Keras损失似乎是错误的-加权总和是错误的

from sklearn.utils import class_weight

# 假设y_train是训练标签
class_weights = class_weight.compute_class_weight('balanced', np.unique(y_train), y_train)
class_weights_dict = dict(enumerate(class_weights))

model.fit(X_train, y_train, class_weight=class_weights_dict)

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

from keras.models import Sequential
from keras.layers import Dense

model = Sequential()
model.add(Dense(64, activation='relu', input_dim=X_train.shape[1]))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

model.compile(optimizer='adam', loss='binary_crossentropy')

def custom_loss(y_true, y_pred):
    loss = K.mean(K.square(y_true - y_pred), axis=-1)
    print("Custom Loss:", loss)
    return loss

model.compile(optimizer='adam', loss=custom_loss)

import numpy as np
from sklearn.utils import class_weight
from sklearn.preprocessing import StandardScaler
from keras.models import Sequential
from keras.layers import Dense
from keras import backend as K

# 假设X_train, y_train是训练数据和标签
X_train = np.random.rand(100, 10)
y_train = np.random.randint(0, 2, (100, 1))

# 数据预处理
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)

# 计算类别权重
class_weights = class_weight.compute_class_weight('balanced', np.unique(y_train), y_train)
class_weights_dict = dict(enumerate(class_weights))

# 构建模型
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=X_train.shape[1]))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# 自定义损失函数
def custom_loss(y_true, y_pred):
    loss = K.mean(K.square(y_true - y_pred), axis=-1)
    print("Custom Loss:", loss)
    return loss

model.compile(optimizer='adam', loss=custom_loss)

# 训练模型
model.fit(X_train, y_train, class_weight=class_weights_dict, epochs=10)