InvalidArgumentError：您必须为占位符张量'Placeholder_1'输入一个值

Question

我在MNIST数据集上用TensorFlow训练了一个简单的神经网络。代码的训练部分工作正常。但是，当我将单个图像馈送到网络中时，它会给我以下回溯：

Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1021, in _do_call
    return fn(*args)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1003, in _run_fn
    status, run_metadata)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py", line 88, in __exit__
    next(self.gen)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder_1' with dtype float
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "tfbasics.py", line 113, in <module>
    classification = sess.run(y, feed_dict)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 766, in run
    run_metadata_ptr)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 964, in _run
    feed_dict_string, options, run_metadata)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1014, in _do_run
    target_list, options, run_metadata)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1034, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder_1' with dtype float
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'Placeholder_1', defined at:
  File "tfbasics.py", line 20, in <module>
    y = tf.placeholder('float') #labels
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1587, in placeholder
    name=name)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2043, 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 759, 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 2240, 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 1128, in __init__
    self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder_1' with dtype float
     [[Node: Placeholder_1 = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

这是我的变量：

x = tf.placeholder('float', shape = [None, 784]) 
y = tf.placeholder('float') #labels

这是我尝试输入单个数字(从数据集中随机选择(的地方：

#pick random number
num = randint(0, mnist.test.images.shape[0])
img = mnist.test.images[num]
#format the image
inp = np.asarray(img)
inp = np.transpose(inp)
image = np.expand_dims(inp, axis=0) # shape  : (1, 784)

#feed the image into the session
with tf.Session() as sess:
    feed_dict = {x: image}
    classification = sess.run(y, feed_dict)
    print(classification)

任何帮助将不胜感激！我是TensorFlow的新手。

Answer 1

您的feed_dict只为 x 放置值，而不为标签放置值。 您还应该输入 y place_holder，即：{x：image， y：val}

Answer 2

在你的代码中，y是一个占位符：

x = tf.placeholder('float', shape = [None, 784]) 
y = tf.placeholder('float') #labels

当你告诉 tensorflow sess.run(y, ...) 时，它计算的是占位符值，而不是推理值(这是在损失函数中与y进行比较的张量(。这就是它抱怨的原因。

您要计算的是预测的y值。它不在你的代码片段中，但由于训练有效，应该有一个。这个张量依赖于x，所以它可以通过输入x值来评估。

Answer 3

如果在输入正确的 numpy 形状并按照错误消息的建议维护正确的 dtypes(np.int32 或 np.float32(后仍然遇到相同的错误，则以下代码应该可以解决您的问题：

#this code will print the list of placeholders and other variables declared in the memory which is causing your error
[n.name for n in tf.get_default_graph().as_graph_def().node] 
#it will reset your declared placeholders so you can start over
tf.reset_default_graph()

这个类似的问题可以通过为每个调试重复重新启动内核来解决，但这是不可行的。