tensorflow evaluate()中的损失是什么？是MAE吗？MSE？如何将结果与其他回归进行比较？

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# 创建一个简单的模型
model = Sequential([
    Dense(64, activation='relu', input_shape=(10,)),
    Dense(1)
])

# 编译模型，指定损失函数为均方误差（MSE）
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mae'])

# 假设你有训练数据和测试数据
import numpy as np
x_train = np.random.rand(100, 10)
y_train = np.random.rand(100, 1)
x_test = np.random.rand(20, 10)
y_test = np.random.rand(20, 1)

# 训练模型
model.fit(x_train, y_train, epochs=10)

# 评估模型
loss, mae = model.evaluate(x_test, y_test)
print(f"Loss (MSE): {loss}")
print(f"Mean Absolute Error (MAE): {mae}")

from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, mean_absolute_error

# 创建并训练线性回归模型
lr_model = LinearRegression()
lr_model.fit(x_train, y_train)

# 预测
y_pred = lr_model.predict(x_test)

# 计算MSE和MAE
mse = mean_squared_error(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)

print(f"Linear Regression MSE: {mse}")
print(f"Linear Regression MAE: {mae}")