无法展平 Keras 模型的输出

Question

我使用 Keras 构建了以下模型，并且正在使用 StratifiedKFold 对其进行训练。训练效果很好，性能很好。现在我正在尝试使用 SHAP 库来解释模型预测。我的日期集形状是 (107012, 67)，下面是我编写的代码，用于对我的数据进行编码、训练和预测。 original_X 是我使用 Pandas 读取数据的变量。我的大部分数据都是分类数据，只有一列包含连续值。

ohe = OneHotEncoder()
mms = MinMaxScaler()

ct = make_column_transformer(
    (ohe, categorical_columns_encode),
    (mms, numerical_columns_encode),
    remainder='passthrough')

ct.fit(original_X.astype(str))
X = ct.transform(original_X.astype(str))
print(X.shape) # Shape of the encoded value (107012, 47726)

recall = Recall(name="recall")
prec = Precision(name="precision")
ba = BinaryAccuracy()

def get_model():
  network = Sequential()
  network.add(Input(shape=X_1.shape))
  network.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
  network.add(Dropout(0.5))
  network.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
  network.add(Dropout(0.5))
  network.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
  # network.add(Flatten())
  network.add(Dense(1, activation='sigmoid'))

  network.compile(loss='binary_crossentropy',
              optimizer=Adam(learning_rate=0.001),
              metrics=[recall, prec, ba])
  return network

classifier = KerasClassifier(build_fn=get_model)
kfold = RepeatedStratifiedKFold(n_splits=3, n_repeats=3, random_state=42)

callback = EarlyStopping(
    monitor='val_recall',
    min_delta=0,
    patience=0,
    verbose=1,
    mode="auto",
    baseline=None,
    restore_best_weights=True
)

epochs_per_fold = []

for train, validation in kfold.split(X_1, y_1):
  X_train, X_validation = X_1[train], X_1[validation]
  y_train, y_validation = y_1[train], y_1[validation]

  # Printing the distribution of classes in the training set
  counter = Counter(y_train)
  print("Number of class distributions of the training set ", counter)
  print("Minority case percentage of the training set ", counter[1] / (counter[0] + counter[1]))
  
  # Training our model and saving the history of the training
  history = classifier.fit(
    x=X_train,
    y=y_train,
    verbose=1,
    epochs=30,
    shuffle=True,
    callbacks=[callback],
    class_weight={0: 1.0, 1: 3.0},
    validation_data=(X_validation, y_validation))

  # predict classes for our validation set in order to manually verify the metrics
  yhat_classes = (classifier.predict(X_validation) > 0.5).astype("int32")

  TP = 0
  FP = 0
  TN = 0
  FN = 0

  # Record our preditions for the confusion matrix for manually verifying our metrics
  for p,t in zip(y_validation, yhat_classes):
    if p == 1 and t == 1:
      TP += 1
    elif p == 0 and t == 1:
      FP += 1
    elif p == 1 and t == 0:
      FN += 1
    elif p == 0 and t == 0:
      TN += 1
  
  print("\n")
  print(" "*16, "T  F")
  print("Positive result ", TP, FP, )
  print("Negative result ", TN, FN, )
  print("\n")

  # Printing the built in classification report of our model
  print(classification_report(y_validation, yhat_classes))

  report_dict = classification_report(y_validation, yhat_classes, output_dict=True)

  # Record the average number of epochs of training
  epochs_per_fold.append(len(history.history['recall']))
  print(yhat_classes)

在这里，我尝试使用 Shap 库中的 DeepExplainer 来查看我的预测。

# we use the first 100 training examples as our background dataset to integrate over
background = X_2[np.random.choice(X_2.shape[0], 100, replace=False)]

explainer = shap.DeepExplainer(get_model(), background)

当代码到达解释器声明时，会抛出以下错误。

Your TensorFlow version is newer than 2.4.0 and so graph support has been removed in eager mode. See PR #1483 for discussion.
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-113-d24b2d1e3b91> in <module>()
----> 1 explainer = shap.DeepExplainer(get_model(), background)

1 frames
/usr/local/lib/python3.7/dist-packages/shap/explainers/_deep/deep_tf.py in __init__(self, model, data, session, learning_phase_flags)
    100         self.model_output = _get_model_output(model)
    101         assert type(self.model_output) != list, "The model output to be explained must be a single tensor!"
--> 102         assert len(self.model_output.shape) < 3, "The model output must be a vector or a single value!"
    103         self.multi_output = True
    104         if len(self.model_output.shape) == 1:

AssertionError: The model output must be a vector or a single value!

我的问题是：

1. 如何在 get_model 函数中展平模型的输出？
2. 有没有更好的方法来解释我对 Shap 的预测？

如果我需要分享这方面的任何额外信息，请告诉我。

Answer 1

在Dense 层之后添加Flatten 层会导致错误。请注意，导致错误的行是，

assert len(self.model_output.shape) < 3, "The model output must be a vector or a single value!"        

考虑到二维输入，Dense 层的输出为( None , units )。所以，如果我们有一个Dense( 32 ) 层并且批量大小设置为 16，那么这样一个层的输出将是一个形状为 ( 16 , 32 ) 的张量。 Flatten 层保留了第 0 轴（即批次维度），因此形状为 ( 16 , 32 ) 的张量可以进一步展平。

另一方面，如果您有一个形状为 ( 16 , 32 , 3 ) 的张量（例如带有 3 个过滤器的 Conv2D 层的输出），那么 Flatten 层的输出将是一个形状为 @987654333 的张量@。

由于您有 2D 输入，只需删除 Flatten 层。如果你是 尝试重塑输出，请改用Reshape 层。