def __init__(self,
num_class=150,
fc_dim=4096,
use_softmax=False,
pool_scales=(1, 2, 3, 6)):
super(PPMBilinearDeepsup, self).__init__()
self.use_softmax = use_softmax
self.ppm = []
for scale in pool_scales:
self.ppm.append(
nn.Sequential(
nn.AdaptiveAvgPool2d(scale),
nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False),
SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True)))
self.ppm = nn.ModuleList(self.ppm)
#self.cbr_deepsup = conv3x3_bn_relu(fc_dim // 2, fc_dim // 4, 1)
self.aspp_last = nn.Sequential(
nn.Conv2d(fc_dim + len(pool_scales) * 512,
512,
kernel_size=3,
padding=1,
bias=False), SynchronizedBatchNorm2d(512),
nn.ReLU(inplace=True), nn.Dropout2d(0.1))
#self.conv_last_deepsup = nn.Conv2d(fc_dim // 4, num_class, 1, 1, 0)
#self.dropout_deepsup = nn.Dropout2d(0.1)
for m in self.modules():
if isinstance(m, nn.Conv2d):
our_kaiming_normal_(m.weight, 0.1)
if m.bias is not None:
constant_(m.bias, 0)
elif isinstance(m, nn.BatchNorm2d):
constant_(m.weight, 1)
constant_(m.bias, 0)
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 128
super(ResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = SynchronizedBatchNorm2d(64)
self.relu1 = nn.ReLU(inplace=True)
self.conv2 = conv3x3(64, 64)
self.bn2 = SynchronizedBatchNorm2d(64)
self.relu2 = nn.ReLU(inplace=True)
self.conv3 = conv3x3(64, 128)
self.bn3 = SynchronizedBatchNorm2d(128)
self.relu3 = 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):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
elif isinstance(m, SynchronizedBatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self,
num_class=150,
fc_dim=4096,
use_softmax=False,
pool_scales=(1, 2, 3, 6)):
super(PPMBilinear, self).__init__()
self.use_softmax = use_softmax
self.ppm = []
for scale in pool_scales:
self.ppm.append(
nn.Sequential(
nn.AdaptiveAvgPool2d(scale),
nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False),
SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True)))
self.ppm = nn.ModuleList(self.ppm)
self.aspp_conv = nn.Sequential(
nn.Conv2d(fc_dim + len(pool_scales) * 512,
512,
kernel_size=3,
padding=1,
bias=False), SynchronizedBatchNorm2d(512),
nn.ReLU(inplace=True))
self.conv_last = nn.Sequential(
nn.Dropout2d(0.1), nn.Conv2d(512, num_class, kernel_size=1))
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = SynchronizedBatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = SynchronizedBatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def __init__(self):
super(Generalized_SEMSEG, self).__init__()
builder = semseg_heads.ModelBuilder()
self.encoder = builder.build_encoder(
arch=cfg.SEM.ARCH_ENCODER,
fc_dim=cfg.SEM.FC_DIM,
weights=cfg.RESNETS.IMAGENET_PRETRAINED_WEIGHTS)
#define shape weights
self.decoder = builder.build_decoder(arch=cfg.SEM.DECODER_TYPE,
fc_dim=cfg.SEM.FC_DIM,
num_class=cfg.MODEL.NUM_CLASSES,
use_softmax=not self.training,
weights='')
##define semseg loss
self.conv_last_semseg = nn.Sequential(
nn.Conv2d(cfg.SEM.DIM * 2, cfg.MODEL.NUM_CLASSES, kernel_size=1))
self.conv_last_semseg.apply(self._init_weights_kaiming)
self.crit = nn.NLLLoss(ignore_index=255)
self.deep_sup_scale = cfg.SEM.DEEP_SUB_SCALE
if len(cfg.SEM.DOWNSAMPLE) > 1:
self.semseg_deepsup = nn.Sequential(
nn.Conv2d(cfg.SEM.FC_DIM // 2,
cfg.SEM.FC_DIM // 4,
kernel_size=3,
stride=1,
padding=1,
bias=None),
SynchronizedBatchNorm2d(cfg.SEM.FC_DIM // 4),
nn.ReLU(inplace=True), nn.Dropout2d(0.1),
nn.Conv2d(cfg.SEM.FC_DIM // 4,
cfg.MODEL.NUM_CLASSES,
kernel_size=1))
#self.semseg_deepsup.apply(self._init_weights_kaiming)
if len(cfg.SEM.DOWNSAMPLE) > 1:
self.disp_deepsup = nn.Sequential(
nn.Conv2d(cfg.SEM.FC_DIM // 2,
cfg.SEM.FC_DIM // 4,
kernel_size=3,
stride=1,
padding=1,
bias=None),
SynchronizedBatchNorm2d(cfg.SEM.FC_DIM // 4),
nn.ReLU(inplace=True), nn.Dropout2d(0.1),
nn.Conv2d(cfg.SEM.FC_DIM // 4,
1,
kernel_size=3,
stride=1,
padding=1,
bias=None))
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 = SynchronizedBatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = SynchronizedBatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = SynchronizedBatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def __init__(self,
num_class=150,
fc_dim=4096,
use_softmax=False,
pool_scales=(1, 2, 3, 6),
fpn_inplanes=(256, 512, 1024, 2048),
fpn_dim=256):
super(UPerNet, self).__init__()
self.use_softmax = use_softmax
# PPM Module
self.ppm_pooling = []
self.ppm_conv = []
for scale in pool_scales:
self.ppm_pooling.append(nn.AdaptiveAvgPool2d(scale))
self.ppm_conv.append(
nn.Sequential(
nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False),
SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True)))
self.ppm_pooling = nn.ModuleList(self.ppm_pooling)
self.ppm_conv = nn.ModuleList(self.ppm_conv)
self.ppm_last_conv = conv3x3_bn_relu(fc_dim + len(pool_scales) * 512,
fpn_dim, 1)
# FPN Module
self.fpn_in = []
for fpn_inplane in fpn_inplanes[:-1]: # skip the top layer
self.fpn_in.append(
nn.Sequential(
nn.Conv2d(fpn_inplane, fpn_dim, kernel_size=1, bias=False),
SynchronizedBatchNorm2d(fpn_dim), nn.ReLU(inplace=True)))
self.fpn_in = nn.ModuleList(self.fpn_in)
self.fpn_out = []
for i in range(len(fpn_inplanes) - 1): # skip the top layer
self.fpn_out.append(
nn.Sequential(conv3x3_bn_relu(fpn_dim, fpn_dim, 1), ))
self.fpn_out = nn.ModuleList(self.fpn_out)
self.conv_last = nn.Sequential(
conv3x3_bn_relu(len(fpn_inplanes) * fpn_dim, fpn_dim, 1))
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck_GE, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = SynchronizedBatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=stride,
padding=1,
bias=False)
self.bn2 = SynchronizedBatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = SynchronizedBatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
self.Sigmoid = nn.Sigmoid()
ge_list = []
if cfg.SEM.USE_GE_BLOCK:
for i in range(3):
ge_list.append(self._conv(inplanes, inplanes, groups=inplanes))
self.ge_model_list = nn.ModuleList(ge_list)
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),
SynchronizedBatchNorm2d(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 conv3x3_bn_relu(in_planes, out_planes, stride=1):
return nn.Sequential(
conv3x3(in_planes, out_planes, stride),
SynchronizedBatchNorm2d(out_planes),
nn.ReLU(inplace=True),
)