如何修复深度学习代码中显示的错误

Question

我正在运行以下代码：

estimator = KerasClassifier(build_fn=baseline_model, epochs=5, batch_size=100, verbose=0)
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)
#results = cross_val_score(estimator, x_train, y_train, cv=kfold, scoring='accuracy', n_jobs=1))

但是，我遇到了一个问题

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-43-2b316c99ac78> in <module>()
      1 estimator = KerasClassifier(build_fn=baseline_model, epochs=5, batch_size=100, verbose=0)
      2 kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=0)
----> 3 results = cross_val_score(estimator, x_train, y_train, cv=kfold, scoring='accuracy')#.fit(x_train, y_train)

    16 frames
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in __call__(self, *args, **kwargs)
       1456         ret = tf_session.TF_SessionRunCallable(self._session._session,
                                                  self._handle, args,                                               run_metadata_ptr)
               if run_metadata:
                 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

    InvalidArgumentError: indices[87,14] = -1 is not in [0, 5000)
         [[{{node embedding_5/embedding_lookup}}]]

此代码在google colab中运行