def __init__(self, in_planes, out_planes, stride, dropRate=0.0):
super(BasicBlock, self).__init__()
self.bn1 = custom.BN_Class(in_planes)
self.relu1 = nn.ReLU(inplace=True)
self.conv1 = custom.Con2d_Class(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = custom.BN_Class(out_planes)
self.relu2 = nn.ReLU(inplace=True)
self.conv2 = custom.Con2d_Class(out_planes,
out_planes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.droprate = dropRate
self.equalInOut = (in_planes == out_planes)
self.convShortcut = (not self.equalInOut) and custom.Con2d_Class(
in_planes,
out_planes,
kernel_size=1,
stride=stride,
padding=0,
bias=False) or None
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = custom.Con2d_Class(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = custom.BN_Class(64)
self.relu = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.classifier = custom.Linear_Class(512 * block.expansion,
num_classes)
for m in self.modules():
if isinstance(m, custom.Con2d_Class):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, custom.BN_Class):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self, inplanes, expansion=4, growthRate=12, dropRate=0):
super(Bottleneck, self).__init__()
planes = expansion * growthRate
self.bn1 = nn.BatchNorm2d(inplanes)
self.conv1 = custom.Con2d_Class(inplanes,
planes,
kernel_size=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv2 = custom.Con2d_Class(planes,
growthRate,
kernel_size=3,
padding=1,
bias=False)
self.relu = nn.ReLU(inplace=True)
self.dropRate = dropRate
def __init__(self, in_channels, out_channels, stride, cardinality,
widen_factor):
""" Constructor
Args:
in_channels: input channel dimensionality
out_channels: output channel dimensionality
stride: conv stride. Replaces pooling layer.
cardinality: num of convolution groups.
widen_factor: factor to reduce the input dimensionality before convolution.
"""
super(ResNeXtBottleneck, self).__init__()
D = cardinality * out_channels // widen_factor
self.conv_reduce = custom.Con2d_Class(in_channels,
D,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn_reduce = nn.BatchNorm2d(D)
self.conv_conv = custom.Con2d_Class(D,
D,
kernel_size=3,
stride=stride,
padding=1,
groups=cardinality,
bias=False)
self.bn = nn.BatchNorm2d(D)
self.conv_expand = custom.Con2d_Class(D,
out_channels,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.bn_expand = nn.BatchNorm2d(out_channels)
self.shortcut = nn.Sequential()
if in_channels != out_channels:
self.shortcut.add_module(
'shortcut_conv',
custom.Con2d_Class(in_channels,
out_channels,
kernel_size=1,
stride=stride,
padding=0,
bias=False))
self.shortcut.add_module('shortcut_bn',
nn.BatchNorm2d(out_channels))
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return custom.Con2d_Class(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def __init__(self, inplanes, outplanes):
super(Transition, self).__init__()
self.bn1 = nn.BatchNorm2d(inplanes)
self.conv1 = custom.Con2d_Class(inplanes,
outplanes,
kernel_size=1,
bias=False)
self.relu = nn.ReLU(inplace=True)
def __init__(self,
depth=22,
block_name='BasicBlock',
dropRate=0,
num_classes=10,
growthRate=12,
compressionRate=2):
super(DenseNet, self).__init__()
# Model type specifies number of layers for CIFAR-10 model
if block_name.lower() == 'basicblock':
assert (
depth - 4
) % 3 == 0, 'When use basicblock, depth should be 3n+4, e.g. 40, 100, 190, 250'
n = (depth - 4) // 3
block = BasicBlock
elif block_name.lower() == 'bottleneck':
assert (
depth - 4
) % 6 == 0, 'When use bottleneck, depth should be 6n+4, e.g. 40, 100, 190, 250'
n = (depth - 4) // 6
block = Bottleneck
else:
raise ValueError('block_name shoule be Basicblock or Bottleneck')
self.growthRate = growthRate
self.dropRate = dropRate
# self.inplanes is a global variable used across multiple
# helper functions
self.inplanes = growthRate * 2
self.conv1 = custom.Con2d_Class(3,
self.inplanes,
kernel_size=3,
padding=1,
bias=False)
self.dense1 = self._make_denseblock(block, n)
self.trans1 = self._make_transition(compressionRate)
self.dense2 = self._make_denseblock(block, n)
self.trans2 = self._make_transition(compressionRate)
self.dense3 = self._make_denseblock(block, n)
self.bn = nn.BatchNorm2d(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.avgpool = nn.AvgPool2d(8)
self.classifier = custom.Linear_Class(self.inplanes, num_classes)
# Weight initialization
for m in self.modules():
if isinstance(m, custom.Linear_Class) or isinstance(
m, custom.Con2d_Class):
init.kaiming_normal_(m.weight)
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
if m.bias is not None:
m.bias.data.zero_()
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = custom.Con2d_Class(inplanes,
planes,
kernel_size=1,
bias=False)
self.bn1 = custom.BN_Class(planes)
self.conv2 = custom.Con2d_Class(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = custom.BN_Class(planes)
self.conv3 = custom.Con2d_Class(planes,
planes * 4,
kernel_size=1,
bias=False)
self.bn3 = custom.BN_Class(planes * 4)
self.relu = nn.ReLU(inplace=False)
self.downsample = downsample
self.stride = stride
def make_layers(cfg, batch_norm=False):
layers = []
in_channels = 3
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = custom.Con2d_Class(in_channels,
v,
kernel_size=3,
padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
custom.Con2d_Class(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False), )
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def __init__(self,
cardinality,
depth,
num_classes,
widen_factor=4,
dropRate=0):
""" Constructor
Args:
cardinality: number of convolution groups.
