【LLM学习之路】9月16日 第六天

损失函数

L1Loss

可以取平均也可以求和

参数解析

input （N，*） N是batchsize，星号代表可以是任意维度 不是输入的参数，只是描述数据

target 形状要同上

MSELoss平方差

CrossEntropyLoss交叉熵

inputs的形状要是(N, C) N是批次大小

x = torch.tensor([0.1,0.2,0.3]) #形状为 (3,) 的 1D 张量
y = torch.tensor([1])
x = torch.reshape(x,(1,3)) #inputs 的形状要是 (N, C)
loss_cross = nn.CrossEntropyLoss()
result_cross = loss_cross(x,y)

反向传播

result_loss.backward()

优化器

套路是这样的

optim = torch.optim.SGD(tudui.parameters(),loss=0.01)
optim.zero_grad() 进行梯度清零
result_loss.backward() 反向传播计算梯度
optim.step() 对模型参数进行调优

后面自己添加了如何使用显卡

import torch
import torchvision.datasets
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
# 检查是否有 GPU 可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using device: {device}")

dataset = torchvision.datasets.CIFAR10("./data",train = False,download=True,transform=torchvision.transforms.ToTensor())
dataloader = DataLoader(dataset,batch_size=1)
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui,self).__init__()
        self.conv1 = Conv2d(3,32,5,padding=2)
        self.maxpool1 = MaxPool2d(2)
        self.conv2 = Conv2d(32,32,5,padding=2)
        self.maxpool2 = MaxPool2d(2)
        self.conv3 = Conv2d(32,64,5,padding=2)
        self.maxpool3 = MaxPool2d(2)
        self.flatten = Flatten()
        self.linear1 = Linear(1024,64)
        self.linear2 = Linear(64,10)

        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()
tudui = Tudui().to(device)
optim = torch.optim.SGD(tudui.parameters(),lr=0.01)

for epoch in range(20):
    running_loss = 0.0
    for data in dataloader:
        imgs,targets = data
        imgs,targets = imgs.to(device), targets.to(device)
        outputs = tudui(imgs)
        # print(outputs)
        # print(targets)
        result_loss = loss(outputs,targets)
        optim.zero_grad()
        result_loss.backward()
        optim.step()
        # print("ok")
        running_loss = result_loss + running_loss

    print(running_loss)

完整的模型验证套路

利用已经训练好的模型，然后给它提供输入