我有一个带有单热编码标签的 CNN 二进制分类器，它是我使用 Keras 编写的，它只是没有训练到我想要鼓励的指标。我的数据非常不平衡（91% 0 类，9% 1 类），无论我做什么，它总是有利于大多数类的准确性。我玩过班级重量。我试过创建平衡的测试和训练文件。我的 CNN 似乎更难在少数类中找到模式，所以它总是返回多数类的改进。我想做的是创建一个自定义损失，允许我定义一个分数，奖励少数类的真阳性 (TP) 并惩罚其假阳性 (FP)。类似于以下内容：

def minority_score(y_true, y_pred):

    max_value_true = K.argmax(y_true, -1)
    max_value_pred = K.argmax(y_pred, -1)

    FP = np.logical_and(K.eval(max_value_pred) == 1, K.eval(max_value_true) == 0)
    TP = np.logical_and(K.eval(max_value_pred) == 1, K.eval(max_value_true) == 1)
    score = (TP *3) - FP # punish each FP with a -1 and reward each TP with a +3
    return score # invert if using as loss function

model = build_model()

model.compile(loss=minority_score,
    optimizer=keras.optimizers.Adam(lr=0.0001),
    metrics=[minority_score, metrics.categorical_accuracy])

我尝试了各种方法，但由于我的标签是单热编码的，我总是在解码它们时遇到问题。y_pred并且y_true是上例中的张量。在该示例中，我收到此错误：

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'conv2d_1_input' with dtype float and shape [?,28,28,1]

这是所有放在一起的相关代码。谢谢你。

def minority_score(y_true, y_pred):

    max_value_true = K.argmax(y_true, -1)
    max_value_pred = K.argmax(y_pred, -1)

    # below line errors out
    FP = np.logical_and(K.eval(max_value_pred) == 1, K.eval(max_value_true) == 0) 
    TP = np.logical_and(K.eval(max_value_pred) == 1, K.eval(max_value_true) == 1)
    score = (TP *3) - FP # punish each FP with a -1 and reward each TP with a +3
    return score 

class Modeler:
    def build_model(self):
        """
        this method only builds the scaffolding
        weights should be set and/or loaded
        outside of it

        """

        model = Sequential()

        # layerset 1
        model.add(Conv2D(
            filters=32,
            kernel_size=[3, 3],
            strides=(1, 1),
            input_shape=(28, 28, 1),
            padding='same'
        ))
        model.add(BatchNormalization())
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
        model.add(Dropout(0.2))
        # layerset 2
        model.add(Conv2D(
            filters=64,
            kernel_size=[3, 3],
            padding='same'
        ))
        model.add(BatchNormalization())
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.2))
        # layerset 3
        model.add(Conv2D(
            filters=128,
            kernel_size=[3, 3],
            padding='same'
        ))
        model.add(BatchNormalization())
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Dropout(0.25))

        model.add(Flatten())
        model.add(Dense(2048, activation='relu'))
        model.add(Dense(self.num_classes, activation='softmax'))

        return model

    def compile_model(self, model, learning_rate):
        model.compile(loss=minority_score,
                      optimizer=keras.optimizers.Adam(lr=learning_rate),
                      metrics=[minority_score, metrics.categorical_accuracy)
        return model

    def one_hot_encode_labels(self, data):

        return keras.utils.to_categorical(data, self.num_classes)

modeler = modeler.build_model()
model = modeler.compile_model()

# load model weights from checkpoint here
# load and shape data here
# create class weight dictionary here

model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=num_epochs,
          verbose=1,
          validation_data=(x_test, y_test),
          callbacks=callbacks_list,
          class_weight=weight_dict)


```