首先
必須將權(quán)重也轉(zhuǎn)為Tensor的cuda格式；
然后
將該class_weight作為交叉熵函數(shù)對應(yīng)參數(shù)的輸入值。
class_weight = torch.FloatTensor([0.13859937, 0.5821059, 0.63871904, 2.30220396, 7.1588294, 0]).cuda()
補(bǔ)充：關(guān)于pytorch的CrossEntropyLoss的weight參數(shù)
首先這個(gè)weight參數(shù)比想象中的要考慮的多
你可以試試下面代碼
import torch
import torch.nn as nn
inputs = torch.FloatTensor([0,1,0,0,0,1])
outputs = torch.LongTensor([0,1])
inputs = inputs.view((1,3,2))
outputs = outputs.view((1,2))
weight_CE = torch.FloatTensor([1,1,1])
ce = nn.CrossEntropyLoss(ignore_index=255,weight=weight_CE)
loss = ce(inputs,outputs)
print(loss)
這里的手動計(jì)算是：
loss1 = 0 + ln(e0 + e0 + e0) = 1.098
loss2 = 0 + ln(e1 + e0 + e1) = 1.86
求平均 = (loss1 *1 + loss2 *1)/ 2 = 1.4803
加權(quán)呢？
import torch
import torch.nn as nn
inputs = torch.FloatTensor([0,1,0,0,0,1])
outputs = torch.LongTensor([0,1])
inputs = inputs.view((1,3,2))
outputs = outputs.view((1,2))
weight_CE = torch.FloatTensor([1,2,3])
ce = nn.CrossEntropyLoss(ignore_index=255,weight=weight_CE)
loss = ce(inputs,outputs)
print(loss)
手算發(fā)現(xiàn)，并不是單純的那權(quán)重相乘：
loss1 = 0 + ln(e0 + e0 + e0) = 1.098
loss2 = 0 + ln(e1 + e0 + e1) = 1.86
求平均 = (loss1 * 1 + loss2 * 2)/ 2 = 2.4113
而是
loss1 = 0 + ln(e0 + e0 + e0) = 1.098
loss2 = 0 + ln(e1 + e0 + e1) = 1.86
求平均 = (loss1 *1 + loss2 *2) / 3 = 1.6075
發(fā)現(xiàn)了么，加權(quán)后，除以的是權(quán)重的和，不是數(shù)目的和。
我們再驗(yàn)證一遍：
import torch
import torch.nn as nn
inputs = torch.FloatTensor([0,1,2,0,0,0,0,0,0,1,0,0.5])
outputs = torch.LongTensor([0,1,2,2])
inputs = inputs.view((1,3,4))
outputs = outputs.view((1,4))
weight_CE = torch.FloatTensor([1,2,3])
ce = nn.CrossEntropyLoss(weight=weight_CE)
# ce = nn.CrossEntropyLoss(ignore_index=255)
loss = ce(inputs,outputs)
print(loss)
手算：
loss1 = 0 + ln(e0 + e0 + e0) = 1.098
loss2 = 0 + ln(e1 + e0 + e1) = 1.86
loss3 = 0 + ln(e2 + e0 + e0) = 2.2395
loss4 = -0.5 + ln(e0.5 + e0 + e0) = 0.7943
求平均 = (loss1 * 1 + loss2 * 2+loss3 * 3+loss4 * 3) / 9 = 1.5472
可能有人對loss的CE計(jì)算過程有疑問，我這里細(xì)致寫寫交叉熵的計(jì)算過程，就拿最后一個(gè)例子的loss4的計(jì)算說明
以上為個(gè)人經(jīng)驗(yàn)，希望能給大家一個(gè)參考，也希望大家多多支持腳本之家。
您可能感興趣的文章:- PyTorch的SoftMax交叉熵?fù)p失和梯度用法
- pytorch中常用的損失函數(shù)用法說明
- Pytorch十九種損失函數(shù)的使用詳解
- pytorch中交叉熵?fù)p失(nn.CrossEntropyLoss())的計(jì)算過程詳解
- Python機(jī)器學(xué)習(xí)pytorch交叉熵?fù)p失函數(shù)的深刻理解
