def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1,
norm_layer=None):
super(BasicBlock, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError(
'BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError(
"Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.share1 = tqt.fold.ShareQuant()
self.share2 = tqt.fold.ShareQuant()
self.relu2 = nn.ReLU(inplace=True)
self.stride = stride
def __init__(self,
inplanes,
planes,
stride=1,
downsample=None,
groups=1,
base_width=64,
dilation=1,
norm_layer=None):
super(Bottleneck, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.)) * groups
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.share1 = tqt.fold.ShareQuant()
self.share2 = tqt.fold.ShareQuant()
self.relu2 = nn.ReLU(inplace=True)
self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride=stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu1 = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.share1 = tqt.fold.ShareQuant()
self.share2 = tqt.fold.ShareQuant()
self.relu2 = nn.ReLU(inplace=True)
self.stride = stride
def __init__(self, block, layers, num_classes=10):
super(ResNet, self).__init__()
self.inplanes = 16
# self.proc = ['conv1', 'bn1', 'relu']
self.proc = [
'conv1', 'bn1', 'relu', 'layer1', 'layer2', 'layer3', 'avgpool',
'fc', 'bn2'
]
self.conv1 = nn.Conv2d(3,
16,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(16)
self.relu = nn.ReLU(inplace=True)
self.layer1 = self._make_layer(block, 16, layers[0])
self.layer2 = self._make_layer(block, 32, layers[1], stride=2)
self.layer3 = self._make_layer(block, 64, layers[2], stride=2)
self.avgpool = nn.AvgPool2d(8, stride=1)
self.fc = nn.Conv2d(64 * block.expansion, num_classes, 1, bias=False)
self.bn2 = nn.BatchNorm2d(num_classes)
for m in self.modules():
if isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1, 6, 5, padding=2)
self.mp1 = nn.MaxPool2d((2, 2))
self.relu1 = nn.ReLU()
self.conv2 = nn.Conv2d(6, 16, 5)
self.mp2 = nn.MaxPool2d((2, 2))
self.relu2 = nn.ReLU()
self.conv3 = nn.Conv2d(16, 120, 5)
self.relu3 = nn.ReLU()
self.fc1 = nn.Linear(120, 84)
self.relu4 = nn.ReLU()
self.fc2 = nn.Linear(84, 10)
self.proc = [
'conv1', 'mp1', 'relu1', 'conv2', 'mp2', 'relu2', 'conv3', 'relu3',
'fc1', 'relu4', 'fc2'
]
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.proc = ['conv1', 'bn1', 'relu', 'conv2', 'bn2']
self.conv1 = conv3x3(inplanes, planes, stride=stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def __init__(self,
block,
layers,
num_classes=1000,
zero_init_residual=False,
groups=1,
width_per_group=64,
replace_stride_with_dilation=None,
norm_layer=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(
replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3,
self.inplanes,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
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,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block,
256,
layers[2],
stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block,
512,
layers[3],
stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = nn.AvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
torch.nn.init.kaiming_normal_(m.weight,
mode='fan_out',
nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d)):
torch.nn.init.constant_(m.weight, 1)
torch.nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)