evaluate: Evaluate a Model

In ggmlR: 'GGML' Tensor Operations for Machine Learning

Evaluate a Model

Description

Computes loss and metrics on test data. This is the keras-compatible interface; it delegates to ggml_evaluate.

Usage

## S3 method for class 'ggml_sequential_model'
evaluate(x, test_x, test_y, batch_size = 32L, ...)

## S3 method for class 'ggml_functional_model'
evaluate(x, test_x, test_y, batch_size = 32L, ...)

Arguments

x	A trained model object.
test_x	Test data.
test_y	Test labels.
batch_size	Batch size (default 32).
...	Additional arguments passed to ggml_evaluate.

Value

A named list with loss and metric values.

ggmlR documentation built on July 14, 2026, 1:08 a.m.