我刚为初学者完成了TensorFlow MNIST tutorial。我在Python 3上运行Jupyter中的最新版本的TensorFlow（本地安装）。
我的代码如下，基本上从教程中逐字逐句：
---------------------------------------------------------------------------
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"]()]]
我认为问题可能在于python3。所以，我尝试在python 2.7版本的张量流中运行相同的代码。没有改变。
$tablet: new-breakpoint(min-width $mq-m max-width 959px 12);
有人能告诉我我做错了什么吗？我认为在本教程中修复错误会很有用。
解决！非常愚蠢的错误。在最后一行，当我需要写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。
答案 0 :(得分：1)
产生此错误的原因在于代码的这一行中的类型：
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})
您尝试将一批100个标签送入一个varibale，其设计用于保存单个值。
y 是您在此处实施的模型的输出：
y = tf.nn.softmax(tf.matmul(x,W)+b)
虽然 y _ 代表尺寸[100,10]的张量，但您首先为其创建了占位符变量。对于每次训练迭代，您将加载一批100个示例，这些示例将被提供给会话：
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})
我想您的混淆是因为session.run()期间必须将batch_x分配给x，而batch_y则会y_。原因是训练图像（ x ）来自MNIST数据集，正确的标签（ y _ ）也是如此，而模型输出/预测（ y ）由卷积神经网络计算。
您使用一批输入图像提供会话。您的模型会对此图像所属的类别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。最后一步是在代码的以下行中执行的：
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y)
正如您所看到的，交叉熵函数是通过传递来自您的数据集和预测的正确标签来调用的，这些标签是在飞行中计算出来的。按你的模特。这就是 y _ 必须在会话运行期间传递数据的原因，而对 y 执行相同的操作并不是必需的。