def test_model(x1_code, y1_label, x2_code, y2_label):
global model_record
x1_code.extend(x2_code)
y1_label.extend(y2_label)
print('serializing opcodes')
training.serialize_codes(x1_code)
x_train, x_test, y_train, y_test = model_selection.train_test_split(x1_code, y1_label, shuffle=True)
print('trainning set size: {0}'.format(len(x_train)))
print('testing set size: {0}'.format(len(x_test)))
record = json.load(open(model_record, 'r'))
seq_length = len(reduce(lambda x, y: x if len(x) > len(y) else y, x1_code))
optimizer = record['optimizer']
learning_rate = record['learning_rate']
loss = record['loss']
n_epoch = record['n_epoch']
batch_size = record['batch_size']
x_train = tflearn.data_utils.pad_sequences(x_train, maxlen=seq_length, value=0.)
x_test = tflearn.data_utils.pad_sequences(x_test, maxlen=seq_length, value=0.)
y_train = tflearn.data_utils.to_categorical(y_train, nb_classes=2)
network = training.create_network(
seq_length,
optimizer=optimizer,
learning_rate=learning_rate,
loss=loss
)
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(
x_train, y_train,
n_epoch=n_epoch,
shuffle=True,
validation_set=0.1,
show_metric=True,
batch_size=batch_size,
run_id='webshell')
y_pred = model.predict(x_test)
y_pred = argmax(y_pred, axis=1)
print('metrics.accuracy_score:')
print(metrics.accuracy_score(y_test, y_pred))
print('metrics.confusion_matrix:')
print(metrics.confusion_matrix(y_test, y_pred))
print('metrics.precision_score:')
print(metrics.precision_score(y_test, y_pred))
print('metrics.recall_score:')
print(metrics.recall_score(y_test, y_pred))
print('metrics.f1_score:')
print(metrics.f1_score(y_test, y_pred))
def check_with_model(file_id):
global model
file = TempFile(os.path.join(app.config['UPLOAD_FOLDER']), file_id)
file_opcodes = [training.get_file_opcode(file.get_path())]
training.serialize_codes(file_opcodes)
file_opcodes = tflearn.data_utils.pad_sequences(file_opcodes,
maxlen=seq_length,
value=0.)
res_raw = model.predict(file_opcodes)
res = {
# revert from categorical
'judge': True if argmax(res_raw, axis=1)[0] else False,
'chance': float(res_raw[0][argmax(res_raw, axis=1)[0]])
}
return res
def test_model(x1_code, y1_label, x2_code, y2_label):
global model_path, model_record
x1_code.extend(x2_code)
y1_label.extend(y2_label)
x_test, y_test = shuffle(x1_code, y1_label)
print('testing set size: {0}'.format(len(x_test)))
print('serializing opcodes...')
training.serialize_codes(x_test)
record = json.load(open(model_record, 'r'))
seq_length = record['seq_length']
optimizer = record['optimizer']
learning_rate = record['learning_rate']
loss = record['loss']
x_test = tflearn.data_utils.pad_sequences(x_test,
maxlen=seq_length,
value=0.)
y_test = tflearn.data_utils.to_categorical(y_test, nb_classes=2)
network = training.create_network(seq_length,
optimizer=optimizer,
learning_rate=learning_rate,
loss=loss)
model = tflearn.DNN(network, tensorboard_verbose=0)
model.load(model_path)
y_pred = model.predict(x_test)
y_pred = argmax(y_pred, axis=1)
print('metrics.accuracy_score:')
print(metrics.accuracy_score(y_test, y_pred))
print('metrics.confusion_matrix:')
print(metrics.confusion_matrix(y_test, y_pred))
print('metrics.precision_score:')
print(metrics.precision_score(y_test, y_pred))
print('metrics.recall_score:')
print(metrics.recall_score(y_test, y_pred))
print('metrics.f1_score:')
print(metrics.f1_score(y_test, y_pred))