BCELoss in PyTorch

*Memos:
My post explains BCE(Binary Cross Entropy) Loss.
My post explains BCEWithLogitsLoss().
My post explains CrossEntropyLoss().
BCELoss() can get the 0D or more D tensor of the zero or more values(float) computed by BCE Loss from the 0D or more D tensor of zero or more elements as shown below:
*Memos:
The 1st argument for initialization is weight(Optional-Default:None-Type:tensor of int, float or bool): *Memos:
- If it’s not given, it’s 1.
- It must be the 0D or more D tensor of zero or more elements.
There is reduction argument for initialization(Optional-Default:'mean'-Type:str). *'none', 'mean' or 'sum' can be selected.
There are size_average and reduce argument for initialization but they are deprecated.
The 1st argument is input(Required-Type:tensor of float). *It must be 0<=x<=1.
The 2nd argument is target(Required-Type:tensor of float). *It must be 0<=y<=1.
input and target must be the same size otherwise there is error.
The empty 1D or more D input and target tensor with reduction='mean' return nan.
The empty 1D or more D input and target tensor with reduction='sum' return 0..

<span>import</span> <span>torch</span>
<span>from</span> <span>torch</span> <span>import</span> <span>nn</span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.4</span><span>,</span> <span>0.8</span><span>,</span> <span>0.6</span><span>,</span> <span>0.3</span><span>,</span> <span>0.0</span><span>,</span> <span>0.5</span><span>])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.2</span><span>,</span> <span>0.9</span><span>,</span> <span>0.4</span><span>,</span> <span>0.1</span><span>,</span> <span>0.8</span><span>,</span> <span>0.5</span><span>])</span>
             <span># -w*(y*log(x)+(1-y)*log(1-x)) </span>             <span># -1*(0.2*log(0.4)+(1-0.2)*log(1-0.4)) </span>             <span># ↓↓↓↓↓↓ </span>             <span># 0.5919 + 0.3618 + 0.7541 + 0.4414 + 80.0 + 0.6931 = 82.8423 </span>             <span># 82.8423 / 6 = 13.8071 </span><span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(7.2500) </span>
<span>bceloss</span>
<span># BCELoss() </span>
<span>print</span><span>(</span><span>bceloss</span><span>.</span><span>weight</span><span>)</span>
<span># None </span>
<span>bceloss</span><span>.</span><span>reduction</span>
<span># 'mean' </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>None</span><span>,</span> <span>reduction</span><span>=</span><span>'</span><span>mean</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>sum</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(82.8423) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>none</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor([0.5919, 0.3618, 0.7541, 0.4414, 80.0000, 0.6931]) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.</span><span>,</span> <span>1.</span><span>,</span> <span>2.</span><span>,</span> <span>3.</span><span>,</span> <span>4.</span><span>,</span> <span>5.</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(54.4433) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0</span><span>,</span> <span>1</span><span>,</span> <span>2</span><span>,</span> <span>3</span><span>,</span> <span>4</span><span>,</span> <span>5</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(54.4433) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span>
              <span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>True</span><span>,</span> <span>False</span><span>,</span> <span>True</span><span>,</span> <span>False</span><span>,</span> <span>True</span><span>,</span> <span>False</span><span>])</span>
          <span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.5577) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>False</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[</span><span>0.4</span><span>,</span> <span>0.8</span><span>,</span> <span>0.6</span><span>],</span> <span>[</span><span>0.3</span><span>,</span> <span>0.0</span><span>,</span> <span>0.5</span><span>]])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[</span><span>0.2</span><span>,</span> <span>0.9</span><span>,</span> <span>0.4</span><span>],</span> <span>[</span><span>0.1</span><span>,</span> <span>0.8</span><span>,</span> <span>0.5</span><span>]])</span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[[</span><span>0.4</span><span>],</span> <span>[</span><span>0.8</span><span>],</span> <span>[</span><span>0.6</span><span>]],</span> <span>[[</span><span>0.3</span><span>],</span> <span>[</span><span>0.0</span><span>],</span> <span>[</span><span>0.5</span><span>]]])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[[</span><span>0.2</span><span>],</span> <span>[</span><span>0.9</span><span>],</span> <span>[</span><span>0.4</span><span>]],</span> <span>[[</span><span>0.1</span><span>],</span> <span>[</span><span>0.8</span><span>],</span> <span>[</span><span>0.5</span><span>]]])</span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([])</span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>mean</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(nan) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>sum</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>import</span> <span>torch</span>
<span>from</span> <span>torch</span> <span>import</span> <span>nn</span>

