我在R中为Keras和Tensorflow创建了一个自定义损失函数。为了使我的编码尝试看起来合理，我尝试重新创建MSE，并将其与Keras的内置功能进行比较。在这个完全可重现的示例中，我开发了函数my_mse（）和metric_mse（）：

library(keras)
library(tensorflow)

epochs <- 3

dataset <- dataset_boston_housing()

c(c(train_data, train_targets), c(test_data, test_targets)) %<-% dataset

X_mean <- apply(train_data, 2, mean)
X_std <- apply(train_data, 2, sd)

train_data <- scale(train_data, center = X_mean, scale = X_std)
test_data <- scale(test_data, center = X_mean, scale = X_std)

set_random_seed(1234)

model <- keras_model_sequential() %>%
  layer_dense(units = 64, activation = "relu", kernel_initializer = initializer_he_uniform(),input_shape = dim(train_data)[[2]]) %>%
  layer_dense(units = 64, activation = "relu", kernel_initializer = initializer_he_uniform()) %>%
  layer_dense(units = 1)

my_mse <- function(y_true, y_pred){
  K        <- backend()
  loss <- K$mean(K$square(y_true-y_pred))
  loss
}

metric_mse <- custom_metric("my_mse", function(y_true, y_pred) {
  my_mse(y_true, y_pred)
})

model <- model %>% compile(
  loss = "mse", 
  optimizer = optimizer_adam(lr=0.001),
  metrics = metric_mse)

history <- model %>% fit(
  train_data, train_targets,
  epochs = epochs, batch_size = 2^4,
  validation_split=0.2
)

但是，每个时期的度量和损耗结果总是略有不同，例如"1s 33ms/步长-损耗：490.4459-我的最小错误：484.7218-价值_损失：441.9290-我的最小值：446.8440 ".有没有什么明显的东西我遗漏了？
编辑：如果我把metric_mse（）作为loss，把"mse"作为度量，那么这两个值实际上是一致的!这怎么可能呢？
提前感谢!