ggmlR (version 0.6.1)

ggml_dense: Create a Dense Layer Object

Description

Returns a reusable layer object for use with ggml_apply(). Applying the same object to multiple tensor nodes shares weights.

Usage

ggml_dense(units, activation = NULL, name = NULL, trainable = TRUE)

Value

A ggml_layer object.

Arguments

units

Number of output units.

activation

Activation function name or NULL.

name

Optional character name.

trainable

Logical; whether weights are updated during training.

Examples

# \donttest{
encoder <- ggml_dense(64L, activation = "relu")
x1 <- ggml_input(shape = 32L)
x2 <- ggml_input(shape = 32L)
out1 <- x1 |> ggml_apply(encoder)
out2 <- x2 |> ggml_apply(encoder)  # shared weights
# }