def __init__(self):
super(SegmentationModuleBase, self).__init__()
# For cache
self.mapping_to_detectron = None
self.orphans_in_detectron = None
self.iter = 0
self.draw = False
builder = semseg_heads.ModelBuilder()
#define encoder
if cfg.SEM.USE_RESNET:
self.encoder = get_func(cfg.MODEL.CONV_BODY)()
else:
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 3DSD loss
self.crit = nn.NLLLoss(ignore_index=255 * cfg.DISP.MAX_DISPLACEMENT +
1)
self.SmoothL1Loss = nn.SmoothL1Loss(
reduction='none') #elementwise_mean
self.disp_gain = 1.0 * cfg.DISP.EXPECT_MAXDISP / cfg.DISP.MAX_DISPLACEMENT
print('epe of each pixel is set to %.2f' % self.disp_gain)
self.BCELoss = nn.BCELoss(reduction='elementwise_mean')
def __init__(self):
super(SegmentationModuleBase, self).__init__()
print("hello")
# For cache
self.mapping_to_detectron = None
self.orphans_in_detectron = None
self.iter=0
self.draw=False
builder = semseg_heads.ModelBuilder()
#define encoder
if cfg.SEM.USE_RESNET:
self.encoder = get_func(cfg.MODEL.CONV_BODY)()
else:
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='')
self.crit = nn.NLLLoss(ignore_index=255)
self.deep_sup_scale = cfg.SEM.DEEP_SUB_SCALE
if cfg.DISP.ORIGINAL:
self.conv_last_disp = nn.Conv2d(cfg.DISP.DIM*2,1,kernel_size=3,padding=1,bias=False)
self.conv_last_disp.apply(self._init_weights_normal)
if cfg.DISP.USE_CRL_DISPFUL:
self.conv_last_disp = CRL.DispFulNetSubset()
if cfg.DISP.USE_CRL_DISPRES:
self.conv_last_disp = CRL.DispResNetSubset(),
self.conv_last_disp.apply(self._init_weights_normal)
self.SmoothL1Loss = nn.SmoothL1Loss(reduction='none') #elementwise_mean
#self.disp_loss = self._disp_loss
#self.hardtanh = nn.Hardtanh(-1, 1,inplace=True)
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)
)
self.disp_deepsup.apply(self._init_weights_kaiming)
def __init__(self):
super(SegmentationModuleBase, self).__init__()
print("hello")
# For cache
self.mapping_to_detectron = None
self.orphans_in_detectron = None
self.iter=0
self.draw=False
builder = semseg_heads.ModelBuilder()
#define encoder
if cfg.SEM.USE_RESNET:
self.encoder = get_func(cfg.MODEL.CONV_BODY)()
else:
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='')
self.minipsm = semseg_heads.MiniPSMNet()
self.fusion = semseg_heads.FusionNet()
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.SmoothL1Loss = nn.SmoothL1Loss(reduction='none') #elementwise_mean
self.multiScaleLoss = Lossfuction.MultiScaleLoss(scales=4,downscale=1,loss='L1').to('cuda')