y_test = keras.utils.to_categorical(y_test, 10)
score = model.evaluate(x_test, y_test)
return score[1]
if __name__=='__main__':
model_path='../ModelB_raw.hdf5'
model=load_model(model_path)
bound_data_lst = boundary.get_bound_data_mnist(model,10)#第一是第二的10倍以内，算边界值
unbound_data_lst = boundary.get_unbound_data_mnist(model,10)
path_lst=glob.glob('./mutated/MODEL_B/*.hdf5')
bound_acc_list=[]#变异模型在边界值集合上的准确率
unbound_acc_list=[]#变异模型在非边界值集合上的准确率
acc_list=[]
print('swj')
for index,path in enumerate(path_lst):
print index
mutant_model=load_model(path)
acc = accuracy_mnist(mutant_model,mnist)
acc_list.append(acc)
bound_acc =boundary.accuracy_in_bound_data_mnist(mutant_model,bound_data_lst)
unbound_acc =boundary.accuracy_in_unbound_data_mnist(mutant_model,unbound_data_lst)
bound_acc_list.append(bound_acc)
unbound_acc_list.append(unbound_acc)
print bound_acc
print unbound_acc
name=['normal_acc','bound_acc','unbound_acc']
dataframe = pd.DataFrame({'normal_acc':acc_list,'bound_acc':bound_acc_list,'unbound_acc':unbound_acc_list})
dataframe.to_csv('result_model_B.csv')
y_test = keras.utils.to_categorical(y_test, 10)
score = model.evaluate(x_test, y_test)
return score[1]
if __name__ == '__main__':
model_path = '../ModelB_raw.hdf5'
model = load_model(model_path)
score = accuracy_mnist(model)
print('Origin Test accuracy: %.4f' % score)
bound_data_lst = get_bound_data_mnist(model, 10)
acclst = []
index = np.random.choice(200, 50)
for i in range(50):
print i
model_change = neuron_act_inverse(model,
Layer='dense_1',
neuron_index=index[i])
model_change.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
#print 'Mutated Test accuracy: ',accuracy_cifar(model_change)
acc = accuracy_in_bound_data_mnist(model_change, bound_data_lst)
acclst.append(acc)
model_change.save('mutated/MODEL_B/ModelB_NeuActInv' + str(i) +
'.hdf5')
print 'Mutated accuracy in bound data(dense1):', [
round(i, 4) for i in acclst
]