, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-4-c355762e89a9>", line 2, in <module>
    y_ = tf.placeholder(tf.float32,[None,10])
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1530, in placeholder
    return gen_array_ops._placeholder(dtype=dtype, shape=shape, name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 1954, in _placeholder
    name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1269, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Shape [-1,10] has negative dimensions
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[?,10], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

有人能告诉我我做错了什么吗？我认为在本教程中修复这个错误是有用的。

解决了！非常愚蠢的错误。在最后一行中，当我需要编写y_时，我写了y。如果有人能向我解释为什么这个错误会产生错误信息，我会非常高兴的。

Answer 1

产生此错误的原因在于代码行中的类型：

sess.run(train_step,feed_dict={x:batch_x, y:batch_y})

相反，你应该写：

sess.run(train_step,feed_dict={x:batch_x, y_:batch_y})

所发生的情况是，您正在尝试将一批100个标签提供给一个变量，该变量被设计为保存单个值。

y是您在这里实现的模型的输出：

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

y_表示大小为[100,10]的张量，您首先为其创建了一个占位符变量。对于每一次训练迭代，您将加载一批100个示例，这些示例提供给会话：

y_ = tf.placeholder(tf.float32,[None,10])
batch_x,batch_y = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={x:batch_x,y_:batch_y})

我猜想，您的困惑是因为在session.run()期间，必须将batch_x分配给x，而batch_y则在y_中被喂食。原因是训练图像(x)来自MNIST数据集，正确的标签(y_)也来自MNIST，而模型输出/预测(y)是由卷积神经网络计算的。

您使用一批输入图像来填充会话。您的模型对该图像所属的每个图像进行预测，最后将这些预测与正确的标签进行比较。这些步骤的最后一步在代码的下面一行中执行：

cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y)

如您所见，交叉熵函数是通过传递来自数据集的正确标签和由模型计算的“动态”预测来调用的。这就是为什么在会话运行期间必须将数据传递给y_的原因，而不必对y执行同样的操作。