<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.4</span><span>,</span> <span>0.8</span><span>,</span> <span>0.6</span><span>,</span> <span>0.3</span><span>,</span> <span>0.0</span><span>,</span> <span>0.5</span><span>])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.2</span><span>,</span> <span>0.9</span><span>,</span> <span>0.4</span><span>,</span> <span>0.1</span><span>,</span> <span>0.8</span><span>,</span> <span>0.5</span><span>])</span>
             <span># -w*(y*log(x)+(1-y)*log(1-x)) </span>             <span># -1*(0.2*log(0.4)+(1-0.2)*log(1-0.4)) </span>             <span># ↓↓↓↓↓↓ </span>             <span># 0.5919 + 0.3618 + 0.7541 + 0.4414 + 80.0 + 0.6931 = 82.8423 </span>             <span># 82.8423 / 6 = 13.8071 </span><span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(7.2500) </span>
<span>bceloss</span>
<span># BCELoss() </span>
<span>print</span><span>(</span><span>bceloss</span><span>.</span><span>weight</span><span>)</span>
<span># None </span>
<span>bceloss</span><span>.</span><span>reduction</span>
<span># 'mean' </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>None</span><span>,</span> <span>reduction</span><span>=</span><span>'</span><span>mean</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>sum</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(82.8423) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>none</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor([0.5919, 0.3618, 0.7541, 0.4414, 80.0000, 0.6931]) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.</span><span>,</span> <span>1.</span><span>,</span> <span>2.</span><span>,</span> <span>3.</span><span>,</span> <span>4.</span><span>,</span> <span>5.</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(54.4433) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0.</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0</span><span>,</span> <span>1</span><span>,</span> <span>2</span><span>,</span> <span>3</span><span>,</span> <span>4</span><span>,</span> <span>5</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(54.4433) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>0</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span>
              <span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>True</span><span>,</span> <span>False</span><span>,</span> <span>True</span><span>,</span> <span>False</span><span>,</span> <span>True</span><span>,</span> <span>False</span><span>])</span>
          <span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.5577) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>weight</span><span>=</span><span>torch</span><span>.</span><span>tensor</span><span>([</span><span>False</span><span>]))</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[</span><span>0.4</span><span>,</span> <span>0.8</span><span>,</span> <span>0.6</span><span>],</span> <span>[</span><span>0.3</span><span>,</span> <span>0.0</span><span>,</span> <span>0.5</span><span>]])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[</span><span>0.2</span><span>,</span> <span>0.9</span><span>,</span> <span>0.4</span><span>],</span> <span>[</span><span>0.1</span><span>,</span> <span>0.8</span><span>,</span> <span>0.5</span><span>]])</span>

<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[[</span><span>0.4</span><span>],</span> <span>[</span><span>0.8</span><span>],</span> <span>[</span><span>0.6</span><span>]],</span> <span>[[</span><span>0.3</span><span>],</span> <span>[</span><span>0.0</span><span>],</span> <span>[</span><span>0.5</span><span>]]])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([[[</span><span>0.2</span><span>],</span> <span>[</span><span>0.9</span><span>],</span> <span>[</span><span>0.4</span><span>]],</span> <span>[[</span><span>0.1</span><span>],</span> <span>[</span><span>0.8</span><span>],</span> <span>[</span><span>0.5</span><span>]]])</span>

<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>()</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(13.8071) </span>
<span>tensor1</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([])</span>
<span>tensor2</span> <span>=</span> <span>torch</span><span>.</span><span>tensor</span><span>([])</span>

