def __init__(self, in_planes, planes, stride=1):
super(Bottleneck, self).__init__()
self.conv1 = QWAConv2D(in_planes, planes, kernel_size=1, bias=True)
self.conv2 = QWAConv2D(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=True)
self.conv3 = QWAConv2D(planes, planes * 4, kernel_size=1, bias=True)
self.relu = nn.ReLU6(inplace=True)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.downsample = True
self.shortcut = nn.Sequential(
QWAConv2D(in_planes,
self.expansion * planes,
kernel_size=1,
stride=stride,
bias=True))
else:
self.downsample = False
self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = QWAConv2D(inplanes, planes, kernel_size=1, bias=True)
self.conv2 = QWAConv2D(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=True)
self.conv3 = QWAConv2D(planes, planes * 4, kernel_size=1, bias=True)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return QWAConv2D(in_planes,
out_planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
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 = QWAConv2D(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU6(inplace=True)]
else:
layers += [conv2d, nn.ReLU6(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(
QWAConv2D(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=True),
)
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, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(in_planes, planes, stride)
self.relu = nn.ReLU6(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.downsample = True
self.shortcut = nn.Sequential(
QWAConv2D(in_planes,
self.expansion * planes,
kernel_size=1,
stride=stride,
bias=True))
else:
self.downsample = False
self.stride = stride