왜 Value로 사용했는지?

• loss와 accuracy를 함께 넣기 위해서

소스 코드

import torch
import torch.nn as nn

import torch.optim as optim

import torchvision
import torchvision.transforms as transforms

import visdom

vis = visdom.Visdom()
vis.close(env="main")

def value_tracker(value_plot, value, num):
    '''num, loss_value, are Tensor'''
    vis.line(X=num,
             Y=value,
             win = value_plot,
             update='append'
             )
             
device = 'cuda' if torch.cuda.is_available() else 'cpu'

torch.manual_seed(777)
if device =='cuda':
    torch.cuda.manual_seed_all(777)
    
transform_train = transforms.Compose([
    transforms.RandomCrop(32, padding=4),
    transforms.ToTensor(),
    transforms.Normalize(train_data_mean, train_data_std)
])

transform_test = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(train_data_mean, train_data_std)
])

trainset = torchvision.datasets.CIFAR10(root='./cifar10', train=True,
                                        download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=256,
                                          shuffle=True, num_workers=0)

testset = torchvision.datasets.CIFAR10(root='./cifar10', train=False,
                                       download=True, transform=transform_test)

testloader = torch.utils.data.DataLoader(testset, batch_size=256,
                                         shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
           
import resnet

conv1x1=resnet.conv1x1
Bottleneck = resnet.Bottleneck
BasicBlock= resnet.BasicBlock

class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000, zero_init_residual=False):
        super(ResNet, self).__init__()
        self.inplanes = 16
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        #self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        
        self.layer1 = self._make_layer(block, 16, layers[0], stride=1)
        self.layer2 = self._make_layer(block, 32, layers[1], stride=1)
        self.layer3 = self._make_layer(block, 64, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 128, layers[3], stride=2)
        
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(128 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        # Zero-initialize the last BN in each residual branch,
        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        #x.shape =[1, 16, 32,32]
        x = self.bn1(x)
        x = self.relu(x)
        #x = self.maxpool(x)

        x = self.layer1(x)
        #x.shape =[1, 128, 32,32]
        x = self.layer2(x)
        #x.shape =[1, 256, 32,32]
        x = self.layer3(x)
        #x.shape =[1, 512, 16,16]
        x = self.layer4(x)
        #x.shape =[1, 1024, 8,8]
        
        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x
        
resnet50 = ResNet(resnet.Bottleneck, [3, 4, 6, 3], 10, True).to(device) 
#1(conv1) + 9(layer1) + 12(layer2) + 18(layer3) + 9(layer4) +1(fc)= ResNet50

resnet50

a=torch.Tensor(1,3,32,32).to(device)
out = resnet50(a)
print(out)

criterion = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.SGD(resnet50.parameters(), lr = 0.1, momentum = 0.9, weight_decay=5e-4)
lr_sche = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.5)

loss_plt = vis.line(Y=torch.Tensor(1).zero_(),opts=dict(title='loss_tracker', legend=['loss'], showlegend=True))
acc_plt = vis.line(Y=torch.Tensor(1).zero_(),opts=dict(title='Accuracy', legend=['Acc'], showlegend=True))

def acc_check(net, test_set, epoch, save=1):
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_set:
            images, labels = data
            images = images.to(device)
            labels = labels.to(device)
            outputs = net(images)

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

            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    
    acc = (100 * correct / total)
    print('Accuracy of the network on the 10000 test images: %d %%' % acc)
    if save:
        torch.save(net.state_dict(), "./model/model_epoch_{}_acc_{}.pth".format(epoch, int(acc)))
    return acc
    
print(len(trainloader))
epochs = 150

for epoch in range(epochs):  # loop over the dataset multiple times

    running_loss = 0.0
    lr_sche.step()
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data
        inputs = inputs.to(device)
        labels = labels.to(device)

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = resnet50(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 30 == 29:    # print every 30 mini-batches
            value_tracker(loss_plt, torch.Tensor([running_loss/30]), torch.Tensor([i + epoch*len(trainloader) ]))
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 30))
            running_loss = 0.0
    
    #Check Accuracy
    acc = acc_check(resnet50, testloader, epoch, save=1)
    value_tracker(acc_plt, torch.Tensor([acc]), torch.Tensor([epoch]))
    

print('Finished Training')

correct = 0
total = 0

with torch.no_grad():
    for data in testloader:
        images, labels = data
        images = images.to(device)
        labels = labels.to(device)
        outputs = resnet50(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: %d %%' % (
    100 * correct / total))