ggmlR — Neural Networks for R

install.packages("ggmlR")

sudo apt install libvulkan-dev glslc

install.packages("ggmlR", configure.args = "--with-vulkan")
install.packages("ggmlR", configure.args = "--without-vulkan")

install.packages("ggmlR", configure.args = "--with-simd")

install.packages("ggmlR", configure.args = "--with-vulkan --with-simd")

library(ggmlR)

model <- ggml_model_sequential() |>
  ggml_layer_dense(128L, activation = "relu",    input_shape = 784L) |>
  ggml_layer_dropout(rate = 0.3) |>
  ggml_layer_dense(10L,  activation = "softmax")

model <- ggml_compile(model,
                      optimizer = "adam",
                      loss      = "categorical_crossentropy",
                      metrics   = "accuracy")

model <- ggml_fit(model, x_train, y_train,
                  epochs           = 10L,
                  batch_size       = 32L,
                  validation_split = 0.1,
                  verbose          = 1L)
# Important: always assign the return value back to model —
# ggml_fit() returns the model with updated weights.

plot(model$history)

ggml_evaluate(model, x_test, y_test)
preds <- ggml_predict(model, x_new)

model <- ggml_model_sequential() |>
  ggml_layer_conv_2d(32L, kernel_size = c(3L, 3L), activation = "relu",
                     input_shape = c(28L, 28L, 1L)) |>
  ggml_layer_max_pooling_2d(pool_size = c(2L, 2L)) |>
  ggml_layer_conv_2d(64L, kernel_size = c(3L, 3L), activation = "relu") |>
  ggml_layer_global_average_pooling_2d() |>
  ggml_layer_dense(10L, activation = "softmax")

inp <- ggml_input(shape = 64L)
x   <- inp |> ggml_layer_dense(64L, activation = "relu")
res <- ggml_layer_add(list(inp, x))        # element-wise add
out <- res |> ggml_layer_dense(10L, activation = "softmax")

m <- ggml_model(inputs = inp, outputs = out)
m <- ggml_compile(m, optimizer = "adam", loss = "categorical_crossentropy")
m <- ggml_fit(m, x_train, y_train, epochs = 5L, batch_size = 32L)

inp <- ggml_input(shape = 30L, dtype = "int32", name = "tokens")
emb <- inp |> ggml_layer_embedding(vocab_size = 500L, dim = 32L)

# Branch A: GRU path
proj_a <- emb |>
  ggml_layer_gru(32L, return_sequences = FALSE) |>
  ggml_layer_dense(32L)

# Branch B: flatten + projection
proj_b <- emb |>
  ggml_layer_flatten() |>
  ggml_layer_dense(32L, activation = "relu") |>
  ggml_layer_dense(32L)

# Residual merge
out <- ggml_layer_add(list(proj_a, proj_b)) |>
  ggml_layer_dropout(rate = 0.3) |>
  ggml_layer_dense(2L, activation = "softmax")

m <- ggml_model(inputs = inp, outputs = out)

inp1 <- ggml_input(shape = 20L, name = "timeseries")
inp2 <- ggml_input(shape = 3L,  name = "metadata")

br1 <- inp1 |> ggml_layer_dense(16L, activation = "relu")
br2 <- inp2 |> ggml_layer_dense(8L,  activation = "relu")

out <- ggml_layer_concatenate(list(br1, br2), axis = 0L) |>
  ggml_layer_dense(2L, activation = "softmax")

m <- ggml_model(inputs = list(inp1, inp2), outputs = out)
m <- ggml_compile(m, optimizer = "adam", loss = "categorical_crossentropy")

# Pass x as a list — one matrix per input
m <- ggml_fit(m, x = list(x_ts, x_meta), y = y,
              epochs = 10L, batch_size = 32L)
preds <- ggml_predict(m, list(x_ts, x_meta))

inp    <- ggml_input(shape = 64L)
hidden <- inp    |> ggml_layer_dense(64L, activation = "relu")
out    <- hidden |> ggml_layer_dense(10L, activation = "softmax")

m     <- ggml_model(inputs = inp, outputs = list(hidden, out))
preds <- ggml_predict(m, x)
# preds[[1]] — hidden activations  [n × 64]
# preds[[2]] — class probabilities [n × 10]

residual_block <- function(x, filters, name) {
  main     <- x |> ggml_layer_conv_2d(filters, c(3L, 3L), padding = "same",
                                       name = paste0(name, "_conv"))
  shortcut <- x |> ggml_layer_conv_2d(filters, c(1L, 1L), padding = "same",
                                       name = paste0(name, "_proj"))
  ggml_layer_add(list(main, shortcut), name = paste0(name, "_add"))
}

