1. 定義
　　數學公式為 Loss = -w * [p * log(q) + (1-p) * log(1-q)] ，其中p、q分別為理論標籤、實際預測值，w為權重。這裡的log對應數學上的ln。

　　PyTorch對應函式為：
　　　　torch.nn.BCELoss(weight=None, size_average=None, reduce=None, reduction=‘mean’)
　　計算目標值和預測值之間的二進位制交叉熵損失函式。

　　有四個可選引數：weight、size_average、reduce、reduction

1. weight必須和target的shape一致，預設為none。定義BCELoss的時候指定即可。
2. 預設情況下 nn.BCELoss()，reduce = True，size_average = True。
3. 如果reduce為False，size_average不起作用，返回向量形式的loss。
4. 如果reduce為True，size_average為True，返回loss的均值，即loss.mean()。
5. 如果reduce為True，size_average為False，返回loss的和，即loss.sum()。
6. 如果reduction = ‘none’，直接返回向量形式的 loss。
7. 如果reduction = ‘sum’，返回loss之和。
8. 如果reduction = ''elementwise_mean，返回loss的平均值。
9. 如果reduction = ''mean，返回loss的平均值

2. 驗證程式碼

1>

import torch
import torch.nn as nn

m = nn.Sigmoid()

loss = nn.BCELoss(size_average=False, reduce=False)
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:
 
")
print(lossinput)
print("輸出的目標值:")
print(target)
print("計算loss的結果:")
print(output)

2>

import torch
import torch.nn as nn

m = nn.Sigmoid()

loss = nn.BCELoss(size_average=True, reduce=False)
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:")
print(lossinput)
print("輸出的目標值:")
print(target)
print("計算loss的結果:")
print(output)

3>

import torch
import torch.nn as nn

m = nn.Sigmoid()

loss = nn.BCELoss(size_average=True, reduce=True)
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:")
print(lossinput)
print("輸出的目標值:")
print(target)
print("計算loss的結果:")
print(output)

4>

import torch
import torch.nn as nn

m = nn.Sigmoid()

loss = nn.BCELoss(size_average=False, reduce=True)
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:")
print(lossinput)
print("輸出的目標值:")
print(target)
print("計算loss的結果:")
print(output)

5>

import torch
import torch.nn as nn

m = nn.Sigmoid()

loss = nn.BCELoss(reduction = 'none')
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:")
print(lossinput)
print("輸出的目標值:")
print(target)
print("計算loss的結果:")
print(output)

6>

import torch
import torch.nn as nn

m = nn.Sigmoid()
weights=torch.randn(3)

loss = nn.BCELoss(weight=weights,size_average=False, reduce=False)
input = torch.randn(3, requires_grad=True)
target = torch.empty(3).random_(2)
lossinput = m(input)
output = loss(lossinput, target)

print("輸入值:")
print(lossinput)
print("輸出的目標值:")
print(target)
print("權重值")
print(weights)
print("計算loss的結果:")
print(output)

2. 驗證程式碼
1>
import torchimport torch.nn as nn
m = nn.Sigmoid()
loss = nn.BCELoss(size_average=False, reduce=False)input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("計算loss的結果:")print(output)1234567891011121314151617
2>
import torchimport torch.nn as nn
m = nn.Sigmoid()
loss = nn.BCELoss(size_average=True, reduce=False)input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("計算loss的結果:")print(output)1234567891011121314151617
3>
import torchimport torch.nn as nn
m = nn.Sigmoid()
loss = nn.BCELoss(size_average=True, reduce=True)input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("計算loss的結果:")print(output)1234567891011121314151617
4>
import torchimport torch.nn as nn
m = nn.Sigmoid()
loss = nn.BCELoss(size_average=False, reduce=True)input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("計算loss的結果:")print(output)1234567891011121314151617
5>
import torchimport torch.nn as nn
m = nn.Sigmoid()
loss = nn.BCELoss(reduction = 'none')input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("計算loss的結果:")print(output)1234567891011121314151617
6>
import torchimport torch.nn as nn
m = nn.Sigmoid()weights=torch.randn(3)
loss = nn.BCELoss(weight=weights,size_average=False, reduce=False)input = torch.randn(3, requires_grad=True)target = torch.empty(3).random_(2)lossinput = m(input)output = loss(lossinput, target)
print("輸入值:")print(lossinput)print("輸出的目標值:")print(target)print("權重值")print(weights)print("計算loss的結果:")print(output)1234567891011121314151617181920
————————————————版權宣告：本文為CSDN博主「qq_29631521」的原創文章，遵循CC 4.0 BY-SA版權協議，轉載請附上原文出處連結及本宣告。原文連結：https://blog.csdn.net/qq_29631521/article/details/104907401

因上求緣，果上努力~~~~ 作者：希望每天漲粉，轉載請註明原文連結：https://www.cnblogs.com/BlairGrowing/p/15510527.html