From 4f4981c864cb58de4650ca0ca559e9165a4f3684 Mon Sep 17 00:00:00 2001 From: Leandro Soares <98189939+SoaresLMB@users.noreply.github.com> Date: Thu, 11 Jul 2024 14:54:09 -0300 Subject: [PATCH] Add files via upload --- builders/data_training_generators.py | 9 ++++++--- builders/model_builders.py | 2 +- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/builders/data_training_generators.py b/builders/data_training_generators.py index 321abc534..1742fbd5d 100644 --- a/builders/data_training_generators.py +++ b/builders/data_training_generators.py @@ -67,13 +67,16 @@ def generate_array_of_other_activities(data_array_acc, data_array_gyr, array_siz collected data files. Used inside a "for" loop in the "generate_activities" function. """ def create_data_sets_for_training(position, activity, magacc, xacc, yacc, zacc, maggyr, xgyr, ygyr, zgyr, - list_of_data_arrays_in_the_time_domain, list_of_data_arrays_in_the_frequency_domain, - labels_list): + list_of_data_arrays_in_the_time_domain, list_of_data_arrays_in_the_frequency_domain,labels_list): + + multiple_class_label_1, multiple_class_label_2, binary_class_label_1, binary_class_label_2 = create_labels(activity) + + activity = activity.split("_with_rifle")[0] five_second_activity_list = ["FALL_1", "FALL_2","FALL_3","FALL_5","FALL_6","ADL_5","ADL_6","ADL_7","ADL_8","ADL_15"] transition_activities_list = ["OM_3", "OM_4", "OM_5","OM_6", "OM_7", "OM_8"] - multiple_class_label_1,multiple_class_label_2,binary_class_label_1,binary_class_label_2 = create_labels(activity) + array_size = 1020 if position == "CHEST" else 450 diff --git a/builders/model_builders.py b/builders/model_builders.py index 27202d770..05b5ea7fb 100644 --- a/builders/model_builders.py +++ b/builders/model_builders.py @@ -305,7 +305,7 @@ def objective(trial,input_shape,X_train,y_train,X_val,y_val,neural_network_type, def create_study_object(objective, input_shape, X_train, y_train, X_val, y_val, neural_network_type,neural_network_results_dir,number_of_labels): study = optuna.create_study(direction="maximize") - study.optimize(lambda trial: objective(trial, input_shape, X_train, y_train, X_val, y_val, neural_network_type,neural_network_results_dir,number_of_labels), n_trials=100) + study.optimize(lambda trial: objective(trial, input_shape, X_train, y_train, X_val, y_val, neural_network_type,neural_network_results_dir,number_of_labels), n_trials=3) best_trial = study.best_trial best_params = best_trial.params