试图校准keras模型

Question

我正在尝试通过 Sklearn 实现 CalibratedClassifierCV 来校准我的 CNN 模型，尝试将其包装为 KerasClassifier 并覆盖预测功能，但没有成功。有人可以说我做错了什么吗？这是模型代码：

def create_model():
    model = Sequential()
    model.add(Conv2D(64, kernel_size=(3,3), activation = 'relu', input_shape=(28, 28 ,1) ))
    model.add(MaxPooling2D(pool_size = (2, 2)))

    model.add(Conv2D(64, kernel_size = (3, 3), activation = 'relu'))
    model.add(MaxPooling2D(pool_size = (2, 2)))

    model.add(Conv2D(64, kernel_size = (3, 3), activation = 'relu'))
    model.add(MaxPooling2D(pool_size = (2, 2)))

    model.add(Flatten())
    model.add(Dense(128, activation = 'relu'))
    model.add(Dropout(0.20))

    model.add(Dense(24, activation = 'softmax'))

    model.compile(loss = keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adam(), metrics=['accuracy'])
    
    return model

这是我在尝试校准它：

model = KerasClassifier(build_fn=create_model,epochs=5, batch_size=128,validation_data=(evalX_cnn, eval_y_cnn))
model.fit(trainX_cnn, train_y_cnn)
model_c = CalibratedClassifierCV(base_estimator=model, cv='prefit')
model_c.fit(valX_cnn, val_y_cnn)

输出：

-------------------------------------------------------
TypeError             Traceback (most recent call last)
<ipython-input-19-3d3ce9ce4fca> in <module>
----> 1 model_c.fit(np.array(valX_cnn), np.array(val_y_cnn))

~\anaconda3\lib\site-packages\sklearn\calibration.py in fit(self, X, y, sample_weight)
    286             pred_method, method_name = _get_prediction_method(base_estimator)
    287             n_classes = len(self.classes_)
--> 288             predictions = _compute_predictions(pred_method, method_name, X, n_classes)
    289 
    290             calibrated_classifier = _fit_calibrator(

~\anaconda3\lib\site-packages\sklearn\calibration.py in _compute_predictions(pred_method, method_name, X, n_classes)
    575         (X.shape[0], 1).
    576     """
--> 577     predictions = pred_method(X=X)
    578 
    579     if method_name == "decision_function":

TypeError: predict_proba() missing 1 required positional argument: 'x'

valX_cnn 和 val_y_cnn 属于 np.array.

类型

甚至试图覆盖该方法：

keras.models.Model.predict_proba = keras.models.Model.predict

Answer 1

问题是因为 KerasClassifier 中的 predict_proba 需要 x 作为输入，而 sklearn 中的 predict_proba 方法接受 X 作为输入参数（注意区别: X 不是 x).

您可以简单地将问题 KerasClassifier 包装到一个新的 class 中以更正 predict_proba 方法。

samples,classes = 100,3

X = np.random.uniform(0,1, (samples,28,28,1))
Y = tf.keras.utils.to_categorical(np.random.randint(0,classes, (samples)))

class MyKerasClassifier(KerasClassifier):
  
  def predict_proba(self, X):
      return self.model.predict(X)

model = MyKerasClassifier(build_fn=create_model, epochs=3, batch_size=128)
model.fit(X, Y)

model_c = CalibratedClassifierCV(base_estimator=model, cv='prefit')
model_c.fit(X, Y)

Answer 2

包装器将被弃用。从 tensorflow>=2.7.0 你可能想使用 scikeras.

pckg 回购>
https://github.com/adriangb/scikeras

代码示例>

from sklearn.datasets import make_classification
from tensorflow import keras

from scikeras.wrappers import KerasClassifier


X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)
y = y.astype(np.int64)

def get_model(hidden_layer_dim, meta):
    # note that meta is a special argument that will be
    # handed a dict containing input metadata
    n_features_in_ = meta["n_features_in_"]
    X_shape_ = meta["X_shape_"]
    n_classes_ = meta["n_classes_"]

    model = keras.models.Sequential()
    model.add(keras.layers.Dense(n_features_in_, input_shape=X_shape_[1:]))
    model.add(keras.layers.Activation("relu"))
    model.add(keras.layers.Dense(hidden_layer_dim))
    model.add(keras.layers.Activation("relu"))
    model.add(keras.layers.Dense(n_classes_))
    model.add(keras.layers.Activation("softmax"))
    return model

clf = KerasClassifier(
    get_model,
    loss="sparse_categorical_crossentropy",
    hidden_layer_dim=100,
)

clf.fit(X, y)
y_proba = clf.predict_proba(X)

试图校准keras模型

trying to callibrate keras model

python

machine-learning

scikit-learn

keras

tensorflow