codes.benchmark.bench_fcts

Functions

compare_MAE(metrics, config)	Compare the MAE of different surrogate models over the course of training.
compare_UQ(all_metrics, config)	Compare the uncertainty quantification (UQ) metrics of different surrogate models.
compare_batchsize(all_metrics, config)	Compare the batch size training errors of different surrogate models.
compare_dynamic_accuracy(metrics, config)	Compare the gradients of different surrogate models.
compare_extrapolation(all_metrics, config)	Compare the extrapolation errors of different surrogate models.
compare_inference_time(metrics, config[, save])	Compare the mean inference time of different surrogate models.
compare_interpolation(all_metrics, config)	Compare the interpolation errors of different surrogate models.
compare_main_losses(metrics, config)	Compare the training and test losses of the main models for different surrogate models.
compare_models(metrics, config)
compare_relative_errors(metrics, config)	Compare the relative errors over time for different surrogate models.
compare_sparse(all_metrics, config)	Compare the sparse training errors of different surrogate models.
evaluate_UQ(model, surr_name, test_loader, ...)	Evaluate the uncertainty quantification (UQ) performance of the surrogate model.
evaluate_accuracy(model, surr_name, ...[, ...])	Evaluate the accuracy of the surrogate model.
evaluate_batchsize(model, surr_name, ...)	Evaluate the performance of the surrogate model with different batch sizes.
evaluate_compute(model, surr_name, ...)	Evaluate the computational resource requirements of the surrogate model.
evaluate_dynamic_accuracy(model, surr_name, ...)	Evaluate the gradients of the surrogate model.
evaluate_extrapolation(model, surr_name, ...)	Evaluate the extrapolation performance of the surrogate model.
evaluate_interpolation(model, surr_name, ...)	Evaluate the interpolation performance of the surrogate model.
evaluate_sparse(model, surr_name, ...)	Evaluate the performance of the surrogate model with sparse training data.
run_benchmark(surr_name, surrogate_class, conf)	Run benchmarks for a given surrogate model.
tabular_comparison(all_metrics, config)	Compare the metrics of different surrogate models in a tabular format.
time_inference(model, surr_name, ...[, n_runs])	Time the inference of the surrogate model.