def __init__(self, cfg, backbone=resnet50_atrous):
super(DeeplabV3Plus, self).__init__()
self.backbone = backbone(pretrained=False, os=cfg.OUTPUT_STRIDE)
input_channel = 512 * self.backbone.block.expansion
self.aspp = ASPP(in_chans=input_channel, out_chans=cfg.ASPP_OUTDIM, rate=16//cfg.OUTPUT_STRIDE)
self.dropout1 = nn.Dropout(0.5)
self.upsample4 = nn.UpsamplingBilinear2d(scale_factor=4)
self.upsample_sub = nn.UpsamplingBilinear2d(scale_factor=cfg.OUTPUT_STRIDE//4)
indim = 64 * self.backbone.block.expansion
self.shortcut_conv = nn.Sequential(
nn.Conv2d(indim, cfg.SHORTCUT_DIM, cfg.SHORTCUT_KERNEL, 1, padding=cfg.SHORTCUT_KERNEL//2,bias=False),
nn.BatchNorm2d(cfg.SHORTCUT_DIM),
nn.ReLU(inplace=True),
)
self.cat_conv = nn.Sequential(
nn.Conv2d(cfg.ASPP_OUTDIM+cfg.SHORTCUT_DIM, cfg.ASPP_OUTDIM, 3, 1, padding=1,bias=False),
nn.BatchNorm2d(cfg.ASPP_OUTDIM),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(cfg.ASPP_OUTDIM, cfg.ASPP_OUTDIM, 3, 1, padding=1, bias=False),
nn.BatchNorm2d(cfg.ASPP_OUTDIM),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(cfg.ASPP_OUTDIM, cfg.NUM_CLASSES, 1, 1, padding=0)
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, model_name, project_dir):
super(DeepLabV3, self).__init__()
self.num_classes = 20
self.model_name = model_name
self.project_dir = project_dir
self.create_model_dirs()
# specify the type of resnet model / or any other model for feature extraction
self.resnet = ResNet18(project_dir)
self.aspp = ASPP(num_classes=self.num_classes)
def __init__(self):
super(DeepLabV3, self).__init__()
self.num_classes = 4
self.resnet = ResNet50_OS16() # NOTE! specify the type of ResNet here
self.aspp = ASPP(
num_classes=self.num_classes
) # NOTE! if you use ResNet50-152, set self.aspp = ASPP_Bottleneck(num_classes=self.num_classes) instead
def __init__(self, sess, config, is_training=True):
self.resnet_model = resnet.__dict__.get(config.resnet_model)(
sess, pretrained=True, is_training=is_training)
self.aspp = ASPP(is_training=is_training)
self.conv = ConvBlock(config.num_classes,
1,
1,
is_training=is_training,
name='conv1')
def __init__(self, model_id, project_dir):
super(DeepLabV3, self).__init__()
self.num_classes = 5
self.model_id = model_id
self.project_dir = project_dir
self.resnet = ResNet18_OS8() # NOTE! specify the type of ResNet here
self.aspp = ASPP(num_classes=self.num_classes) # NOTE! if you use ResNet50-152, set self.aspp = ASPP_Bottleneck(num_classes=self.num_classes) instead
def __init__(self, model_id, project_dir):
super(DeepLabV3, self).__init__() # extend from parent class's constructor
self.num_classes = 20 # cityscapes class constains 20 kinds + one background class
self.model_id = model_id # model_id = "eval_seq"
self.project_dir = project_dir # project_dir = "/root/deeplabv3"
self.create_model_dirs()
self.resnet = ResNet18_OS8() # NOTE! specify the type of ResNet here
self.aspp = ASPP(num_classes=self.num_classes) # NOTE! if you use ResNet50-152, set self.aspp = ASPP_Bottleneck(num_classes=self.num_classes) instead
def __init__(self, num_classes, backbone='50'):
super(DeepLabV3Plus, self).__init__()
if backbone == '50':
self.backbone = resnet50()
elif backbone == '101':
self.backbone = resnet101()
elif backbone == '152':
self.backbone = resnet152()
else:
raise ValueError('backbone {} not supported.'.format(backbone))
self.num_classes = num_classes
self.aspp = ASPP()
self.decoder = Decoder(self.num_classes)
def __init__(self):
super(DeepLabV3, self).__init__()
self.num_classes = 6
# self.model_id = model_id
# self.project_dir = project_dir
#self.create_model_dirs()
self.resnet = resnet18(
