8-pytorch-损失函数与反向传播

b站小土堆pytorch教程学习笔记

根据loss更新模型参数
1.计算实际输出与目标之间的差距
2.为我们更新输出提供一定的依据（反向传播）

在这里插入图片描述

1 MSEloss

import torch
from torch.nn import L1Loss
from torch import nn

inputs=torch.tensor([1,2,3],dtype=torch.float32)
targets=torch.tensor([1,2,5],dtype=torch.float32)

inputs=torch.reshape(inputs,(-1,1,1,3))
targets=torch.reshape(targets,(-1,1,1,3))

loss=L1Loss()
result=loss(inputs,targets)

loss_mse=nn.MSELoss()
result_mse=loss_mse(inputs,targets)

print(result)
print(result_mse)

tensor(0.6667)
tensor(1.3333)

2 Cross EntropyLoss

在这里插入图片描述

x=torch.tensor([0.1,0.2,0.3])#需要reshape为要求的(batch_size,class)
y=torch.tensor([1])#target已经为要求的batch_size无需reshape
x=torch.reshape(x,(-1,3))
loss_cross=nn.CrossEntropyLoss()
result_cross=loss_cross(x,y)
print(result_cross)

tensor(1.1019)

3 在具体的神经网络中使用loss

import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset=torchvision.datasets.CIFAR10('dataset',train=False,
                                     transform=torchvision.transforms.ToTensor(),
                                     download=True)
dataloader=DataLoader(dataset,batch_size=1)

class Han(nn.Module):
    def __init__(self):
        super(Han, self).__init__()
        self.model1=Sequential(
            Conv2d(3,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,64,5,padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024,64),
            Linear(64,10)
        )

    def forward(self,x):
        x=self.model1(x)
        return x

loss=nn.CrossEntropyLoss()
han=Han()
for data in dataloader:
    imgs,target=data
    output=han(imgs)
    # print(target)
    # print(output)
    result_loss=loss(output,target)
    print(result_loss)

*tensor([7])
tensor([[ 0.0057, -0.0201, -0.0796, 0.0556, -0.0625, 0.0125, -0.0413, -0.0056,
0.0624, -0.1072]], grad_fn=)…

tensor(2.2664, grad_fn=)…

4 反向传播优化器

定义优化器
将待更新的每个参数梯度清零
调用损失函数的反向传播函数求出每个节点的梯度
使用step函数对模型的每个参数调优

import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

dataset=torchvision.datasets.CIFAR10('dataset',train=False,
                                     transform=torchvision.transforms.ToTensor(),
                                     download=True)
dataloader=DataLoader(dataset,batch_size=64)

class Han(nn.Module):
    def __init__(self):
        super(Han, self).__init__()
        self.model1=Sequential(
            Conv2d(3,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,32,5,padding=2),
            MaxPool2d(2),
            Conv2d(32,64,5,padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024,64),
            Linear(64,10)
        )

    def forward(self,x):
        x=self.model1(x)
        return x

loss=nn.CrossEntropyLoss()
han=Han()
optim=torch.optim.SGD(han.parameters(),lr=0.01)

for epoch in range(5):
    running_loss=0.0#一个epoch结束的loss和
    for data in dataloader:
        imgs,target=data
        output=han(imgs)

        result_loss=loss(output,target)#每次迭代的loss
        optim.zero_grad()#将网络中每个可调节参数对应的梯度调为0
        result_loss.backward()#优化器需要每个参数的梯度，使用反向传播获得
        optim.step()#对每个参数调优
        running_loss=running_loss+result_loss
    print(running_loss)

Files already downloaded and verified
tensor(361.0316, grad_fn=)
tensor(357.6938, grad_fn=)
tensor(343.0560, grad_fn=)
tensor(321.8132, grad_fn=)
tensor(313.3173, grad_fn=)

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：/a/408522.html

如若内容造成侵权/违法违规/事实不符，请联系我们进行投诉反馈qq邮箱809451989@qq.com，一经查实，立即删除！