Inspect the Results
Let’s examine the results to see how the different combinations of fitting and compilation parameters performed.
# Show the best performing models based on accuracy
show_best(tune_res, metric = "accuracy")
#> # A tibble: 5 × 11
#> learn_rate fit_batch_size fit_epochs compile_optimizer compile_loss .metric
#> <dbl> <int> <int> <chr> <chr> <chr>
#> 1 0.01 16 30 adam categorical_cr… accura…
#> 2 0.01 16 30 adam kl_divergence accura…
#> 3 0.01 64 30 adam kl_divergence accura…
#> 4 0.01 64 30 adam categorical_cr… accura…
#> 5 0.01 16 10 adam kl_divergence accura…
#> # ℹ 5 more variables: .estimator <chr>, mean <dbl>, n <int>, std_err <dbl>,
#> # .config <chr>
# Plot the results
autoplot(tune_res) + theme_minimal()
# Select the best hyperparameters
best_params <- select_best(tune_res, metric = "accuracy")
print(best_params)
#> # A tibble: 1 × 6
#> learn_rate fit_batch_size fit_epochs compile_optimizer compile_loss .config
#> <dbl> <int> <int> <chr> <chr> <chr>
#> 1 0.01 16 30 adam categorical_cr… Prepro…The results show that tune has successfully explored
different optimizers, loss functions, learning rates, epochs, and batch
sizes, identifying the combination that yields the best accuracy.