Question

我找到了有关print activation maps的GitHub示例。代码很简单。我所做的就是复制粘贴功能。

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

然后我通过了模型和输入。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

我不确定如何解决此问题。

Answer 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行select * from s.t where h_code = 'KGD78' and h_no = '265'

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

Answer 2

从输出/获取层中排除输入层（这就是为什么错误显示“ fed＆fetch”的原因-无法从输入层（Feed）本身获取输入（Feed）的输出（获取））

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

或通过完全删除图层名称填充；

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

应解决该问题（最后是通知-> [1:]，这是针对您问题的简单解决方法）

InvalidArgumentError：同时输入和获取input_1：0

2 个答案: