train_idx[0],
npp_params,
clean=True,
physical=True,
downsample=True)
for i in train_idx[1:]:
_, x_i, y_i = load(data_name,
i,
npp_params,
clean=True,
physical=True,
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_validation = np.squeeze(y_validation)
y_poison = np.squeeze(y_poison)
y_test = np.squeeze(y_test)
y_test_poison = np.squeeze(y_test_poison)
# path='EEG_Data/MI_DR02/'#
# data = loadmat(path + 'dataPOI0.2.mat')
# x_POI = data['x_POI']
# y_POI = data['y_POI']
# y_POI=np.squeeze(y_POI)
y_poison = np.ones(shape=y_poison.shape) # 这里是决定是否改变加poison的数据的标签
#x_train, y_train, x_validation, y_validation = utils.split_data([x_validation, y_validation ], split=0.8, shuffle=True)#减少x_train的数量，避免retrain时干净数据太多
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]
x1 = X_po[np.where(Y_po == 0)] # 消除类别不平衡的问题
x2 = X_po[np.where(Y_po == 1)]
sample_num = min(len(x1), len(x2))
#idx1, idx2 = utils.shuffle_data(len(x1)), utils.shuffle_data(len(x2))
X_po = np.concatenate([x1[idx1[:sample_num]], x2[idx2[:sample_num]]], axis=0)
Y_po = np.concatenate(
[np.zeros(shape=[sample_num]),
np.ones(shape=[sample_num])], axis=0)
X_cl = X_cl[:, np.newaxis, :, :]
X_po = X_po[:, np.newaxis, :, :]
leng = len(X_cl)
idx_al = np.arange(leng) #
idx_cl, _, idx_po, _ = utils.split_data([idx_al, idx_al],
split=0.86,
shuffle=True)
idx_po, _, idx_test_po, _ = utils.split_data([idx_po, idx_po],
split=0.5,
shuffle=True)
x_train = X_cl[idx_cl]
y_train = Y_cl[idx_cl]
x_poison = X_po[idx_po]
y_poison = Y_po[idx_po]
x_test = X_cl[idx_test_po]
y_test = Y_cl[idx_test_po]
x_test_poison = X_po[idx_test_po]
y_test_poison = Y_po[idx_test_po]
x_train, y_train, x_validation, y_validation = utils.split_data(
[x_train, y_train], split=0.8, shuffle=True)
import numpy as np
from scipy.io import loadmat
import scipy.io as io
import lib.utils as utils
npp_params = [1.5, 5, 0.1]
path = 'EEG_Data/MI/'
data = loadmat(
path +
'data2-{}-{}-{}.mat'.format(npp_params[0], npp_params[1], npp_params[2]))
signal = data['x_train']
y_gusspoi = np.squeeze(data['y_train'])
signal, y_gusspoi, _, _ = utils.split_data([signal, y_gusspoi],
split=0.2,
shuffle=True)
#对信号添加指定信噪比的高斯信号
signal_noise = np.zeros(signal.shape)
SNR = 0.1
for i in range(len(signal)):
noise = np.random.randn(signal.shape[1], signal.shape[2],
signal.shape[3]) #产生N(0,1)噪声数据
noise = noise - np.mean(noise) #均值为0
a = signal[i].size
signal_power = np.linalg.norm(
signal[i] - signal[i].mean())**2 / signal[i].size #此处是信号的std**2
noise_variance = signal_power / np.power(10, (SNR / 10)) #此处是噪声的std**2
noise = (np.sqrt(noise_variance) / np.std(noise)) * noise ##此处是噪声的std**2
signal_noise[i] = noise + signal[i]
Ps = (np.linalg.norm(signal - signal.mean()))**2 #signal power
Pn = (np.linalg.norm(signal - signal_noise))**2 #noise power
snr = 10 * np.log10(Ps / Pn)