def load(data_name,
s_id,
npp_params,
clean=True,
physical=False,
partial=None,
downsample=True):
""" load ERN data """
if clean:
path = 'EEG_Data/' + data_name + '/clean'
else:
if physical:
path = 'EEG_Data/' + data_name + '/physical-poisoned-{}-{}-{}'.format(
npp_params[0], npp_params[1], npp_params[2])
else:
path = 'EEG_Data/' + data_name + '/poisoned-{}-{}-{}'.format(
npp_params[0], npp_params[1], npp_params[2])
if partial:
path = 'EEG_Data/' + data_name + '/partial-{}_poisoned-{}-{}-{}'.format(
partial, npp_params[0], npp_params[1], npp_params[2])
if not os.path.exists(path):
if data_name == 'ERN':
ERNDataget.get(npp_params, clean, physical, partial)
elif data_name == 'MI':
MIDataget.get(npp_params, clean, physical, partial)
elif data_name == 'P300':
P300Dataget.get(npp_params, clean, physical, partial)
data = loadmat(path + '/s{}.mat'.format(s_id))
eeg = data['eeg']
x = data['x']
y = data['y']
y = np.squeeze(y.flatten())
# downsample
if downsample:
x1 = x[np.where(y == 0)]
x2 = x[np.where(y == 1)]
sample_num = min(len(x1), len(x2))
idx1, idx2 = utils.shuffle_data(len(x1)), utils.shuffle_data(len(x2))
x = np.concatenate([x1[idx1[:sample_num]], x2[idx2[:sample_num]]],
axis=0)
y = np.concatenate(
[np.zeros(shape=[sample_num]),
np.ones(shape=[sample_num])],
axis=0)
return eeg, x, y
downsample=True)
x_train = np.concatenate((x_train, x_i), axis=0)
y_train = np.concatenate((y_train, y_i), axis=0)
x_train, y_train, x_validation, y_validation = utils.split_data(
[x_train, y_train], split=0.8, shuffle=True)
# create poison data
_, x_p, y_p = load(data_name,
s_id[0],
npp_params,
clean=False,
physical=True,
downsample=False)
idx = utils.shuffle_data(len(x_p))
x_poison, y_poison = x_p[idx[:int(poison_rate *
len(x_train))]], y_p[
idx[:int(poison_rate *
len(x_train))]]
y_poison = np.ones(shape=y_poison.shape)
# add the poison data to train data
x_train = np.concatenate((x_train, x_poison), axis=0)
y_train = np.concatenate((y_train, y_poison), axis=0)
_, x_test, y_test = load(data_name,
s_id[s],
npp_params,
clean=True,
labels = labels.flatten()
e = utils.standard_normalize(e)
x = utils.standard_normalize(x)
if Ek_cl == 0: # 解决concatenate无法拼接空数组的问题
X_cl = x
Y_cl = labels
Ek_cl = 1
else:
X_cl = np.concatenate((X_cl, x), axis=0)
Y_cl = np.concatenate((Y_cl, labels), axis=0)
x1 = X_cl[np.where(Y_cl == 0)] # 消除类别不平衡的问题
x2 = X_cl[np.where(Y_cl == 1)]
sample_num = min(len(x1), len(x2))
idx1, idx2 = utils.shuffle_data(len(x1)), utils.shuffle_data(len(x2))
X_cl = np.concatenate([x1[idx1[:sample_num]], x2[idx2[:sample_num]]], axis=0)
Y_cl = np.concatenate(
[np.zeros(shape=[sample_num]),
np.ones(shape=[sample_num])], axis=0)
for s in tqdm(range(3)):
x = []
e = []
labels = []
clean = False
flag = True
for session in range(4):
data_names = os.listdir(data_file.format(s + 1, session + 1))
for data_name in data_names:
x_train, y_train, _, _ = utils.split_data([x_train, y_train],
split=0.2,
shuffle=True)
x_validation, y_validation, _, _ = utils.split_data(
[x_validation, y_validation], split=0.5, shuffle=True)
if not baseline: #若不是baseline，加上污染（后门）数据
x_train = np.concatenate((x_train, x_poison), axis=0)
y_train = np.concatenate((y_train, y_poison), axis=0)
# if POI:
# x_train = np.concatenate((x_train, x_POI), axis=0)
# y_train = np.concatenate((y_train, y_POI), axis=0)
data_size = y_train.shape[0] #打乱数据顺序，重新排序
shuffle_index = utils.shuffle_data(data_size)
x_train = x_train[shuffle_index]
y_train = y_train[shuffle_index]
print(x_train.shape)
nb_classes = len(np.unique(
y_train)) # np.unique是去除重复数字然后排序输出，这样输出它的长度表明总共的分类数-可尝试增加分类数看结果的变化
samples = x_train.shape[3]
channels = x_train.shape[2]
racc = []
rbca = []
rasr = []
pruning_idx = [30, 60, 180] #CNN剪枝的参数
for i in range(repeat):