"""
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
[docs]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
[docs]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
[docs]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
[docs]def DenseNet121():
"""DenseNet121.
"""
return DenseNet(Bottleneck, [6,12,24,16], growth_rate=32)
[docs]def DenseNet169():
"""DenseNet169.
"""
return DenseNet(Bottleneck, [6,12,32,32], growth_rate=32)
[docs]def DenseNet201():
"""DenseNet201.
"""
return DenseNet(Bottleneck, [6,12,48,32], growth_rate=32)
[docs]def DenseNet161():
"""DenseNet161.
"""
return DenseNet(Bottleneck, [6,12,36,24], growth_rate=48)
[docs]def densenet_cifar():
"""densenet_cifar.
"""
return DenseNet(Bottleneck, [6,12,24,16], growth_rate=12)
[docs]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)))
[docs]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]))