Predict through ONNX Runtime on CPU — onnxPredict • PhysioML

Materializes a validated raw ONNX payload only for the current call, disables provider fallback, and reuses the shared prediction formatter.

Usage

onnxPredict(
  model,
  newdata,
  batch_size = 64L,
  type = c("class", "probability", "response", "logit"),
  providers = "CPUExecutionProvider"
)

Arguments

model: A validated physio_onnx_model.
newdata: A compatible physio_torch_dataset.
batch_size: Positive whole-number inference batch size.
type: Exact output type.
providers: Execution provider; currently CPU only.

Value

The same identity-preserving output shapes as predictModel().

Examples

# \donttest{
# `model` is from importONNX(); `newdata` is a matching peDataset() (CPU ORT).
onnxPredict(model, newdata, type = "class")
#> Error: object 'model' not found
# }