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) # self.dropout = torch.nn.Dropout(p=0.1, inplace=False) self.upsample4 = nn.UpsamplingBilinear2d(scale_factor=4) self.upsample_sub = nn.UpsamplingBilinear2d(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), 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), nn.ReLU(inplace=True), nn.Conv2d(cfg.MODEL_ASPP_OUTDIM, cfg.MODEL_ASPP_OUTDIM, 3, 1, padding=1), nn.ReLU(inplace=True), ) self.cls_conv = nn.Conv2d(cfg.MODEL_ASPP_OUTDIM, cfg.MODEL_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()
def __init__(self, cfg): super(deeplabv3plus, self).__init__() self.backbone = build_backbone(cfg.MODEL_BACKBONE) self.backbone_layers = self.backbone.get_layers() input_channel = 2048 self.aspp = ASPP(dim_in=input_channel, dim_out=cfg.MODEL_ASPP_OUTDIM, resolution_in=cfg.MODEL_ASPP_RESOLUTION) self.upsample = nn.UpsamplingBilinear2d(scale_factor=4) self.shortcut_conv = nn.Sequential( nn.Conv2d(256, cfg.MODEL_SHORTCUT_DIM, 1, 1, padding=0), 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), nn.ReLU(inplace=True), nn.Conv2d(cfg.MODEL_ASPP_OUTDIM, cfg.MODEL_ASPP_OUTDIM, 3, 1, padding=1), nn.ReLU(inplace=True), nn.Conv2d(cfg.MODEL_ASPP_OUTDIM, cfg.MODEL_NUM_CLASSES, 1, 1, padding=0), )
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)
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.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.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.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(cfg.MODEL_ASPP_OUTDIM,
cfg.MODEL_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, SynchronizedBatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
self.backbone = build_backbone(cfg.MODEL_BACKBONE,
os=cfg.MODEL_OUTPUT_STRIDE)
self.backbone_layers = self.backbone.get_layers()
def __init__(self, cfg, test=False):
super(deeplabv3plus, self).__init__()
if test:
self.batch_size = cfg.TEST_BATCHES
else:
self.batch_size = cfg.TRAIN_BATCHES
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)
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.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.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.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(cfg.MODEL_ASPP_OUTDIM,
cfg.MODEL_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, SynchronizedBatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
self.backbone1 = build_backbone(cfg.MODEL_BACKBONE,
os=cfg.MODEL_OUTPUT_STRIDE)
self.backbone2 = build_backbone(cfg.MODEL_BACKBONE,
os=cfg.MODEL_OUTPUT_STRIDE)
self.backbone_layers1 = self.backbone1.get_layers()
self.backbone_layers2 = self.backbone2.get_layers()
self.tc_conv = nn.Sequential(
nn.Conv2d(6, 96, 7, stride=3), # 96*20*20
nn.ReLU(inplace=True), # 96*20*20
nn.MaxPool2d(2), # 96*10*10
nn.Conv2d(96, 256, 5), # 192*6*6
nn.ReLU(), # 192*6*6
nn.MaxPool2d(2), # 192*3*3
nn.Conv2d(256, 512, 3),
nn.ReLU() # 256*1*1
)
self.liner = nn.Sequential(nn.Linear(41472, 256), nn.ReLU())
self.out = nn.Linear(256, 1)