pytorch实现resnet18（CIFAR10数据集，92%的准确率）

最新推荐文章于 2024-06-06 18:00:00 发布

「已注销」

最新推荐文章于 2024-06-06 18:00:00 发布

阅读量1.4k

点赞数 1

分类专栏：深度学习文章标签： pytorch 深度学习 python

本文链接：https://blog.csdn.net/m0_73817310/article/details/127196012

版权

本文详细介绍了如何使用PyTorch实现ResNet18模型，并在CIFAR10数据集上进行训练，最终获得了92%的高准确率。内容涵盖了数据预处理、模型构建、训练过程及结果分析。

摘要由CSDN通过智能技术生成

导入相关的库

import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import time
import torch.nn.functional as F

导入数据

train_transform = transforms.Compose([
    transforms.RandomResizedCrop(224),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor()
])

val_transform = transforms.Compose([
   transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor()
])

batch_size = 64
 
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=train_transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
                                          shuffle=True, num_workers=2)
 
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=val_transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
                                         shuffle=False, num_workers=2)

Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz

170499072/? [00:05<00:00, 32627522.63it/s]

Extracting ./data/cifar-10-python.tar.gz to ./data
Files already downloaded and verified

device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Using {device} device")

Using cuda device

class Residual(nn.Module):  
    def __init__(self, in_channels, out_channels, use_1x1conv=False, stride=1):
        super(Residual, self).__init__()
        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1, stride=stride)
        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
        return F.relu(Y + X)


def resnet_block(in_channels, out_channels, num_residuals, first_block=False):
    if first_block:
        assert in_channels == out_channels # 第一个模块的通道数同输入通道数一致
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(in_channels, out_channels, use_1x1conv=True, stride=2))
        else:
            blk.append(Residual(out_channels, out_channels))
    return nn.Sequential(*blk)



net = nn.Sequential(
        nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),
        nn.BatchNorm2d(64), 
        nn.ReLU(),
        nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
 
net.add_module("resnet_block1", resnet_block(64, 64, 2, first_block=True))
net.add_module("resnet_block2", resnet_block(64, 128, 2))
net.add_module("resnet_block3", resnet_block(128, 256, 2))
net.add_module("resnet_block4", resnet_block(256, 512, 2))
 
fc = nn.Sequential(
    nn.AvgPool2d(7,7),
    nn.Flatten(),
    nn.Dropout(0.5),
    nn.Linear(512, 10),
 
)
 
net.add_module("fc", fc) 
model = net.to(device)
model

Sequential(
  (0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
  (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (2): ReLU()
  (3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (resnet_block1): Sequential(
    (0): Residual(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats&#