函数调用栈：train_function

Question

在训练使用 keras 创建的功能模型时出现以下错误：

File "D:\Age_prediction\testmatrixshape.py", line 34, in <module>

    cnn_lstm.fit(X_train, y_train, batch_size=10, epochs=10)

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\keras\engine\training.py", line 66, in _method_wrapper

    return method(self, *args, **kwargs)

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\keras\engine\training.py", line 848, in fit

    tmp_logs = train_function(iterator)

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\def_function.py", line 580, in __call__

    result = self._call(*args, **kwds)

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\def_function.py", line 644, in _call

    return self._stateless_fn(*args, **kwds)

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 2420, in __call__

    return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 1661, in _filtered_call

    return self._call_flat(

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 1745, in _call_flat

    return self._build_call_outputs(self._inference_function.call(

  File "C:\Users\Pranaswi Reddy\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 593, in call

    outputs = execute.execute(

Answer 1

检查您的所有输入是否不包含任何“字符串”类型的数据。如果是这样改变它们，例如你可以使用 TensorFlow categorical_column_* 函数

Answer 2

在您的代码之前添加此代码from tensorflow.compat.v1 import ConfigProtofrom tensorflow.compat.v1 import InteractiveSessionconfig = ConfigProto()config.gpu_options.allow_growth = Truesession = InteractiveSession(config=config)

Answer 3

当所有 y_train（groundtruth 值）具有相同的值（单个类）时，我遇到了这个错误。当修复它并且 y_train 变成了几个类时，它解决了问题。

Answer 4

我的错误源于具有 Nan 值的标记化输入层。如果您有相同的东西，请使用tf.keras.preprocessing.sequence.pad_sequences或.fillna()

Answer 5

我的问题是我打开了同一程序的另一个外壳。尝试检查双窗口。