cifar_classifier.py

import argparse
import dataloader
import math

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

import torchvision.transforms as transforms



'''DenseNet in PyTorch.'''
# Refer to: https://github.com/kuangliu/pytorch-cifar/blob/master/models/densenet.py 



class Bottleneck(nn.Module):
    def __init__(self, in_planes, growth_rate):
        super(Bottleneck, self).__init__()
        self.bn1 = nn.BatchNorm2d(in_planes)
        self.conv1 = nn.Conv2d(in_planes, 4*growth_rate, kernel_size=1, bias=False)
        self.bn2 = nn.BatchNorm2d(4*growth_rate)
        self.conv2 = nn.Conv2d(4*growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)

    def forward(self, x):
        out = self.conv1(F.relu(self.bn1(x)))
        out = self.conv2(F.relu(self.bn2(out)))
        out = torch.cat([out,x], 1)
        return out


class Transition(nn.Module):
    def __init__(self, in_planes, out_planes):
        super(Transition, self).__init__()
        self.bn = nn.BatchNorm2d(in_planes)
        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=1, bias=False)

    def forward(self, x):
        out = self.conv(F.relu(self.bn(x)))
        out = F.avg_pool2d(out, 2)
        return out


class DenseNet(nn.Module):
    def __init__(self, block, nblocks, growth_rate=12, reduction=0.5, num_classes=10):
        super(DenseNet, self).__init__()
        self.growth_rate = growth_rate

        num_planes = 2*growth_rate
        self.conv1 = nn.Conv2d(3, num_planes, kernel_size=3, padding=1, bias=False)

        self.dense1 = self._make_dense_layers(block, num_planes, nblocks[0])
        num_planes += nblocks[0]*growth_rate
        out_planes = int(math.floor(num_planes*reduction))
        self.trans1 = Transition(num_planes, out_planes)
        num_planes = out_planes

        self.dense2 = self._make_dense_layers(block, num_planes, nblocks[1])
        num_planes += nblocks[1]*growth_rate
        out_planes = int(math.floor(num_planes*reduction))
        self.trans2 = Transition(num_planes, out_planes)
        num_planes = out_planes

        self.dense3 = self._make_dense_layers(block, num_planes, nblocks[2])
        num_planes += nblocks[2]*growth_rate
        out_planes = int(math.floor(num_planes*reduction))
        self.trans3 = Transition(num_planes, out_planes)
        num_planes = out_planes

        self.dense4 = self._make_dense_layers(block, num_planes, nblocks[3])
        num_planes += nblocks[3]*growth_rate

        self.bn = nn.BatchNorm2d(num_planes)
        self.linear = nn.Linear(num_planes, num_classes)

    def _make_dense_layers(self, block, in_planes, nblock):
        layers = []
        for i in range(nblock):
            layers.append(block(in_planes, self.growth_rate))
            in_planes += self.growth_rate
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv1(x)
        out = self.trans1(self.dense1(out))
        out = self.trans2(self.dense2(out))
        out = self.trans3(self.dense3(out))
        out = self.dense4(out)
        out = F.avg_pool2d(F.relu(self.bn(out)), 4)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        out = F.log_softmax(out, dim=1)
        return out

def DenseNet121():
    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=32)

def DenseNet169():
    return DenseNet(Bottleneck, [6,12,32,32], growth_rate=32)

def DenseNet201():
    return DenseNet(Bottleneck, [6,12,48,32], growth_rate=32)

def DenseNet161():
    return DenseNet(Bottleneck, [6,12,36,24], growth_rate=48)

def densenet_cifar():
    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=12)

# def uni_test():
#     net = densenet_cifar()
#     x = torch.randn(1,3,32,32)
#     y = net(x)
#     print(y)


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
            if args.dry_run:
                break


def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Example')
    parser.add_argument('--batch-size', type=int, default=256, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=14, metavar='N',
                        help='number of epochs to train (default: 14)')
    parser.add_argument('--lr', type=float, default=1e-2)
    parser.add_argument('--weight-decay', type=float, default=5e-4)
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--dry-run', action='store_true', default=False,
                        help='quickly check a single pass')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--save-model', action='store_true', default=False,
                        help='For Saving the current Model')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    transform_train = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor()
    ])

    train_dataloader, test_dataloader = dataloader.load_data('CIFAR10', args.batch_size, train_transform=transform_train)

    model = DenseNet121().to(device)
    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=0.9, weight_decay=args.weight_decay)
    scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=args.epochs)

    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_dataloader, optimizer, epoch)
        test(model, device, test_dataloader)
        scheduler.step()

    if args.save_model:
        torch.save(model.state_dict(), "./pretrained/cifar_densenet.pth")


if __name__ == '__main__':
    main()