def __init__(self, in_planes, planes, stride=1):
super(Bottleneck, self).__init__()
self.conv1 = Quantize(nn.Conv2d)(in_planes,
planes,
kernel_size=1,
bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = Quantize(nn.Conv2d)(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = Quantize(nn.Conv2d)(planes,
self.expansion * planes,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion * planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = nn.Sequential(
Quantize(nn.Conv2d)(in_planes,
self.expansion * planes,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(self.expansion * planes))
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = Quantize(nn.Conv2d)(3,
64,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
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)
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)
self.fc = Quantize(nn.Linear)(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self, features, num_classes=1000):
super(VGG, self).__init__()
self.features = features
self.classifier = nn.Sequential(
Quantize(nn.Linear)(512 * 7 * 7, 4096),
nn.ReLU(True),
nn.Dropout(),
Quantize(nn.Linear)(4096, 4096),
nn.ReLU(True),
nn.Dropout(),
Quantize(nn.Linear)(4096, num_classes),
)
self._initialize_weights()
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_planes = 64
self.conv1 = Quantize(nn.Conv2d)(3,
64,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = Quantize(nn.Linear)(512 * block.expansion, num_classes)
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return Quantize(nn.Conv2d)(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
def __init__(self, num_classes=1000, small_input=False, use_ttq=False):
super(AlexNet, self).__init__()
self.feature_output_size = 256 if small_input else 256 * 6 * 6
if not use_ttq:
Conv2d = nn.Conv2d
Linear = nn.Linear
else:
Conv2d = Quantize(nn.Conv2d)
Linear = Quantize(nn.Linear)
feature_layers = [
Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
Conv2d(64, 192, kernel_size=5, padding=2),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=3, stride=2),
Conv2d(192, 384, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
Conv2d(384, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
Conv2d(256, 256, kernel_size=3, padding=1),
nn.ReLU(inplace=True),
]
if not small_input:
feature_layers.append(nn.MaxPool2d(kernel_size=3, stride=2))
self.features = nn.Sequential(*feature_layers)
fc_size = min(self.feature_output_size, 4096)
self.classifier = nn.Sequential(
nn.Dropout(0.5),
Linear(self.feature_output_size, fc_size),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
Linear(fc_size, fc_size),
nn.ReLU(inplace=True),
Linear(fc_size, num_classes),
)
for m in self.modules():
if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
init.kaiming_uniform(m.weight.data)
if m.bias is not None:
m.bias.data.zero_()
if isinstance(m, TTQ):
init.uniform(m.W_p.data, 0.05, 0.1)
init.uniform(m.W_n.data, -0.1, -0.05)
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = Quantize(nn.Conv2d)(inplanes,
planes,
kernel_size=1,
bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = Quantize(nn.Conv2d)(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = Quantize(nn.Conv2d)(planes,
planes * 4,
kernel_size=1,
bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
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 = Quantize(nn.Conv2d)(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(
Quantize(nn.Conv2d)(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
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):
super().__init__()
self.fc1 = Quantize(nn.Linear)(784, 512)
self.fc2 = Quantize(nn.Linear)(512, 512)
self.fc3 = Quantize(nn.Linear)(512, 512)
self.fc4 = Quantize(nn.Linear)(512, 10)
def __init__(self):
super().__init__()
self.conv1 = Quantize(nn.Conv2d)(1, 10, kernel_size=5)
self.conv2 = Quantize(nn.Conv2d)(10, 20, kernel_size=5)
self.fc1 = Quantize(nn.Linear)(320, 128)
self.fc2 = Quantize(nn.Linear)(128, 10)