卷积神经网络学习

最新推荐文章于 2022-10-21 00:48:29 发布

「已注销」

最新推荐文章于 2022-10-21 00:48:29 发布

阅读量1k

点赞数

文章标签： python

本文链接：https://blog.csdn.net/m0_55233369/article/details/123658220

版权

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
dataset = torchvision.datasets.CIFAR10("F:/projects/venv/imgs", train=False, transform=torchvision.transforms.ToTensor(),
                                       download=True)
dataload = DataLoader(dataset, batch_size=64)

class convd(nn.Module):
    def __init__(self):
        super(convd, self).__init__()
        self.model = 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.model(x)
Convd=convd()
print(Convd)
loss=nn.CrossEntropyLoss()
optic=torch.optim.SGD(Convd.parameters(),lr=0.01)
for epoch in range(20):
    running_loss=0
    for data in dataload:
        imgs, target = data
        output = Convd(imgs)
        result_loss=loss(output,target)
        optic.zero_grad()
        result_loss.backward()
        optic.step()
        running_loss=running_loss+result_loss
    print("输出损失",running_loss)