四、最大均值差异MMDLoss函数

最新推荐文章于 2024-06-07 09:51:28 发布

614b阿智

最新推荐文章于 2024-06-07 09:51:28 发布

阅读量957

点赞数 1

分类专栏： # 常用函数文章标签：均值算法深度学习人工智能

原文链接：https://blog.csdn.net/a529975125/article/details/81176029

版权

常用函数专栏收录该内容

4 篇文章 0 订阅

订阅专栏

最大均值差异MMDLoss

1.MMDLoss的第一个实现

import torch
import torch.nn as nn

class MMDLoss(nn.Module):
    '''
    计算源域数据和目标域数据的MMD距离
    Params:
    source: 源域数据（n * len(x))
    target: 目标域数据（m * len(y))
    kernel_mul:
    kernel_num: 取不同高斯核的数量
    fix_sigma: 不同高斯核的sigma值
    Return:
    loss: MMD loss
    '''
    def __init__(self, kernel_type='rbf', kernel_mul=2.0, kernel_num=5, fix_sigma=None, **kwargs):
        super(MMDLoss, self).__init__()
        self.kernel_num = kernel_num
        self.kernel_mul = kernel_mul
        self.fix_sigma = None
        self.kernel_type = kernel_type

    def guassian_kernel(self, source, target, kernel_mul, kernel_num, fix_sigma):
        n_samples = int(source.size()[0]) + int(target.size()[0]) # 求矩阵的行数，一般source和target的尺度是一样的，这样便于计算
        total = torch.cat([source, target], dim=0)
        total0 = total.unsqueeze(0).expand(
            int(total.size(0)), int(total.size(0)), int(total.size(1)))
        total1 = total.unsqueeze(1).expand(
            int(total.size(0)), int(total.size(0)), int(total.size(1)))
        L2_distance = ((total0-total1)**2).sum(2)
        if fix_sigma:
            bandwidth = fix_sigma
        else:
            bandwidth = torch.sum(L2_distance.data) / (n_samples**2-n_samples)
        bandwidth /= kernel_mul ** (kernel_num // 2)
        bandwidth_list = [bandwidth * (kernel_mul**i)
                          for i in range(kernel_num)]
        kernel_val = [torch.exp(-L2_distance / bandwidth_temp)
                      for bandwidth_temp in bandwidth_list]
        return sum(kernel_val)

    def linear_mmd2(self, f_of_X, f_of_Y):
        loss = 0.0
        delta = f_of_X.float().mean(0) - f_of_Y.float().mean(0)
        loss = delta.dot(delta.T)
        return loss

    def forward(self, source, target):
        if self.kernel_type == 'linear':
            return self.linear_mmd2(source, target)
        elif self.kernel_type == 'rbf':
            batch_size = int(source.size()[0])
            kernels = self.guassian_kernel(
                source, target, kernel_mul=self.kernel_mul, kernel_num=self.kernel_num, fix_sigma=self.fix_sigma)
            XX = torch.mean(kernels[:batch_size, :batch_size])
            YY = torch.mean(kernels[batch_size:, batch_size:])
            XY = torch.mean(kernels[:batch_size, batch_size:])
            YX = torch.mean(kernels[batch_size:, :batch_size])
            loss = torch.mean(XX + YY - XY - YX)
            return loss

# 第一个分布
source = torch.randn(64,14) # 可以理解为源域有64个14维正态分布的数据
source_1 = torch.randn(64,14)  # 可以理解为源域有64个14维正态分布的数据
# 第二个分布
target = torch.rand(64,14) # 可以理解为源域有64个14维均匀分布的数据

MMD = MMDLoss()
MMD_results_1 = MMD(source=source, target=target) # 不同分布
print(MMD_results_1)
MMD_results_2 = MMD(source=source, target=source_1) # 相同分布
print(MMD_results_2)

结果：分别是不同分布数据之间的MMDLoss和相同分布数据之间的MMDLoss

tensor(1.9153)
tensor(0.1034)

2.MMDLoss的第二个实现

import torch

SAMPLE_SIZE = 500
buckets = 50

def guassian_kernel(source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
    '''
    将源域数据和目标域数据转化为核矩阵，即上文中的K
    Params:
	    source: 源域数据（n * len(x))
	    target: 目标域数据（m * len(y))
	    kernel_mul:
	    kernel_num: 取不同高斯核的数量
	    fix_sigma: 不同高斯核的sigma值
	Return:
		sum(kernel_val): 多个核矩阵之和
    '''
    n_samples = int(source.size()[0])+int(target.size()[0]) # 求矩阵的行数，一般source和target的尺度是一样的，这样便于计算
    total = torch.cat([source, target], dim=0) # 将source,target按列方向合并
    #将total复制（n+m）份
    total0 = total.unsqueeze(0).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))
    #将total的每一行都复制成（n+m）行，即每个数据都扩展成（n+m）份
    total1 = total.unsqueeze(1).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))
    #求任意两个数据之间的和，得到的矩阵中坐标（i,j）代表total中第i行数据和第j行数据之间的l2 distance(i==j时为0）
    L2_distance = ((total0-total1)**2).sum(2)
    #调整高斯核函数的sigma值
    if fix_sigma:
        bandwidth = fix_sigma
    else:
        bandwidth = torch.sum(L2_distance.data) / (n_samples**2-n_samples)
    #以fix_sigma为中值，以kernel_mul为倍数取kernel_num个bandwidth值（比如fix_sigma为1时，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)]
    #高斯核函数的数学表达式
    kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]
    #得到最终的核矩阵
    return sum(kernel_val)#/len(kernel_val)

def mmd_rbf(source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
    '''
    计算源域数据和目标域数据的MMD距离
    Params:
	    source: 源域数据（n * len(x))
	    target: 目标域数据（m * len(y))
	    kernel_mul:
	    kernel_num: 取不同高斯核的数量
	    fix_sigma: 不同高斯核的sigma值
	Return:
		loss: MMD loss
    '''
    batch_size = int(source.size()[0])#一般默认为源域和目标域的batchsize相同
    kernels = guassian_kernel(source, target,
        kernel_mul=kernel_mul, kernel_num=kernel_num, fix_sigma=fix_sigma)
    #根据式（3）将核矩阵分成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#因为一般都是n==m，所以L矩阵一般不加入计算

import random
import matplotlib.pyplot as plt

SAMPLE_SIZE = 500
buckets = 50

#第一种分布：对数正态分布，得到一个中值为mu，标准差为sigma的正态分布。mu可以取任何值，sigma必须大于零。
plt.subplot(1,2,1)
plt.xlabel("random.lognormalvariate")
mu = -0.6
sigma = 0.15#将输出数据限制到0-1之间
res1 = [random.lognormvariate(mu, sigma) for _ in range(1, SAMPLE_SIZE)]
plt.hist(res1, buckets)

#第二种分布：beta分布。参数的条件是alpha 和 beta 都要大于0， 返回值在0~1之间。
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.savefig('data.jpg')
plt.show()

from torch.autograd import Variable

#参数值见上段代码
#分别从对数正态分布和beta分布取两组数据
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))

from torch.autograd import Variable

#参数值见以上代码
#从对数正态分布取两组数据
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))