def build_bottom_up(self, pretrained):
backbone = self.params['backbone']
if backbone == "resnet50":
model = models.resnet50(pretrained=pretrained)
elif backbone == "resnet101":
model = models.resnet101(pretrained=pretrained)
else:
raise Exception("unimplemented backbone %s" % backbone)
# p3 ~ p5 are extracted from backbone
p3 = nn.Sequential(model.conv1, model.bn1, model.relu, model.maxpool,
model.layer1, model.layer2)
p4 = model.layer3
p5 = model.layer4
# build remaining layers
in_channels = self.calc_in_channel_width(p5)
p6 = nn.Sequential(nn.Conv2d(in_channels, 256, 3, 2, 1),
nn.BatchNorm2d(256))
p7 = nn.Sequential(nn.ReLU(), nn.Conv2d(256, 256, 3, 2, 1),
nn.BatchNorm2d(256))
# register bottom up layers
self.bottom_up_layers = nn.ModuleList((p3, p4, p5, p6, p7))
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = NN.BatchNorm2d(planes) #NN.BatchNorm2d
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = NN.BatchNorm2d(planes) #NN.BatchNorm2d
self.downsample = downsample
self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = NN.BatchNorm2d(planes) #NN.BatchNorm2d
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.bn2 = NN.BatchNorm2d(planes) #NN.BatchNorm2d
self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
self.bn3 = NN.BatchNorm2d(planes * self.expansion) #NN.BatchNorm2d
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def __init__(self, in_planes, out_planes):
super(ConvBlock, self).__init__()
self.bn1 = nn.BatchNorm2d(in_planes)
conv3x3 = partial(nn.Conv2d, kernel_size=3, stride=1, padding=1, bias=False, dilation=1)
self.conv1 = conv3x3(in_planes, int(out_planes / 2))
self.bn2 = nn.BatchNorm2d(int(out_planes / 2))
self.conv2 = conv3x3(int(out_planes / 2), int(out_planes / 4))
self.bn3 = nn.BatchNorm2d(int(out_planes / 4))
self.conv3 = conv3x3(int(out_planes / 4), int(out_planes / 4))
self.downsample = None
if in_planes != out_planes:
self.downsample = nn.Sequential(nn.BatchNorm2d(in_planes),
nn.ReLU(True),
nn.Conv2d(in_planes, out_planes, 1, 1, bias=False))
def __init__(self, in_channels, out_channels, size):
super().__init__()
conv = [
nn.Conv2d(in_channels, out_channels, 1),
nn.BatchNorm2d(out_channels)
]
layer_conv = [
nn.Conv2d(out_channels, out_channels, 3, 1, 1),
nn.BatchNorm2d(out_channels)
]
self.conv = nn.Sequential(*conv)
self.upsample = nn.Upsample(size)
self.layer_conv = nn.Sequential(*layer_conv)
def __init__(self, inchannels, outchannels, upfactor=2):
super(AO, self).__init__()
self.inchannels = inchannels
self.outchannels = outchannels
self.upfactor = upfactor
self.adapt_conv = nn.Sequential(nn.Conv2d(in_channels=self.inchannels, out_channels=self.inchannels//2, kernel_size=3, padding=1, stride=1, bias=True),\
NN.BatchNorm2d(num_features=self.inchannels//2),\
nn.ReLU(inplace=True),\
nn.Conv2d(in_channels=self.inchannels//2, out_channels=self.outchannels, kernel_size=3, padding=1, stride=1, bias=True),\
nn.Upsample(scale_factor=self.upfactor, mode='bilinear', align_corners=True))
self.init_params()
def __init__(self, num_modules=1, end_relu=False, num_landmarks=98, fname_pretrained=None):
super(FAN, self).__init__()
self.num_modules = num_modules
self.end_relu = end_relu
# Base part
self.conv1 = CoordConvTh(256, 256, True, False,
in_channels=3, out_channels=64,
kernel_size=7, stride=2, padding=3)
self.bn1 = nn.BatchNorm2d(64)
self.conv2 = ConvBlock(64, 128)
self.conv3 = ConvBlock(128, 128)
self.conv4 = ConvBlock(128, 256)
# Stacking part
self.add_module('m0', HourGlass(1, 4, 256, first_one=True))
self.add_module('top_m_0', ConvBlock(256, 256))
self.add_module('conv_last0', nn.Conv2d(256, 256, 1, 1, 0))
self.add_module('bn_end0', nn.BatchNorm2d(256))
self.add_module('l0', nn.Conv2d(256, num_landmarks + 1, 1, 1, 0))
if fname_pretrained is not None:
self.load_pretrained_weights(fname_pretrained)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=1, stride=stride, bias=False),
NN.BatchNorm2d(planes * block.expansion), #NN.BatchNorm2d
)
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, inchannels, midchannels=512):
super(FTB, self).__init__()
self.in1 = inchannels
self.mid = midchannels
self.conv1 = nn.Conv2d(in_channels=self.in1,
out_channels=self.mid,
kernel_size=3,
padding=1,
stride=1,
bias=True)
# NN.BatchNorm2d
self.conv_branch = nn.Sequential(nn.ReLU(inplace=True),\
nn.Conv2d(in_channels=self.mid, out_channels=self.mid, kernel_size=3, padding=1, stride=1, bias=True),\
NN.BatchNorm2d(num_features=self.mid),\
nn.ReLU(inplace=True),\
nn.Conv2d(in_channels=self.mid, out_channels= self.mid, kernel_size=3, padding=1, stride=1, bias=True))
self.relu = nn.ReLU(inplace=True)
self.init_params()
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = NN.BatchNorm2d(64) #NN.BatchNorm2d
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, stride=1)
#self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
padding=1,
dilation=1,
stride=1,
groups=1,
is_bn=True,
is_relu=True):
super(ConvBnRelu2d, self).__init__()
self.conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=kernel_size,
padding=padding,
stride=stride,
dilation=dilation,
groups=groups,
bias=False)
self.bn = nn.BatchNorm2d(out_channels, eps=BN_EPS)
self.relu = nn.ReLU(inplace=True)
if is_bn is False: self.bn = None
if is_relu is False: self.relu = None
if num_gpu < 2:
print(
"No multi-gpu found. NN.BatchNorm2d will act as normal nn.BatchNorm2d")
m1 = nn.Sequential(
nn.Conv2d(3, 3, 1, 1, bias=False),
nn.BatchNorm2d(3),
nn.ReLU(inplace=True),
nn.Conv2d(3, 3, 1, 1, bias=False),
nn.BatchNorm2d(3),
).cuda()
torch.manual_seed(123)
init_weight(m1)
m2 = nn.Sequential(
nn.Conv2d(3, 3, 1, 1, bias=False),
NN.BatchNorm2d(3),
nn.ReLU(inplace=True),
nn.Conv2d(3, 3, 1, 1, bias=False),
NN.BatchNorm2d(3),
).cuda()
torch.manual_seed(123)
init_weight(m2)
m2 = nn.DataParallel(m2, device_ids=range(num_gpu))
o1 = torch.optim.SGD(m1.parameters(), 1e-3)
o2 = torch.optim.SGD(m2.parameters(), 1e-3)
y = torch.ones(num_gpu).float().cuda()
torch.manual_seed(123)
for _ in range(100):
x = torch.rand(num_gpu, 3, 2, 2).cuda()
o1.zero_grad()
z1 = m1(x)