<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>mean</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(nan) </span>
<span>bceloss</span> <span>=</span> <span>nn</span><span>.</span><span>BCELoss</span><span>(</span><span>reduction</span><span>=</span><span>'</span><span>sum</span><span>'</span><span>)</span>
<span>bceloss</span><span>(</span><span>input</span><span>=</span><span>tensor1</span><span>,</span> <span>target</span><span>=</span><span>tensor2</span><span>)</span>
<span># tensor(0.) </span>
import torch
from torch import nn

tensor1 = torch.tensor([0.4, 0.8, 0.6, 0.3, 0.0, 0.5])
tensor2 = torch.tensor([0.2, 0.9, 0.4, 0.1, 0.8, 0.5])
             # -w*(y*log(x)+(1-y)*log(1-x))              # -1*(0.2*log(0.4)+(1-0.2)*log(1-0.4))              # ↓↓↓↓↓↓              # 0.5919 + 0.3618 + 0.7541 + 0.4414 + 80.0 + 0.6931 = 82.8423              # 82.8423 / 6 = 13.8071 bceloss = nn.BCELoss()
bceloss(input=tensor1, target=tensor2)
# tensor(7.2500) 
bceloss
# BCELoss() 
print(bceloss.weight)
# None 
bceloss.reduction
# 'mean' 
bceloss = nn.BCELoss(weight=None, reduction='mean')
bceloss(input=tensor1, target=tensor2)
# tensor(13.8071) 
bceloss = nn.BCELoss(reduction='sum')
bceloss(input=tensor1, target=tensor2)
# tensor(82.8423) 
bceloss = nn.BCELoss(reduction='none')
bceloss(input=tensor1, target=tensor2)
# tensor([0.5919, 0.3618, 0.7541, 0.4414, 80.0000, 0.6931]) 
bceloss = nn.BCELoss(weight=torch.tensor([0., 1., 2., 3., 4., 5.]))
bceloss(input=tensor1, target=tensor2)
# tensor(54.4433) 
bceloss = nn.BCELoss(weight=torch.tensor([0.]))
bceloss(input=tensor1, target=tensor2)
# tensor(0.) 
bceloss = nn.BCELoss(weight=torch.tensor([0, 1, 2, 3, 4, 5]))
bceloss(input=tensor1, target=tensor2)
# tensor(54.4433) 
bceloss = nn.BCELoss(weight=torch.tensor([0]))
bceloss(input=tensor1, target=tensor2)
# tensor(0.) 
bceloss = nn.BCELoss(
              weight=torch.tensor([True, False, True, False, True, False])
          )
bceloss(input=tensor1, target=tensor2)
# tensor(13.5577) 
bceloss = nn.BCELoss(weight=torch.tensor([False]))
bceloss(input=tensor1, target=tensor2)
# tensor(0.) 
tensor1 = torch.tensor([[0.4, 0.8, 0.6], [0.3, 0.0, 0.5]])
tensor2 = torch.tensor([[0.2, 0.9, 0.4], [0.1, 0.8, 0.5]])

bceloss = nn.BCELoss()
bceloss(input=tensor1, target=tensor2)
# tensor(13.8071) 
tensor1 = torch.tensor([[[0.4], [0.8], [0.6]], [[0.3], [0.0], [0.5]]])
tensor2 = torch.tensor([[[0.2], [0.9], [0.4]], [[0.1], [0.8], [0.5]]])

bceloss = nn.BCELoss()
bceloss(input=tensor1, target=tensor2)
# tensor(13.8071) 
tensor1 = torch.tensor([])
tensor2 = torch.tensor([])

bceloss = nn.BCELoss(reduction='mean')
bceloss(input=tensor1, target=tensor2)
# tensor(nan) 
bceloss = nn.BCELoss(reduction='sum')
bceloss(input=tensor1, target=tensor2)
# tensor(0.)
Enter fullscreen mode Exit fullscreen mode
原文链接：BCELoss in PyTorch
展开阅读全文
文章版权声明 1、本网站名称：拾光赋
2、本站永久网址：https://www.blogs.ink
3、本网站的文章部分内容可能来源于网络，仅供大家学习与参考，如有侵权，请联系站长QQ：805375623进行删除处理。
4、本站一切资源不代表本站立场，并不代表本站赞同其观点和对其真实性负责。
5、本站一律禁止以任何方式发布或转载任何违法的相关信息，访客发现请向站长举报
6、本站资源大多存储在云盘，如发现链接失效，请联系我们我们会第一时间更新。
THE END