ggmlR (version 0.6.1)

ggml_compile.ggml_functional_model: Compile a Sequential Model

Description

Configures the model for training: infers shapes, creates backend. Weight tensors are created at training time when batch_size is known.

Usage

# S3 method for ggml_functional_model
ggml_compile(
  model,
  optimizer = "adam",
  loss = "categorical_crossentropy",
  metrics = c("accuracy"),
  backend = "auto"
)
ggml_compile(
  model,
  optimizer = "adam",
  loss = "categorical_crossentropy",
  metrics = c("accuracy"),
  backend = "auto"
)
# S3 method for ggml_sequential_model
ggml_compile(
  model,
  optimizer = "adam",
  loss = "categorical_crossentropy",
  metrics = c("accuracy"),
  backend = "auto"
)

Value

The compiled model (invisibly).

Arguments

model

A ggml_sequential_model object

optimizer

Optimizer name: "adam" or "sgd"

loss

Loss function name: "categorical_crossentropy" or "mse"

metrics

Character vector of metrics (currently "accuracy")

backend

Backend to use: "auto" (GPU if available, else CPU), "cpu", or "vulkan"

Examples

# \donttest{
model <- ggml_model_sequential() |>
  ggml_layer_conv_2d(32, c(3,3), activation = "relu",
                     input_shape = c(28, 28, 1)) |>
  ggml_layer_max_pooling_2d(c(2, 2)) |>
  ggml_layer_flatten() |>
  ggml_layer_dense(10, activation = "softmax")
model <- ggml_compile(model, optimizer = "adam",
                      loss = "categorical_crossentropy")
# }