depth: number of layers.
num_classes: number of classes
widen_factor: factor to adjust the channel dimensionality
"""
super(CifarResNeXt, self).__init__()
self.cardinality = cardinality
self.depth = depth
self.block_depth = (self.depth - 2) // 9
self.widen_factor = widen_factor
self.num_classes = num_classes
self.output_size = 64
self.stages = [
64, 64 * self.widen_factor, 128 * self.widen_factor,
256 * self.widen_factor
]
self.conv_1_3x3 = custom.Con2d_Class(3, 64, 3, 1, 1, bias=False)
self.bn_1 = nn.BatchNorm2d(64)
self.stage_1 = self.block('stage_1', self.stages[0], self.stages[1], 1)
self.stage_2 = self.block('stage_2', self.stages[1], self.stages[2], 2)
self.stage_3 = self.block('stage_3', self.stages[2], self.stages[3], 2)
self.classifier = custom.Linear_Class(1024, num_classes)
init.kaiming_normal(self.classifier.weight)
for m in self.modules():
if isinstance(m, custom.Linear_Class) or isinstance(
m, custom.Con2d_Class):
init.kaiming_normal_(m.weight)
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
if m.bias is not None:
m.bias.data.zero_()
def __init__(self, depth, num_classes=1000, block_name='BasicBlock'):
super(ResNet, self).__init__()
# Model type specifies number of layers for CIFAR-10 model
if block_name.lower() == 'basicblock':
assert (
depth - 2
) % 6 == 0, 'When use basicblock, depth should be 6n+2, e.g. 20, 32, 44, 56, 110, 1202'
n = (depth - 2) // 6
block = BasicBlock
elif block_name.lower() == 'bottleneck':
assert (
depth - 2
) % 9 == 0, 'When use bottleneck, depth should be 9n+2, e.g. 20, 29, 47, 56, 110, 1199'
n = (depth - 2) // 9
block = Bottleneck
else:
raise ValueError('block_name shoule be Basicblock or Bottleneck')
self.inplanes = 16
self.conv1 = custom.Con2d_Class(3,
16,
kernel_size=3,
padding=1,
bias=False)
self.bn1 = custom.BN_Class(16)
self.relu = nn.ReLU(inplace=False)
self.layer1 = self._make_layer(block, 16, n)
self.layer2 = self._make_layer(block, 32, n, stride=2)
self.layer3 = self._make_layer(block, 64, n, stride=2)
self.avgpool = nn.AvgPool2d(8)
self.classifier = custom.Linear_Class(64 * block.expansion,
num_classes)
for m in self.modules():
if isinstance(m, custom.Linear_Class) or isinstance(
m, custom.Con2d_Class):
init.kaiming_normal_(m.weight)
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, custom.BN_Class):
m.weight.data.fill_(1)
if m.bias is not None:
m.bias.data.zero_()
def __init__(self, depth, num_classes, widen_factor=1, dropRate=0.0):
super(WideResNet, self).__init__()
nChannels = [
16, 16 * widen_factor, 32 * widen_factor, 64 * widen_factor
]
assert (depth - 4) % 6 == 0, 'depth should be 6n+4'
n = (depth - 4) // 6
block = BasicBlock
# 1st conv before any network block
self.conv1 = custom.Con2d_Class(3,
nChannels[0],
kernel_size=3,
stride=1,
padding=1,
bias=False)
# 1st block
self.block1 = NetworkBlock(n, nChannels[0], nChannels[1], block, 1,
dropRate)
# 2nd block
self.block2 = NetworkBlock(n, nChannels[1], nChannels[2], block, 2,
dropRate)
# 3rd block
self.block3 = NetworkBlock(n, nChannels[2], nChannels[3], block, 2,
dropRate)
# global average pooling and classifier
self.bn1 = custom.BN_Class(nChannels[3])
self.relu = nn.ReLU(inplace=True)
self.classifier = custom.Linear_Class(nChannels[3], num_classes)
self.nChannels = nChannels[3]
for m in self.modules():
if isinstance(m, custom.Con2d_Class):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, custom.BN_Class):
m.weight.data.fill_(1)
m.bias.data.zero_()
elif isinstance(m, custom.Linear_Class):
if m.bias is not None:
m.bias.data.zero_()