'_OptionalInputPlaceHolder' object has no attribute 'inbound_nodes'

[weilaweila]

model = Seq2Seq(batch_input_shape=(16, 7, 5), hidden_dim=10, output_length=8, output_dim=20, depth=4, peek=True)
AttributeError: '_OptionalInputPlaceHolder' object has no attribute 'inbound_nodes'

[natank1]

Suffered from the same problem

[harvcode]

I get this error even for the Simple RNN demo.

[tinglo]

I got the same problem.

[harvcode]

Confirmed same issue with both Theano and Tensorflow backends.

[harvcode]

When used together with Keras 2.1.0 the issue doesn't occur.

[tskoba]

I found cleverhans-lab/cleverhans#341 may help.

[macgaf]

Pls modify code at line 841~851 in engine.py
inbound_nodes -> _inbound_nodes
Just as below:

    if num == 1:
        optional_input_placeholder = _to_list(_OptionalInputPlaceHolder()._inbound_nodes[0].output_tensors)[0]
        assert self._is_optional_input_placeholder(optional_input_placeholder)
        return optional_input_placeholder
    else:
        y = []
        for _ in range(num):
            optional_input_placeholder = _to_list(_OptionalInputPlaceHolder()._inbound_nodes[0].output_tensors)[0]
            assert self._is_optional_input_placeholder(optional_input_placeholder)
            y.append(optional_input_placeholder)
        return y

[natank1]

Yes I already found it out Thanks!!

…

On Fri, Feb 2, 2018 at 5:39 AM, macgaf ***@***.***> wrote: Pls modify code at line 841~851 in engine.py inbound_nodes -> _inbound_nodes Just as below: if num == 1: optional_input_placeholder = _to_list(_OptionalInputPlaceHolder()._inbound_nodes[0].output_tensors)[0] assert self._is_optional_input_placeholder(optional_input_placeholder) return optional_input_placeholder else: y = [] for _ in range(num): optional_input_placeholder = _to_list(_OptionalInputPlaceHolder()._inbound_nodes[0].output_tensors)[0] assert self._is_optional_input_placeholder(optional_input_placeholder) y.append(optional_input_placeholder) return y — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#91 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AH9tZyfT0d3yB0e53jBKMCDi075_08rYks5tQoN-gaJpZM4RijRT> .

[ETMayberry]

duplicated by #90

[paul-cb]

I made this change but it still doesn't work.

[yasuyukiokubo]

Have you changed correct engine.py?

[deepakkumar1984]

I still get the issue with the modified code:

[cdhx]

there are two engine.py,one is in build/lib, the other is in recurentshop,is this two py the same?
why my engine 841-851 line are like this ,should i change code as you said?
`def get_cell(self, **kwargs):
return RNNCellFromModel(self.model, **kwargs)

def _get_optional_input_placeholder(self, name=None, num=1):
    if name:
        if name not in self._optional_input_placeholders:
            if num > 1:
                self._optional_input_placeholders[name] = [self._get_optional_input_placeholder() for _ in range(num)]
            else:
                self._optional_input_placeholders[name] = self._get_optional_input_placeholder()
        return self._optional_input_placeholders[name]`