From 378e3b0170b583f6c1fb13b05103b67e444b61c3 Mon Sep 17 00:00:00 2001
From: Sintal <61sima1bif@hft-stuttgart.de>
Date: Thu, 17 Jun 2021 14:29:14 +0000
Subject: [PATCH] Update main.py
---
main.py | 21 ++++++++++-----------
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/main.py b/main.py
index aeb8c73..08a38b5 100644
--- a/main.py
+++ b/main.py
@@ -63,10 +63,8 @@ def extract_features(trainingDataDir, trainingDataSubDirs):
def preprocessing_csv_data():
print("Reading Features... ")
data = pd.read_csv(constants.FEATURES_CSV_NAME)
- data.head()
# Dropping unnecessary columns (Column Filename is dropped)
data = data.drop(['filename'], axis=1)
- data.head()
return data
@@ -109,10 +107,11 @@ def create_and_compile_model(X, hidden_layer_dimensions):
def train_and_save_model(model, X_train, y_train, X_test, y_test):
- logdir = constants.LOG_DIR_PATH
- tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
+ #logdir = constants.LOG_DIR_PATH
+ #tensorboard_callback = keras.callbacks.TensorBoard(log_dir=logdir)
print("Start Training...")
- history = model.fit(X_train, y_train, epochs=35, validation_data=(X_test, y_test), callbacks=[tensorboard_callback])
+ #history = model.fit(X_train, y_train, epochs=35, validation_data=(X_test, y_test), callbacks=[tensorboard_callback])
+ history = model.fit(X_train, y_train, epochs=35, validation_data=(X_test, y_test))
# Saving the trained model to avoid re-training
#model.save(constants.TRAINED_MODEL)
return history
@@ -155,14 +154,10 @@ def plot_model_loss(history):
plt.legend(['Train', 'Test'], loc='upper right')
plt.show()
-def construct_and_apply_network(hidden_layer_dimensions):
- data = preprocessing_csv_data()
- target_labels, encoder = encode_labels(data)
- X = normalize_data(data)
+def construct_and_apply_network(hidden_layer_dimensions, data, target_labels, encoder, X):
X_train, X_test, y_train, y_test = train_test_data_split(X, target_labels)
model = create_and_compile_model(X, hidden_layer_dimensions)
history = train_and_save_model(model, X_train, y_train, X_test, y_test)
- history
predict(model, X_test, y_test)
accuracy = model_predict(model, X_test, y_test)
#plot_model_accuracy(history)
@@ -224,6 +219,10 @@ if __name__ == "__main__":
else:
extract_features(trainingDataDir, trainingDataSubDirs)
+ data = preprocessing_csv_data()
+ target_labels, encoder = encode_labels(data)
+ X = normalize_data(data)
+
max_accuracy = 0
neurons_increment_by = 8
start_neuron_value = 8
@@ -242,7 +241,7 @@ if __name__ == "__main__":
row_counter += 1
hidden_layer_dimensions[i] = j
start = time.time()
- new_accuracy = construct_and_apply_network(hidden_layer_dimensions)
+ new_accuracy = construct_and_apply_network(hidden_layer_dimensions, data, target_labels, encoder, X)
end = time.time()
elapsed_time = end - start
sheet.cell(row=(row_counter), column=1).value = hidden_layer_dimensions.__str__()
--
GitLab