import math
import torch
import torch.nn as nn
import torch.nn.functional as F
NUM_CLASSES = 10
[docs]class AlexNet(nn.Module):
"""
Modified AlexNet for CIFAR
From: https://github.com/icpm/pytorch-cifar10/blob/master/models/AlexNet.py
"""
def __init__(self, num_classes=NUM_CLASSES):
super(AlexNet, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2),
nn.Conv2d(64, 192, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2),
nn.Conv2d(192, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.Conv2d(256, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2),
)
self.classifier = nn.Sequential(
nn.Dropout(),
nn.Linear(256 * 2 * 2, 4096),
nn.ReLU(inplace=True),
nn.Dropout(),
nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, num_classes),
)
[docs] def forward(self, x):
x = self.features(x)
x = x.view(x.size(0), 256 * 2 * 2)
x = self.classifier(x)
return x
[docs]class Bottleneck(nn.Module):
"""
Bottleneck module in DenseNet Arch.
See: https://arxiv.org/abs/1608.06993
"""
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)
[docs] def forward(self, x):
y = self.conv1(F.relu(self.bn1(x)))
y = self.conv2(F.relu(self.bn2(y)))
x = torch.cat([y, x], 1)
return x
[docs]class Transition(nn.Module):
"""
Transition module in DenseNet Arch.
See: https://arxiv.org/abs/1608.06993
"""
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)
[docs] def forward(self, x):
x = self.conv(F.relu(self.bn(x)))
x = F.avg_pool2d(x, 2)
return x
[docs]class DenseNet(nn.Module):
"""
From: https://github.com/icpm/pytorch-cifar10/blob/master/models/DenseNet.py
"""
def __init__(self, block, num_block, growth_rate=12, reduction=0.5, num_classes=NUM_CLASSES):
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, num_block[0])
num_planes += num_block[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, num_block[1])
num_planes += num_block[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, num_block[2])
num_planes += num_block[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, num_block[3])
num_planes += num_block[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, num_block):
layers = []
for i in range(num_block):
layers.append(block(in_planes, self.growth_rate))
in_planes += self.growth_rate
return nn.Sequential(*layers)
[docs] def forward(self, x):
x = self.conv1(x)
x = self.trans1(self.dense1(x))
x = self.trans2(self.dense2(x))
x = self.trans3(self.dense3(x))
x = self.dense4(x)
x = F.avg_pool2d(F.relu(self.bn(x)), 4)
x = x.view(x.size(0), -1)
x = self.linear(x)
return x
[docs]def DenseNet121():
return DenseNet(Bottleneck, [6, 12, 24, 16], growth_rate=32)
[docs]def DenseNet169():
return DenseNet(Bottleneck, [6, 12, 32, 32], growth_rate=32)
[docs]def DenseNet201():
return DenseNet(Bottleneck, [6, 12, 48, 32], growth_rate=32)
[docs]def DenseNet161():
return DenseNet(Bottleneck, [6, 12, 36, 24], growth_rate=48)
[docs]def densenet_cifar():
return DenseNet(Bottleneck, [6, 12, 24, 16], growth_rate=12)