pretrained=True) # NOTE! specify the type of ResNet here
self.aspp = ASPP(
num_classes=self.num_classes
) # NOTE! if you use ResNet50-152, set self.aspp = ASPP_Bottleneck(num_classes=self.num_classes) instead
def __init__(self, block, layers, num_classes):
print("model.py")
self.inplanes = 128
super(ResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = BatchNorm2d(64)
self.relu1 = nn.ReLU(inplace=False)
self.conv2 = conv3x3(64, 64)
self.bn2 = BatchNorm2d(64)
self.relu2 = nn.ReLU(inplace=False)
self.conv3 = conv3x3(64, 128)
self.bn3 = BatchNorm2d(128)
self.relu3 = nn.ReLU(inplace=False)
self.maxpool = nn.MaxPool2d(
kernel_size=3, stride=2, padding=1, ceil_mode=True
) # NOTE! (ceil_mode=True will do that x (batch_size, 128, h/4, w/4) e.g. has shape (batch_size, 128, 33, 33) instead of (batch_size, 128, 32, 32) if h == w == 256)
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=1,
dilation=2)
self.layer4 = self._make_layer(block,
512,
layers[3],
stride=1,
dilation=4,
multi_grid=(1, 1, 1))
self.aspp = ASPP()
self.cls = nn.Conv2d(512,
num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True)
def __init__(self, backbone='resnet18', num_classes=16, pretrained=False):
super().__init__()
assert backbone in ['resnet18', 'resnet34',
'resnet50'], 'backbone not implemented'
resnet = get_model(backbone, pretrained=pretrained)
self.conv1 = resnet.conv1
self.bn1 = resnet.bn1
self.relu = resnet.relu
self.maxpool = resnet.maxpool
self.layer1 = resnet.layer1
self.layer2 = resnet.layer2
self.layer3 = resnet.layer3
self.layer4 = resnet.layer4
self.aspp = ASPP(256, 512, [4, 8, 12], drop_prob=0)
self.avgpool = resnet.avgpool
self.dropout = nn.Dropout(0.5)
self.fc = nn.Linear(512, num_classes)
def __init__(self, cfg):
super(DeeplabV3plus, self).__init__()
self.backbone = None
self.backbone_layers = None
input_channel = 2048
self.aspp = ASPP(dim_in=input_channel,
dim_out=cfg.MODEL_ASPP_OUTDIM,
rate=16 // cfg.MODEL_OUTPUT_STRIDE,
bn_mom=cfg.TRAIN_BN_MOM)
self.dropout1 = nn.Dropout(0.5)
# self.upsample4 = nn.UpsamplingBilinear2d(scale_factor=4)
# self.upsample_sub = nn.UpsamplingBilinear2d(scale_factor=cfg.MODEL_OUTPUT_STRIDE//4)
# self.upsample4 = nn.Upsample(scale_factor=4)
self.upsample_sub = nn.Upsample(scale_factor=cfg.MODEL_OUTPUT_STRIDE //
4)
indim = 256
self.shortcut_conv = nn.Sequential(
nn.Conv2d(indim,
cfg.MODEL_SHORTCUT_DIM,
cfg.MODEL_SHORTCUT_KERNEL,
1,
padding=cfg.MODEL_SHORTCUT_KERNEL // 2,
bias=True),
# SynchronizedBatchNorm2d(cfg.MODEL_SHORTCUT_DIM, momentum=cfg.TRAIN_BN_MOM),
nn.BatchNorm2d(cfg.MODEL_SHORTCUT_DIM),
nn.ReLU(inplace=True),
)
self.cat_conv = nn.Sequential(
nn.Conv2d(cfg.MODEL_ASPP_OUTDIM + cfg.MODEL_SHORTCUT_DIM,
cfg.MODEL_ASPP_OUTDIM,
3,
1,
padding=1,
bias=True),
# SynchronizedBatchNorm2d(cfg.MODEL_ASPP_OUTDIM, momentum=cfg.TRAIN_BN_MOM),
nn.BatchNorm2d(cfg.MODEL_ASPP_OUTDIM),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(cfg.MODEL_ASPP_OUTDIM,
cfg.MODEL_ASPP_OUTDIM,
3,
1,
padding=1,
bias=True),
# SynchronizedBatchNorm2d(cfg.MODEL_ASPP_OUTDIM, momentum=cfg.TRAIN_BN_MOM),
nn.BatchNorm2d(cfg.MODEL_ASPP_OUTDIM),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(cfg.MODEL_ASPP_OUTDIM,
cfg.num_classes,
1,
1,
padding=0)
self.backbone = build_backbone(cfg.MODEL_BACKBONE,
os=cfg.MODEL_OUTPUT_STRIDE)
# self.backbone_layers = self.backbone.get_layers()
# print(len(self.backbone_layers))
self.pointhead = PointRendSemSegHead()
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, output_stride=16, num_classes=21):
super(DeepLab, self).__init__()
self.backbone = resnet101(output_stride=output_stride)
self.aspp = ASPP(output_stride)
self.decoder = Decoder(num_classes)
