بناء النماذج التسلسلية

النموذج التسلسلي

library(keras)

# An empty sequential model
model <- keras_model_sequential()
print(model)

# Or specify the input shape upfront
model <- keras_model_sequential(input_shape = c(20))
print(model)

layer_dense() — الطبقة كاملة الاتصال

library(keras)

model <- keras_model_sequential(input_shape = c(30)) |>
  layer_dense(units = 128, activation = 'relu') |>
  layer_dense(units = 64,  activation = 'relu') |>
  layer_dense(units = 1,   activation = 'sigmoid')

# Print architecture
summary(model)

دوال تنشيط طبقة الإخراج

# Binary classification
binary_model <- keras_model_sequential(input_shape = c(20)) |>
  layer_dense(64, activation = 'relu') |>
  layer_dense(1,  activation = 'sigmoid')   # P(class=1)

# Multi-class (10 classes)
multi_model <- keras_model_sequential(input_shape = c(20)) |>
  layer_dense(64,  activation = 'relu') |>
  layer_dense(10,  activation = 'softmax')  # P per class

# Regression
reg_model <- keras_model_sequential(input_shape = c(20)) |>
  layer_dense(64, activation = 'relu') |>
  layer_dense(1,  activation = 'linear')   # raw value

compile() — الخسارة والمُحسِّن والمقاييس

model |> compile(
  loss      = 'binary_crossentropy',
  optimizer = optimizer_adam(learning_rate = 0.001),
  metrics   = c('accuracy')
)

# Check configuration
model$loss
model$optimizer$get_config()

optimizer_adam()

# Adam with default settings
model |> compile(
  optimizer = 'adam',
  loss = 'binary_crossentropy',
  metrics = 'accuracy'
)

# Customised Adam
model |> compile(
  optimizer = optimizer_adam(
    learning_rate = 0.0005,
    beta_1  = 0.9,
    beta_2  = 0.999,
    epsilon = 1e-7
  ),
  loss    = 'binary_crossentropy',
  metrics = 'accuracy'
)

fit() — تدريب النموذج

# Prepare example data
x_train <- matrix(rnorm(1000 * 20), nrow = 1000)
y_train <- sample(c(0, 1), 1000, replace = TRUE)

history <- model |> fit(
  x         = x_train,
  y         = y_train,
  epochs    = 20,
  batch_size = 32,
  validation_split = 0.2,  # reserve 20% for validation
  verbose   = 1
)

plot(history)

تنظيم الطبقات — Dropout

model <- keras_model_sequential(input_shape = c(784)) |>
  layer_dense(512, activation = 'relu') |>
  layer_dropout(rate = 0.4) |>
  layer_dense(256, activation = 'relu') |>
  layer_dropout(rate = 0.3) |>
  layer_dense(10,  activation = 'softmax')

summary(model)

تنظيم الأوزان باستخدام L1 وL2

model <- keras_model_sequential(input_shape = c(100)) |>
  layer_dense(
    units = 64,
    activation = 'relu',
    kernel_regularizer = regularizer_l2(l = 0.01)
  ) |>
  layer_dense(
    units = 32,
    activation = 'relu',
    kernel_regularizer = regularizer_l1_l2(l1 = 1e-4, l2 = 1e-3)
  ) |>
  layer_dense(1, activation = 'sigmoid')

summary(model)

تطبيع الدفعات

model <- keras_model_sequential(input_shape = c(100)) |>
  layer_dense(256, use_bias = FALSE) |>
  layer_batch_normalization() |>
  layer_activation('relu') |>
  layer_dense(128, use_bias = FALSE) |>
  layer_batch_normalization() |>
  layer_activation('relu') |>
  layer_dense(1, activation = 'sigmoid')

summary(model)

evaluate() و predict()

x_test <- matrix(rnorm(200 * 20), nrow = 200)
y_test <- sample(c(0, 1), 200, replace = TRUE)

# Evaluate on test set
test_metrics <- model |> evaluate(x_test, y_test, verbose = 0)
cat('Test Loss:', test_metrics['loss'])
cat('Test Accuracy:', test_metrics['accuracy'])

# Generate predictions
prob_preds <- model |> predict(x_test)
class_preds <- ifelse(prob_preds > 0.5, 1, 0)
table(class_preds, y_test)

حفظ النماذج وتحميلها

# Save in TensorFlow SavedModel format (recommended)
save_model_tf(model, '/tmp/my_dense_model')

# Reload
loaded <- load_model_tf('/tmp/my_dense_model')

# Confirm predictions match
new_preds <- loaded |> predict(x_test)
all.equal(prob_preds, new_preds)  # TRUE

تحقق سريع

مراجعة النماذج التسلسلية

library(keras)

model <- keras_model_sequential(input_shape = c(30)) |>
  layer_dense(128, activation = 'relu') |>
  layer_dropout(0.4) |>
  layer_dense(64, activation = 'relu') |>
  layer_dropout(0.3) |>
  layer_dense(1, activation = 'sigmoid')

model |> compile(
  optimizer = optimizer_adam(0.001),
  loss      = 'binary_crossentropy',
  metrics   = 'accuracy'
)

history <- model |> fit(
  x_train, y_train,
  epochs = 30, batch_size = 64,
  validation_split = 0.2, verbose = 0
)
plot(history)