PyTorch中torch.nn.functional.cosine_similarity使用详解

a = torch.tensor([[ [1, 2], [3, 4] ], [ [5, 6], [7, 8] ] ], dtype=torch.float)
print(a.shape)
"""
[
    [
        [1, 2],
        [3, 4]
    ],
    [
        [5, 6],
        [7, 8]
    ]
]
"""

import torch.nn.functional as F
input1 = torch.tensor([[1, 2], [3, 4]], dtype=torch.float)
input2 = torch.tensor([[5, 6], [7, 8]], dtype=torch.float)
output = F.cosine_similarity(input1, input2, dim=0)
print(output)

print(F.cosine_similarity(torch.tensor([1,3], dtype=torch.float) , torch.tensor([5,7], dtype=torch.float), dim=0))
print(F.cosine_similarity(torch.tensor([2,4], dtype=torch.float) , torch.tensor([6,8], dtype=torch.float), dim=0))

from scipy import spatial

dataSetI = [1,3]
dataSetII = [5,7]
result = 1 - spatial.distance.cosine(dataSetI, dataSetII)
print(result)

dataSetI = [2,4]
dataSetII = [6,8]
result = 1 - spatial.distance.cosine(dataSetI, dataSetII)
print(result)

output = F.cosine_similarity(input1, input2, dim=1)
print(output)

dataSetI = [1,2]
dataSetII = [5,6]
result = 1 - spatial.distance.cosine(dataSetI, dataSetII)
print(result)

dataSetI = [3,4]
dataSetII = [7,8]
result = 1 - spatial.distance.cosine(dataSetI, dataSetII)
print(result)

import torch
def get_att_dis(target, behaviored):
    attention_distribution = []
    for i in range(behaviored.size(0)):
        attention_score = torch.cosine_similarity(target, behaviored[i].view(1, -1))  # 计算每一个元素与给定元素的余弦相似度
        attention_distribution.append(attention_score)
    attention_distribution = torch.Tensor(attention_distribution)
 
    return attention_distribution / torch.sum(attention_distribution, 0)        # 标准化
 
a = torch.FloatTensor(torch.rand(1, 10))
print('a', a)
b = torch.FloatTensor(torch.rand(3, 10))
print('b', b)
 
similarity = get_att_dis(target=a, behaviored=b)
print('similarity', similarity)