การฝึก การตรวจสอบ และการป้องกันการเรียนรู้เกิน

การแบ่งข้อมูลฝึก ตรวจสอบ และทดสอบ

# validation_split = 0.2 reserves last 20% as validation
history <- model |> fit(
  x_train, y_train,
  epochs           = 50,
  batch_size       = 32,
  validation_split = 0.2,
  verbose          = 0
)

# history contains train and val metrics per epoch
names(history$metrics)

ออบเจ็กต์ประวัติการฝึก

# Training loss and accuracy over epochs
head(history$metrics$loss)
head(history$metrics$val_loss)

# Plot training curves
plot(history)

# Or create a custom ggplot
library(ggplot2)
df <- data.frame(
  epoch    = seq_along(history$metrics$loss),
  train    = history$metrics$loss,
  val      = history$metrics$val_loss
)
ggplot(df, aes(epoch)) +
  geom_line(aes(y = train, colour = 'Train')) +
  geom_line(aes(y = val,   colour = 'Validation')) +
  labs(y = 'Loss', title = 'Training Curves')

การตรวจจับการเรียนรู้เกินพอดี

# Overfitting is visible in the history
# Example of overfitting signatures:
cat('Epoch 5  — Train loss: 0.12, Val loss: 0.18\n')
cat('Epoch 10 — Train loss: 0.06, Val loss: 0.21\n')
cat('Epoch 20 — Train loss: 0.02, Val loss: 0.31\n')

# The model should have stopped at epoch 5!
# Strategies: early stopping, dropout, regularisation, more data

callback_early_stopping()

early_stop <- callback_early_stopping(
  monitor              = 'val_loss',
  patience             = 10,        # wait 10 epochs
  restore_best_weights = TRUE       # rollback to best
)

history <- model |> fit(
  x_train, y_train,
  epochs           = 200,
  batch_size       = 32,
  validation_split = 0.2,
  callbacks        = list(early_stop),
  verbose          = 0
)

cat('Stopped at epoch:', length(history$metrics$loss))

callback_reduce_lr_on_plateau()

reduce_lr <- callback_reduce_lr_on_plateau(
  monitor  = 'val_loss',
  factor   = 0.5,    # halve the learning rate
  patience = 5,      # after 5 stagnant epochs
  min_lr   = 1e-6    # floor for learning rate
)

history <- model |> fit(
  x_train, y_train,
  epochs           = 100,
  batch_size       = 64,
  validation_split = 0.2,
  callbacks        = list(early_stop, reduce_lr),
  verbose          = 1
)

callback_model_checkpoint()

checkpoint <- callback_model_checkpoint(
  filepath       = '/tmp/best_model.h5',
  monitor        = 'val_accuracy',
  save_best_only = TRUE,
  mode           = 'max',      # higher accuracy = better
  verbose        = 1
)

history <- model |> fit(
  x_train, y_train,
  epochs           = 100,
  batch_size       = 32,
  validation_split = 0.2,
  callbacks        = list(early_stop, reduce_lr, checkpoint)
)

# Reload best model
best_model <- load_model_hdf5('/tmp/best_model.h5')

validation_data เทียบกับ validation_split

# Manually create a random validation split
set.seed(42)
val_idx  <- sample(nrow(x_train), size = 0.2 * nrow(x_train))
x_val    <- x_train[val_idx, ]
y_val    <- y_train[val_idx, ]
x_tr     <- x_train[-val_idx, ]
y_tr     <- y_train[-val_idx, ]

history <- model |> fit(
  x_tr, y_tr,
  epochs         = 50,
  batch_size     = 32,
  validation_data = list(x_val, y_val),  # explicit val set
  callbacks      = list(early_stop)
)

ผลของขนาดกลุ่มข้อมูล

# Compare training with different batch sizes
for (bs in c(32, 128, 512)) {
  set_weights(model, init_weights)  # reset
  h <- model |> fit(
    x_train, y_train,
    epochs           = 20,
    batch_size       = bs,
    validation_split = 0.2,
    verbose          = 0
  )
  cat('Batch:', bs, '| Val Acc:',
      tail(h$metrics$val_accuracy, 1), '\n')
}

การวอร์มอัปอัตราการเรียนรู้

# Custom learning rate schedule with warmup
lr_schedule <- function(epoch, lr) {
  if (epoch < 5) {
    return(lr * (epoch + 1) / 5)  # warmup
  } else if (epoch < 30) {
    return(lr)                     # constant
  } else {
    return(lr * 0.95)              # decay
  }
}

lr_callback <- callback_learning_rate_scheduler(lr_schedule)

history <- model |> fit(
  x_train, y_train,
  epochs     = 50,
  callbacks  = list(lr_callback, early_stop),
  validation_split = 0.2
)

สรุปการทำให้เป็นปกติ

model <- keras_model_sequential(input_shape = c(784)) |>
  layer_dense(512, use_bias = FALSE,
              kernel_regularizer = regularizer_l2(1e-4)) |>
  layer_batch_normalization() |>
  layer_activation('relu') |>
  layer_dropout(0.4) |>
  layer_dense(256, kernel_regularizer = regularizer_l2(1e-4)) |>
  layer_batch_normalization() |>
  layer_activation('relu') |>
  layer_dropout(0.3) |>
  layer_dense(10, activation = 'softmax')

model |> compile('adam', 'categorical_crossentropy', 'accuracy')

การพล็อตเส้นโค้งการฝึก

# Detailed training curve plot
df <- data.frame(
  epoch = seq_along(history$metrics$loss),
  train_loss = history$metrics$loss,
  val_loss   = history$metrics$val_loss,
  train_acc  = history$metrics$accuracy,
  val_acc    = history$metrics$val_accuracy
)

par(mfrow = c(1, 2))
plot(df$epoch, df$train_loss, type = 'l', col = 'blue',
     xlab = 'Epoch', ylab = 'Loss', main = 'Loss')
lines(df$epoch, df$val_loss, col = 'red')
legend('topright', c('Train', 'Val'), col = c('blue','red'), lty=1)

plot(df$epoch, df$train_acc, type = 'l', col = 'blue',
     xlab = 'Epoch', ylab = 'Accuracy', main = 'Accuracy')
lines(df$epoch, df$val_acc, col = 'red')

ตรวจสอบความเข้าใจอย่างรวดเร็ว

ทบทวนการฝึกและการเรียนรู้เกินพอดี

# Best practice training setup
callbacks <- list(
  callback_early_stopping(
    monitor = 'val_loss', patience = 15,
    restore_best_weights = TRUE
  ),
  callback_reduce_lr_on_plateau(
    monitor = 'val_loss', factor = 0.5, patience = 5
  ),
  callback_model_checkpoint(
    '/tmp/best.h5', monitor = 'val_accuracy',
    save_best_only = TRUE
  )
)

model |> fit(
  x_train, y_train,
  epochs = 200, batch_size = 64,
  validation_split = 0.2,
  callbacks = callbacks, verbose = 0
)