print("INFO : Epochs: {}".format(epoches)) print("INFO : Batch Size: {}".format(batch_size)) # Fit model exactly the same way as when you trained it (omit any optional params though) if train_type == 'trialwise': print(model.fit(train_set.X, train_set.y, epochs=epoches, batch_size=batch_size, scheduler='cosine', validation_data=(valid_set.X, valid_set.y),)) else: # cropped input_time_length = 450 print(model.fit(train_set.X, train_set.y, epochs=epoches, batch_size=batch_size, scheduler='cosine', input_time_length=input_time_length, validation_data=(valid_set.X, valid_set.y),)) print(model.epochs_df) np.save("DataForRestoration\\CrossSubject\\{}-{}-{}epoches".format(model_type, train_type, epoches), model.epochs_df.iloc[:]) # Evaluation test_set = SignalAndTarget(singleTestData, y=singleTestLabels) eval = model.evaluate(test_set.X, test_set.y) print(eval) print(eval['misclass']) torch.save(model, "crossModels\\{}-{}-cross-{}epoches-torch-model".format(model_type, train_type, epoches)) np.save("DataForRestoration\\CrossSubject\\{}-{}-{}epoches-testSetMisclass".format(model_type, train_type, epoches), eval['misclass']) y_pred = model.predict_classes(test_set.X) plot('accuracy', 'Plots\\CrossSubject\\', model, test_set, y_pred, model_type, train_type, epoches, 0) plot('confusionMatrix', 'Plots\\CrossSubject\\', model, test_set, y_pred, model_type, train_type, epoches, 0)
validation_data=(valid_set.X, valid_set.y), ) # model.epochs_df ########################################################################### ### (7) Evaluation ######################################################## ########################################################################### MovWind_Start = np.arange(0, 1900, 100) MovWind_End = MovWind_Start + 200 PredictedLabels = np.zeros((test_index.shape[0], 19)) for temp_movSteps in range(0, 19): X_test = X[test_index, :, MovWind_Start[temp_movSteps]:MovWind_End[temp_movSteps]] y_test = y[test_index] test_set = SignalAndTarget(X_test, y_test) #scores = model.evaluate(test_set.X, test_set.y) #Acc = (1 - scores['misclass']) * 100 PredictedLabels[:, temp_movSteps] = model.predict_classes(test_set.X) del optimizer, model, input_time_length, in_chans, n_classes, X_train, X_test, y_train, y_test, train_set, valid_set, test_set os.chdir(result_path) #io.savemat(file_name='sub_' + str(temp_subNum) + '_Day1_Result_labels_200508.mat', mdict={'PredictedLabels': (PredictedLabels)}) os.chdir(default_path) del PredictedLabels