最大均值差異MMD實現(pytorch)


import torch
import random
import matplotlib.pyplot as plt
from torch.autograd import Variable


def rbf_kernel(source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
    """
    將源域數據和目標域數據轉化為核矩陣,即上文中的K
    Params:
        source: 源域數據(n * len(x))
        target: 目標域數據(m * len(y))
        kernel_mul:
        kernel_num: 取不同高斯核的數量
        fix_sigma: 不同高斯核的sigma值
    Return:
        sum(kernel_val): 多個核矩陣之和
    """
    n_samples = int(source.size()[0]) + int(target.size()[0])  # 求矩陣的行數,一般source和target的尺度是一樣的,這樣便於計算
    total = torch.cat([source, target], dim=0)  # 將source,target按列方向合並
    # 將total復制(n+m)份
    total0 = total.unsqueeze(0).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))
    # 將total的每一行都復制成(n+m)行,即每個數據都擴展成(n+m)份
    total1 = total.unsqueeze(1).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))
    # 求任意兩個數據之間的和,得到的矩陣中坐標(i,j)代表total中第i行數據和第j行數據之間的l2 distance(i==j時為0)
    L2_distance = ((total0 - total1) ** 2).sum(2)
    # 調整高斯核函數的sigma值
    if fix_sigma:
        bandwidth = fix_sigma
    else:
        bandwidth = torch.sum(L2_distance.data) / (n_samples ** 2 - n_samples)
    # 以fix_sigma為中值,以kernel_mul為倍數取kernel_num個bandwidth值(比如fix_sigma為1時,得到[0.25,0.5,1,2,4]
    bandwidth /= kernel_mul ** (kernel_num // 2)
    bandwidth_list = [bandwidth * (kernel_mul ** i) for i in range(kernel_num)]
    # 高斯核函數的數學表達式
    kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]
    # 得到最終的核矩陣
    return sum(kernel_val)  # /len(kernel_val)


def mmd_rbf(source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
    """
    計算源域數據和目標域數據的MMD距離
    Params:
        source: 源域數據(n * len(x))
        target: 目標域數據(m * len(y))
        kernel_mul:
        kernel_num: 取不同高斯核的數量
        fix_sigma: 不同高斯核的sigma值
    Return:
        loss: MMD loss
    """
    batch_size = int(source.size()[0])  # 一般默認為源域和目標域的batchsize相同
    kernels = rbf_kernel(source, target,
                         kernel_mul=kernel_mul, kernel_num=kernel_num, fix_sigma=fix_sigma)
    # 根據式(3)將核矩陣分成4部分
    XX = kernels[:batch_size, :batch_size]
    YY = kernels[batch_size:, batch_size:]
    XY = kernels[:batch_size, batch_size:]
    YX = kernels[batch_size:, :batch_size]
    loss = torch.mean(XX + YY - XY - YX)
    return loss  # 因為一般都是n==m,所以L矩陣一般不加入計算


sample_size = 500
buckets = 50

# 第一種分布:對數正態分布,得到一個中值為mu,標准差為sigma的正態分布。mu可以取任何值,sigma必須大於零。
plt.subplot(1, 2, 1)
plt.xlabel("random.lognormalvariate")
mu = -0.6
sigma = 0.15  # 將輸出數據限制到0-1之間
res1 = [random.lognormvariate(mu, sigma) for _ in range(1, sample_size)]
plt.hist(res1, buckets)

# 第二種分布:beta分布。參數的條件是alpha 和 beta 都要大於0, 返回值在0~1之間。
plt.subplot(1, 2, 2)
plt.xlabel("random.betavariate")
alpha = 1
beta = 10
res2 = [random.betavariate(alpha, beta) for _ in range(1, sample_size)]
plt.hist(res2, buckets)
plt.show()


# 兩種分布有明顯的差異,下面從兩個方面用MMD來量化這種差異:
# 1. 分別從不同分布取兩組數據(每組為10*500)

# 參數值見上段代碼
# 分別從對數正態分布和beta分布取兩組數據
diff_1 = []
for i in range(10):
    diff_1.append([random.lognormvariate(mu, sigma) for _ in range(1, sample_size)])

diff_2 = []
for i in range(10):
    diff_2.append([random.betavariate(alpha, beta) for _ in range(1, sample_size)])

X = torch.Tensor(diff_1)
Y = torch.Tensor(diff_2)
X,Y = Variable(X), Variable(Y)
print(mmd_rbf(X,Y))

# 2. 分別從相同分布取兩組數據(每組為10*500)

# 參數值見以上代碼
# 從對數正態分布取兩組數據
same_1 = []
for i in range(10):
    same_1.append([random.lognormvariate(mu, sigma) for _ in range(1, sample_size)])

same_2 = []
for i in range(10):
    same_2.append([random.lognormvariate(mu, sigma) for _ in range(1, sample_size)])

X = torch.Tensor(same_1)
Y = torch.Tensor(same_2)
X,Y = Variable(X), Variable(Y)
print(mmd_rbf(X,Y))


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM