每当我在 R 中训练我的模型时，我都会收到以下错误：

model <- keras_model_sequential()

model %>%
  layer_lstm(units=data_dim, input_shape = c(timesteps, data_dim),return_sequences=TRUE, use_bias=TRUE,dropout=0.35,recurrent_dropout=0.35) %>%
  layer_activation("linear") %>%
  layer_lstm(units=data_dim,return_sequences=TRUE, use_bias=TRUE,dropout=0.35,recurrent_dropout=0.35) %>%
  layer_activation("linear") %>%
  layer_lstm(units=5*data_dim,return_sequences=TRUE, use_bias=TRUE,dropout=0.35,recurrent_dropout=0.35) %>%
  layer_activation("linear") %>%
  layer_dense(units=out_dim,activation="linear")

optimizer <- optimizer_rmsprop(lr = 0.01)

model %>% compile(
  loss = "mean_squared_error", 
  optimizer = optimizer
)

model %>% fit(
    train_in, train_out,
    batch_size = batch_size,
    epochs = 1000)

用户警告：与批量更新 (1.533262) 相比，方法 on_batch_end() 速度较慢。检查你的回调。

有人可以解释发生了什么吗？