【图像识别】cifar10数据集用resnet18实现90%测试集精度

学习了大半年的深度学习，开始跑的第一个效果较好的模型

之前的跑的一些不难的模型测试精度大概在82%点几，用了resnet18，效果达到89.69%

在数据处理的时候Pad（4）有用。

 训练100个epoch，多训练可能还会再涨，不过不浪费时间了。图像识别任务到此结束。下次更一些目标检测和对抗攻击。

# coding: UTF-8
# import packages
import os
import torchvision
import torch
import torch.nn as nn

# Device 
device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Transform configuration and data augmentation
transform_train=torchvision.transforms.Compose([
        torchvision.transforms.Pad(4),
        torchvision.transforms.RandomHorizontalFlip(),
        torchvision.transforms.RandomCrop(32),
        # torchvision.transforms.RandomVerticalFlip(),
        # torchvision.transforms.RandomRotation(15),
        torchvision.transforms.ToTensor(),
        torchvision.transforms.Normalize([0.5,0.5,0.5], [0.5,0.5,0.5])
        ])

transform_test=torchvision.transforms.Compose([
        torchvision.transforms.ToTensor(),
        torchvision.transforms.Normalize([0.5,0.5,0.5], [0.5,0.5, 0.5])
        ])
# hyper-parameters
num_classes=10
batch_size=128
learning_rate=0.001
num_epochs=100

# load downloaded dataset
train_dataset = torchvision.datasets.CIFAR10('./data', download=True, train=True, transform=transform_train)
test_dataset = torchvision.datasets.CIFAR10('./data', download=True, train=False, transform=transform_test)

# Data loader 
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# Define 3*3 convolutional neural network
def conv3x3(in_channels, out_channels, stride=1):
    return nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)


class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
    def forward(self, x):
        residual=x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if(self.downsample):
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out


# Define ResNet-18
# Define ResNet-18
class ResNet(torch.nn.Module):
    def __init__(self, block, layers, num_classes):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = torch.nn.BatchNorm2d(16)
        self.relu = torch.nn.ReLU(inplace=True)
        self.layer1 = self._make_layers(block, 16, layers[0])
        self.layer2 = self._make_layers(block, 32, layers[1], 2)
        self.layer3 = self._make_layers(block, 64, layers[2], 2)
        self.layer4 = self._make_layers(block, 128, layers[3], 2)
        self.avg_pool = torch.nn.AdaptiveAvgPool2d((1, 1))
        self.fc = torch.nn.Linear(128, num_classes)
        
    def _make_layers(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = torch.nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                torch.nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return torch.nn.Sequential(*layers)
    
    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

# Make model.
model=ResNet(ResidualBlock, [2,2,2,2], num_classes).to(device=device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

# Train the model
total_step = len(train_loader)
cur_lr = 0.001

for epoch in range(0,num_epochs):
        
    for i, (images, labels) in enumerate(train_loader):
        
        images = images.to(device=device)
        labels = labels.to(device=device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:

            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# -------------- Test the model ---------------
print('\nTest with best model')
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():

    correct = 0
    total = 0

    for images, labels in test_loader:

        images = images.to(device=device)
        labels = labels.to(device=device)
        outputs = model(images)

        _, predicted = torch.max(outputs.data, 1)

        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    
    print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))