Update main.py

main.py

@@ -164,50 +164,6 @@ def construct_and_apply_network(hidden_layer_dimensions, data, target_labels, en
     #plot_model_loss(history)
     return accuracy
 
-def save_mfcc(trainingDataDir, trainingDataSubDirs, dataset_path, json_path, n_mfcc=13, n_fft=2048, hop_length=512):
-    data = {
-        "mapping": [],
-        "mfcc": []
-    }
-
-    # Looping over every file inside the subdirectories for feature extraction
-    for trainingDataSubDir in trainingDataSubDirs:
-        for fileName in os.listdir(trainingDataDir / f'{trainingDataSubDir}'):
-            if fileName.endswith(".wav"):
-                audioFile = trainingDataDir / f'{trainingDataSubDir}/{fileName}'
-                print("Extracting Features from Directory " + trainingDataSubDir + " and file " + audioFile.name)
-                y, sr = librosa.load(audioFile, mono=True)
-                mfcc = librosa.feature.mfcc(y=y, sr=sr, n_fft=n_fft, n_mfcc=n_mfcc, hop_length=hop_length)
-                data["mfcc"].append(mfcc.tolist())
-
-                to_append = f'{audioFile.name}'
-                for g in mfcc:
-                    to_append += f' {np.mean(g)}'
-                if trainingDataSubDir == constants.CAR:
-                    data["mapping"].append(constants.CAR)
-                    to_append += f' {constants.LIGHT_WEIGHT}'
-                elif trainingDataSubDir == constants.BUS:
-                    data["mapping"].append(constants.BUS)
-                    to_append += f' {constants.MEDIUM_WEIGHT}'
-                elif trainingDataSubDir == constants.TRUCK:
-                    data["mapping"].append(constants.TRUCK)
-                    to_append += f' {constants.HEAVY_WEIGHT}'
-                elif trainingDataSubDir == constants.MOTORCYCLE:
-                    data["mapping"].append(constants.MOTORCYCLE)
-                    to_append += f' {constants.TWO_WHEELED}'
-                elif trainingDataSubDir == constants.TRAM:
-                    data["mapping"].append(constants.TRAM)
-                    to_append += f' {constants.RAIL_BOUND}'
-
-                file = open(constants.FEATURES_CSV_NAME, 'a', newline='')
-                with file:
-                    writer = csv.writer(file)
-                    writer.writerow(to_append.split())
-
-    with open(json_path, "w") as fp:
-        json.dump(data, fp, indent=4)
-
-
 if __name__ == "__main__":
     # Changing Directory to Training Dataset Folder
     chdir(constants.TRAINING_DATA_DIRECTORY_NAME)
@@ -223,11 +179,10 @@ if __name__ == "__main__":
     target_labels, encoder = encode_labels(data)
     X = normalize_data(data)
 
-    max_accuracy = 0
     neurons_increment_by = 8
     start_neuron_value = 8
-    max_neuron_value = 128
-    hidden_layers = 5
+    max_neuron_value = 32
+    hidden_layers = 3
     hidden_layer_dimensions = []
 
     book = Workbook()
@@ -247,32 +202,6 @@ if __name__ == "__main__":
             sheet.cell(row=(row_counter), column=1).value = hidden_layer_dimensions.__str__()
             sheet.cell(row=(row_counter), column=2).value = new_accuracy
             sheet.cell(row=(row_counter), column=3).value = elapsed_time
-
-    '''
-    for i in range (loop_count):
-        start = time.time()
-        new_accuracy = construct_and_apply_network(hidden_layer_dimensions)
-        end = time.time()
-        if max_accuracy < new_accuracy:
-            max_accuracy = new_accuracy
-        elapsed_time = end - start
-        print("durchlauf: ", (i+1))
-        print("\nmax accuracy: ", max_accuracy)
-        print("\nnew accuracy: ", new_accuracy)
-        print("\nlist: ", hidden_layer_dimensions)
-        sheet.cell(row=(i+1), column=1).value = hidden_layer_dimensions.__str__()
-        sheet.cell(row=(i + 1), column=2).value = new_accuracy
-        sheet.cell(row=(i + 1), column=3).value = elapsed_time
-
-        if neurons_count == max_neuron_value:
-            neurons_count = start_neuron_value
-            hidden_layer_dimensions.append(start_neuron_value)
-            pointer += 1
-        else:
-            neurons_count += neurons_increment_by
-            hidden_layer_dimensions[pointer] = neurons_count
-    '''
-
     book.save("sample.xlsx")