InvalidArgumentError: input_1:0 已输入和提取

Posted 2023-02-23

【中文标题】InvalidArgumentError: input_1:0 已输入和提取

【英文标题】：InvalidArgumentError: input_1:0 is both fed and fetched

【发布时间】：2019-03-07 11:40:38

【问题描述】：

我在 GitHub 上找到了关于 print activation maps 的示例。代码非常简单。我所做的只是复制粘贴该功能。

def get_activations(model, model_inputs, print_shape_only=False, layer_name=None):
    print('----- activations -----')
    activations = []
    inp = model.input

    model_multi_inputs_cond = True
    if not isinstance(inp, list):
        # only one input! let's wrap it in a list.
        inp = [inp]
        model_multi_inputs_cond = False

    outputs = [layer.output for layer in model.layers if
               layer.name == layer_name or layer_name is None]  # all layer outputs

    funcs = [K.function(inp + [K.learning_phase()], [out]) for out in outputs]  # evaluation functions

    if model_multi_inputs_cond:
        list_inputs = []
        list_inputs.extend(model_inputs)
        list_inputs.append(0.)
    else:
        list_inputs = [model_inputs, 0.]


    print list_inputs
    layer_outputs = [func(list_inputs)[0] for func in funcs]
    for layer_activations in layer_outputs:
        activations.append(layer_activations)
        if print_shape_only:
            print(layer_activations.shape)
        else:
            print(layer_activations)
    return activations

然后我传递了我的模型和输入。但是，它会产生此错误

Traceback (most recent call last):
  File "test_cnn_128.py", line 80, in <module>
    get_activations(model, test_x)
  File "test_cnn_128.py", line 45, in get_activations
    layer_outputs = [func(list_inputs)[0] for func in funcs]
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2666, in __call__
    return self._call(inputs)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2635, in _call
    session)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2587, in _make_callable
    callable_fn = session._make_callable_from_options(callable_opts)
  File "/home/fatima/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1414, in _make_callable_from_options
    return BaseSession._Callable(self, callable_options)
  File "/home/fatima/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1368, in __init__
    session._session, options_ptr, status)
  File "/home/fatima/.local/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 519, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: input_1:0 is both fed and fetched.
Exception tensorflow.python.framework.errors_impl.InvalidArgumentError: InvalidArgumentError() in <bound method _Callable.__del__ of <tensorflow.python.client.session._Callable object at 0x7f44de0cd210>> ignored

我不确定如何解决这个问题。

【问题讨论】：

你用的是什么 tensorflow 版本？

@mnis 版本是 1.10.1

我认为问题可能在于您的第一层是代表输入的Input 层，您试图在同时提供它的同时提取它的值，这是 TensorFlow 不允许的（如果是这种情况，我不确定为什么它在引用的代码中有效，也许它们不是以Input?...) 开头的。在outputs 的定义中，改用outputs = [layer.output for layer in model.layers[1:] if <etc...>]，即获取除第一个以外的所有层输出，看看是否可行并产生所有隐藏层和输出层激活。

还是同样的错误@jdehesa

@NerdGiraffe 这很有趣。也许您可以尝试在循环中生成值，例如for func, layer in zip(funcs, model.layers):，而不是列表理解，并在调用每个func 之前打印layer，所以至少您知道是否可以评估以及失败的地方。

【参考方案1】：

正如我在线程 Keras, How to get the output of each layer? 上发布的那样，解决此问题的方法是替换该行

outputs = [
    layer.output
    for layer in model.layers
    if layer.name == layer_name or layer_name is None
]

与

outputs = [
    layer.output
    for layer in model.layers
    if layer.name == layer_name or layer_name is None
][1:]

...为了跳过输入层。

【参考方案2】：

从您的输出/获取层中排除输入层（这就是错误显示“fed & fetch”的原因 - 无法从输入层（提要）本身获取输入（提要）的输出（获取））

    outputs = [layer.output for layer in model.layers if
               layer.name == layer_name or layer_name is None][1:]

或者完全删除图层名称；

    outputs = [layer.output for layer in model.layers][1:]

应该解决问题（注意 --> [1:] 在最后，这是解决问题的简单方法）