python - ValueError : The model is not configured to compute accuracy. 您应该传递 `metrics=["准确度“]` to the ` model.compile()` 方法

Question

我对深度学习非常陌生:我正在 Udemy 上学习深度学习类(class)。一旦我执行我的代码，它会说:

ValueError:模型未配置为计算准确性。您应该将 metrics=["accuracy"] 传递给 model.compile() 方法。

我尝试将“accuracy”更改为“acc”，它不再给我带来错误，但是代码非常快，它只显示了 10 个 epoch，而不是 100。此外，我预计准确度约为 83%，但我是大约 79%。

有人可以帮我吗？

''''

import keras
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

def build_classifier():
    classifier = Sequential()
    classifier.add(Dense(6, kernel_initializer='uniform', activation='relu', input_dim= 11))
    classifier.add(Dense(6, kernel_initializer='uniform', activation='relu'))
    classifier.add(Dense(1, kernel_initializer='uniform', activation='sigmoid'))
    classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
    return classifier

classifier = KerasClassifier(build_fn= build_classifier, batch_size=10 , nb_epoch=100)
accuracies = cross_val_score(estimator = classifier, X = x_train, y = y_train, cv=10, n_jobs=-1)

''''这是我的完整回溯:

''''

accuracies = cross_val_score(estimator = classifier, X = x_train, y = y_train, cv=10, n_jobs=-1, verbose=0)
Traceback (most recent call last):

  File "<ipython-input-138-36c63e93365e>", line 1, in <module>
    accuracies = cross_val_score(estimator = classifier, X = x_train, y = y_train, cv=10, n_jobs=-1, verbose=0)

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\site-packages\sklearn\model_selection\_validation.py", line 389, in cross_val_score
    error_score=error_score)

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\site-packages\sklearn\model_selection\_validation.py", line 235, in cross_validate
    for train, test in cv.split(X, y, groups))

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\site-packages\joblib\parallel.py", line 1017, in __call__
    self.retrieve()

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\site-packages\joblib\parallel.py", line 909, in retrieve
    self._output.extend(job.get(timeout=self.timeout))

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\site-packages\joblib\_parallel_backends.py", line 562, in wrap_future_result
    return future.result(timeout=timeout)

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\concurrent\futures\_base.py", line 435, in result
    return self.__get_result()

  File "C:\ProgramData\Anaconda3\envs\deeplearning\lib\concurrent\futures\_base.py", line 384, in __get_result
    raise self._exception

ValueError: The model is not configured to compute accuracy. You should pass `metrics=["accuracy"]` to the `model.compile()` method.
''''

我也尝试过这个:'

try:

    accuracies = cross_val_score(estimator = classifier, X = x_train, y = y_train, cv=10, n_jobs=-1, verbose=0)
except ValueError as e:
    print ("ValueError:", e)
ValueError: The model is not configured to compute accuracy. You should pass `metrics=["accuracy"]` to the `model.compile()` method.

'

Answer 1

在导入中，您在 keras 和 tf.keras 包之间混合导入，这实际上是不支持的，您应该选择一个并从所选包中进行所有导入。