inp <- ggml_input(shape = c(32L, 32L, 3L))
x   <- inp |> ggml_layer_conv_2d(16L, c(3L, 3L), activation = "relu",
                                  padding = "same")
x   <- residual_block(x, 16L, "res1")
x   <- residual_block(x, 32L, "res2")
out <- x |>
  ggml_layer_global_average_pooling_2d() |>
  ggml_layer_dropout(rate = 0.4) |>
  ggml_layer_dense(3L, activation = "softmax")

m <- ggml_model(inputs = inp, outputs = out)

enc <- ggml_dense(32L, activation = "relu", name = "encoder")

x1 <- ggml_input(shape = 16L, name = "left")
x2 <- ggml_input(shape = 16L, name = "right")

h1 <- ggml_apply(x1, enc)   # identical weights
h2 <- ggml_apply(x2, enc)

out <- ggml_layer_add(list(h1, h2)) |>
  ggml_layer_dense(2L, activation = "softmax")

m <- ggml_model(inputs = list(x1, x2), outputs = out)

library(ggmlR)

# Define parameters
W <- ag_param(matrix(rnorm(4 * 8) * 0.1, 8, 4))
b <- ag_param(matrix(0, 8, 1))

# Forward + backward
with_grad_tape({
  h    <- ag_add(ag_matmul(W, x_batch), b)
  h    <- ag_relu(h)
  loss <- ag_mse_loss(h, y_batch)
})
grads <- backward(loss)

opt <- optimizer_adam(list(W = W, b = b), lr = 1e-3)
opt$step(grads)
opt$zero_grad()

model <- ag_sequential(
  ag_linear(64L, 128L, activation = "relu"),
  ag_batch_norm(128L),
  ag_dropout(0.1),
  ag_linear(128L, 10L)
)

params <- model$parameters()
opt    <- optimizer_adam(params, lr = 1e-3)
sch    <- lr_scheduler_cosine(opt, T_max = 50L, lr_min = 1e-5)

dl <- ag_dataloader(x_train, y_train, batch_size = 32L, shuffle = TRUE)

for (epoch in 1:50) {
  for (batch in dl$epoch()) {
    with_grad_tape({
      out  <- model$forward(batch$x)
      loss <- ag_softmax_cross_entropy_loss(out, batch$y)
    })
    grads <- backward(loss)
    clip_grad_norm(params, grads, max_norm = 1.0)
    opt$step(grads)
    opt$zero_grad()
  }
  sch$step()
}

make_model <- function() {
  W <- ag_param(matrix(rnorm(4 * 2) * 0.1, 2, 4))
  b <- ag_param(matrix(0, 2, 1))
  list(
    forward    = function(x) ag_add(ag_matmul(W, x), b),
    parameters = function() list(W = W, b = b)
  )
}

result <- dp_train(
  make_model  = make_model,
  data        = my_dataset,           # list of samples
  loss_fn     = function(out, tgt) ag_mse_loss(out, tgt),
  forward_fn  = function(model, s) model$forward(s$x),
  target_fn   = function(s) s$y,
  n_gpu       = 2L,                   # number of replicas
  n_iter      = 100L,
  lr          = 1e-3,
  max_norm    = 5.0
)

result$loss_history   # numeric vector, one value per iteration
result$model          # trained replica 0

library(mlr3)
library(ggmlR)

# Classification on iris (GPU auto-detected via backend = "auto")
task <- tsk("iris")

learner <- lrn("classif.ggml",
               epochs     = 50L,
               batch_size = 16L,
               backend    = "auto")      # "auto" | "cpu" | "gpu"
learner$predict_type <- "prob"

learner$train(task)
pred <- learner$predict(task)
pred$score(msr("classif.logloss"))

# Regression with a custom architecture
library(mlr3)
library(ggmlR)

learner <- lrn("regr.ggml", epochs = 100L)
learner$model_fn <- function(task, n_features, n_out, pars) {
  ggml_model_sequential() |>
    ggml_layer_dense(256L, activation = "gelu", input_shape = n_features) |>
    ggml_layer_dropout(0.2) |>
    ggml_layer_dense( 64L, activation = "gelu") |>
    ggml_layer_dense(n_out, activation = "linear")
}

learner$train(tsk("mtcars"))

library(ggmlR)
library(parsnip)

spec <- mlp(
  hidden_units = 64,
  epochs       = 100,
  dropout      = 0.2,
  learn_rate   = 0.001
) |>
  set_engine("ggml",
             batch_size = 32,
             backend    = "auto",   # "auto" | "cpu" | "gpu"
             verbose    = 0) |>
  set_mode("classification")

fit_obj <- fit(spec, Species ~ ., data = iris)
predict(fit_obj, new_data = iris)
predict(fit_obj, new_data = iris, type = "prob")

spec_reg <- mlp(hidden_units = 32, epochs = 200) |>
  set_engine("ggml", batch_size = 8, backend = "gpu") |>
  set_mode("regression")

fit_reg <- fit(spec_reg, mpg ~ ., data = mtcars)
predict(fit_reg, new_data = mtcars)

library(ggmlR)

