deeprobust/image/netmodels/densenet.py

"""
This is an implementation of DenseNet model.

Reference
---------
..[1]Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. "Densely connected convolutional networks." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708. 2017.
..[2]Original implementation: https://github.com/kuangliu/pytorch-cifar
"""
import math

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


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):
    """DenseNet.
    
    """

    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)
        return out

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

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

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

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

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

def test(model, device, test_loader):
    """test.

    Parameters
    ----------
    model :
        model
    device :
        device
    test_loader :
        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

            test_loss += F.cross_entropy(output, target)
            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 train(model, device, train_loader, optimizer, epoch):
    """train.

    Parameters
    ----------
    model :
        model
    device :
        device
    train_loader :
        train_loader
    optimizer :
        optimizer
    epoch :
        epoch
    """
    model.train()

    # lr = util.adjust_learning_rate(optimizer, epoch, args) # don't need it if we use Adam

    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = torch.tensor(data).to(device), torch.tensor(target).to(device)
        optimizer.zero_grad()
        output = model(data)
        # loss = F.nll_loss(output, target)
        loss = F.cross_entropy(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % 10 == 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()/data.shape[0]))