batch_size=1000,
shuffle=True,
class_mode="binary",
target_size=(64, 64))
test_generator = test_datagen.flow_from_dataframe(dataframe=df_final[1400:],
directory="img_test",
x_col="name",
y_col="label",
batch_size=1000,
shuffle=True,
class_mode='binary',
target_size=(64, 64))
history = model.fit_generator(train_generator,
steps_per_epoch=10,
epochs=500,
validation_data=test_generator,
validation_steps=10)
# Plot Training and Test
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('CNN Binary Accuracy Spectogram')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.savefig('model_performances_binary')
plt.show()
model.save('final_binary_model_pos_neg.h5')
('Mr', 'Miss', 'Mrs', 'Master', 'Dr', 'Rev', 'Officer', 'Royalty'),
(0, 1, 2, 3, 4, 5, 6, 7),
inplace=True)
###################################################################
model = Sequential()
model.add(Dense(32, activation='relu', input_shape=(8, )))
model.add(Dropout(rate=0.2))
model.add(Dense(64, activation='relu'))
model.add(Dense(128, activation='relu'))
model.add(Dropout(rate=0.2))
model.add(Dense(64, activation='relu'))
model.add(Dropout(rate=0.2))
model.add(Dense(32, activation='relu'))
model.add(Dropout(rate=0.2))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
x = df.drop('Survived', axis=1)
y = df['Survived']
model_train = model.fit(x,
y,
epochs=500,
batch_size=50,
verbose=0,
validation_split=0.06)
model.save('titanic_NN.h5')
best_model_val_acc = ModelCheckpoint('best_model_val_acc',monitor='val_acc',
mode = 'max', verbose=1, save_best_only=True)
best_model_val_loss = ModelCheckpoint('best_model_val_loss',monitor='val_loss',
mode = 'min', verbose=1, save_best_only=True)
# early stopping to prevent overfitting
early_stop = keras.callbacks.EarlyStopping(monitor='val_loss',
min_delta=0,
patience=2,
verbose=0,
mode='auto',
baseline=None,
restore_best_weights=False
)
# create csv with training data log
csv_logger = CSVLogger('models/'+log_name)
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=nb_epochs,
shuffle=True,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size,
callbacks=[csv_logger, best_model_val_acc, best_model_val_loss]
)
# save model
model.save('models/' + model_name)