# 1. Load the model
model <- onnx_load("squeezenet.onnx")
model
#> ONNX Model: torch_jit
#>   Producer: pytorch 2.0.1
#>   IR version: 8 / Opset: 18
#>   Nodes: 66 / Weights: 26

# 2. Check expected inputs
onnx_inputs(model)
#> $x.1
#> [1]   1   3 224 224

# 3. Prepare input data (flat numeric vector, row-major NCHW order)
img <- runif(1 * 3 * 224 * 224)

# 4. Run inference — pass a named list matching input names
result <- onnx_run(model, list(x.1 = img))

# 5. Get predictions
scores <- result[[1]]
cat("Predicted class:", which.max(scores) - 1L, "\n")

# Auto-detect device (Vulkan GPU if available, else CPU)
model <- onnx_load("model.onnx")

# Force CPU
model <- onnx_load("model.onnx", device = "cpu")

# Force Vulkan GPU
model <- onnx_load("model.onnx", device = "vulkan")

model <- onnx_load("bert.onnx",
                    input_shapes = list(
                      input_ids      = c(1L, 128L),
                      attention_mask = c(1L, 128L)
                    ))

# Print overview
model
#> ONNX Model: torch_jit
#>   Nodes: 533 / Weights: 199
#>   Ops: MatMul, Add, LayerNormalization, Softmax, ...

# Detailed metadata
onnx_summary(model)

# Input names and shapes (what to pass to onnx_run)
onnx_inputs(model)

# Backend placement: GPU vs CPU split, scheduler info
onnx_device_info(model)

# Single input model
result <- onnx_run(model, list(x = my_data))

# Multiple inputs
result <- onnx_run(model, list(
  input_ids      = as.numeric(token_ids),
  attention_mask = rep(1, 128)
))

# Result is a named list of output tensors
str(result)
#> List of 1
#>  $ output: num [1:1000] 0.00123 0.00045 ...

# Image classification: model expects [1, 3, 224, 224]
# If you have a 224x224x3 R array:
img_array <- array(runif(224 * 224 * 3), dim = c(224, 224, 3))

# Rearrange to NCHW: [1, 3, 224, 224] — channel first
img_chw <- aperm(img_array, c(3, 1, 2))  # [3, 224, 224]
input <- as.numeric(img_chw)              # flat vector, row-major

result <- onnx_run(model, list(x = input))

# BERT-style: token IDs as numeric vector
tokens <- c(101, 2023, 2003, 1037, 3231, 102, rep(0, 122))  # pad to 128
result <- onnx_run(model, list(input_ids = as.numeric(tokens)))

# Classification: get top-5 predictions
scores <- result[[1]]
top5 <- order(scores, decreasing = TRUE)[1:5]
cat("Top-5 classes:", top5 - 1L, "\n")  # 0-based class indices
cat("Top-5 scores:", scores[top5], "\n")

# Apply softmax if model outputs logits (not probabilities)
probs <- exp(scores) / sum(exp(scores))

model <- onnx_load("classifier.onnx")

for (batch in data_batches) {
  result <- onnx_run(model, list(x = batch))
  # process result...
}

library(ggmlR)

# Load a GGUF file
g <- gguf_load("model.gguf")
g
#> GGUF file: model.gguf
#>   Version:  3
#>   Tensors:  291
#>   Metadata: 24 key-value pairs

# Inspect metadata (architecture, tokenizer, quant info)
meta <- gguf_metadata(g)
meta[["general.architecture"]]

# List all tensor names
gguf_tensor_names(g)

# Get shape and type for a specific tensor
gguf_tensor_info(g, "blk.0.attn_q.weight")
#> $name:  "blk.0.attn_q.weight"
#> $shape: 4096 4096
#> $type:  "Q4_0"

# Extract dequantized weights as R numeric array
w <- gguf_tensor_data(g, "blk.0.attn_q.weight")
dim(w)
#> [1] 4096 4096

# Free when done (also freed by GC)
gguf_free(g)

ggml_save_model(model, "my_model.rds")
model <- ggml_load_model("my_model.rds")

ggml_vulkan_available()   # TRUE if a Vulkan GPU was detected
ggml_vulkan_status()      # device name, memory, capabilities

# Dynamic autograd: switch device at runtime
ag_device("gpu")   # move subsequent ops to GPU (f16 by default)
ag_device("cpu")   # fall back to CPU