CIFAR10分类（AlexNet）

Posted 2022-07-18 liualexsone

#!/usr/bin/env python
# encoding: utf-8
‘‘‘
@author: liualex
@contact: [e-mail]
@software: pycharm
@file: main.py
@time: 2019/8/16 16:21
@desc:
‘‘‘

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import torch.utils.data.dataloader as dataloader
import pdb
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "3"

transform = transforms.Compose(
    [
     transforms.RandomHorizontalFlip(),
     transforms.RandomGrayscale(),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
    ]
)


train_set = torchvision.datasets.CIFAR10(
    root="./data",
    download=True,
    train=True,
    transform=transform
)

train_loader = dataloader.DataLoader(
    dataset=train_set,
    batch_size=100,
    shuffle=False
)

test_set = torchvision.datasets.CIFAR10(
    root="./data",
    download=True,
    train=False,
    transform=transform
)
test_loader = dataloader.DataLoader(
    dataset=test_set,
    batch_size=100,
    shuffle=True
)

class AlexNet(nn.Module):

    def __init__(self, class_num):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(64, 192, kernel_size=3, stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, stride=1, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 4 * 4, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, class_num),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256 * 4 * 4)
        x = self.classifier(x)
        return x


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = AlexNet(10)
model.to(device)

epoches = 100
lr = 0.001
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr)

for epoch in range(epoches):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        output = model(images)
        loss = criterion(output, labels)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print(‘Epoch [/], Loss: :.4f‘
                  .format(epoch + 1, epoches, loss.item()))

with torch.no_grad():
    correct = 0
    total = 0
    for (images, labels) in test_loader:
        images, labels = images.to(device), labels.to(device)
        output = model(images)
        _, predicted = torch.max(output.data, 1)
        total += labels.size(0)
        #pdb.set_trace()
        correct += (predicted == labels).sum().item()

    print("The accuracy of total  images: %".format(total, 100 * correct / total))

卷积计算公式：N = (W − F + 2P )/S+1，其中W指输入图片大小，F指卷积核大小，P指padding，S指stride

结果：由于只迭代了100次，结果只有78.57%。