luz_metric_accuracy: Accuracy

In mlverse/torchlight: Higher Level 'API' for 'torch'

Accuracy

Description

Computes accuracy for multi-class classification problems.

Usage

luz_metric_accuracy()

Details

This metric expects to take logits or probabilities at every update. It will then take the columnwise argmax and compare to the target.

Value

Returns new luz metric.

See Also

Other luz_metrics: luz_metric_binary_accuracy_with_logits(), luz_metric_binary_accuracy(), luz_metric_binary_auroc(), luz_metric_mae(), luz_metric_mse(), luz_metric_multiclass_auroc(), luz_metric_rmse(), luz_metric()

Examples

if (torch::torch_is_installed()) {
library(torch)
metric <- luz_metric_accuracy()
metric <- metric$new()
metric$update(torch_randn(100, 10), torch::torch_randint(1, 10, size = 100))
metric$compute()
}

mlverse/torchlight documentation built on Sept. 19, 2024, 11:22 p.m.