r - R-Keras - 为什么 val_loss 没有绘图

Question

我第一次玩 Keras。我尝试运行模型并查看损失和准确性。出于某种原因，它没有为val_loss.

我的代码：

model <- keras_model_sequential() %>% 
  layer_dense(units = 256, activation = "relu", input_shape = dim(train.X)[[2]]) %>% 
  layer_dropout(rate = 0.4) %>% 
  layer_dense(units = 128, activation = "relu") %>%
  layer_dropout(rate = 0.3) %>% 
  layer_dense(units = 1, activation = "sigmoid")


model %>% compile (
  optimizer = "rmsprop", #configuring optimizer = optimizer_rmsprop(lr = 0.001)
  loss = "binary_crossentropy", #custom loss -> loss_binary_crossentropy
  metrics = c("accuracy") #metric_binary_accuracy
) 

history <- model %>% fit(
  train.X,
  train.Y,
  epochs = 100,
  batch_size = 64,
  validation_data = list(x_val, y_val)
)

我的结果：

如果有人能向我解释为什么 val_loss 函数没有绘图，我将不胜感激。

标签： rmachine-learningkeras