def __init__(self, args, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.relu1 = ReLuPCA(args, planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm2d(planes)
self.relu2 = ReLuPCA(args, planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu3 = ReLuPCA(args, planes * self.expansion)
self.downsample = downsample
self.stride = stride
def __init__(self, args, in_planes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(in_planes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu1 = ReLuPCA(args, planes)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.relu2 = ReLuPCA(args, planes)
self.downsample = downsample
self.stride = stride
def __init__(self, args, inp, oup, stride, expand_ratio):
super(InvertedResidual, self).__init__()
self.stride = stride
assert stride in [1, 2]
hidden_dim = int(round(inp * expand_ratio))
self.use_res_connect = self.stride == 1 and inp == oup
if expand_ratio == 1:
self.conv = nn.Sequential(
# dw
nn.Conv2d(hidden_dim,
hidden_dim,
3,
stride,
1,
groups=hidden_dim,
bias=False),
nn.BatchNorm2d(hidden_dim),
ReLuPCA(args, mxRelu6=True), # nn.ReLU6(inplace=True)
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
else:
self.conv = nn.Sequential(
# pw
nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
nn.BatchNorm2d(hidden_dim),
ReLuPCA(args, mxRelu6=True), # nn.ReLU6(inplace=True)
# dw
nn.Conv2d(hidden_dim,
hidden_dim,
3,
stride,
1,
groups=hidden_dim,
bias=False),
nn.BatchNorm2d(hidden_dim),
ReLuPCA(args, mxRelu6=True), # nn.ReLU6(inplace=True)
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
def __init__(self, block, layers, args, zero_init_residual=False):
super(ResNetImagenet, self).__init__()
num_classes = 1000
self.name = args.model
self.inplanes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = ReLuPCA(args, 64)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(args, block, 64, layers[0])
self.layer2 = self._make_layer(args, block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(args, block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(args, block, 512, layers[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
def __init__(self, args, in_channels, out_channels, **kwargs):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
self.relu = ReLuPCA(args)
def conv_bn(inp, oup, stride, args):
return nn.Sequential(
nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
nn.BatchNorm2d(oup),
ReLuPCA(args, mxRelu6=True) # nn.ReLU6(inplace=True)
)