def __init__(self):
super(BaseResNet50, self).__init__()
with self.init_scope():
self.conv1 = L.Convolution2D(3, 64, 7, 2, 3)
self.bn1 = L.BatchNormalization(64)
self.res2 = R.BuildingBlock(3, 64, 64, 256, 1)
self.res3 = R.BuildingBlock(4, 256, 128, 512, 2)
self.res4 = R.BuildingBlock(6, 512, 256, 1024, 2)
self.res5 = R.BuildingBlock(3, 1024, 512, 2048, 2)
def __init__(self, n_class=36, pretrained_model=None, output_scale=1.0):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
print "train resblock : True"
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
self.n_class = n_class
self.output_scale = output_scale
super(DualCenterProposalNetworkRes50FCN, self).__init__(
# resnet50
conv1=L.Convolution2D(3, 64, 7, 2, 3, **kwargs),
bn1=L.BatchNormalization(64),
res2=R.BuildingBlock(3, 64, 64, 256, 1, **kwargs),
res3=R.BuildingBlock(4, 256, 128, 512, 2, **kwargs),
res4=R.BuildingBlock(6, 512, 256, 1024, 2, **kwargs),
res5=R.BuildingBlock(3, 1024, 512, 2048, 2, **kwargs),
upscore32=L.Deconvolution2D(2048, 512, 8, stride=4, pad=2),
bn_up32=L.BatchNormalization(512),
upscore16=L.Deconvolution2D(1024, 512, 4, stride=2, pad=1),
bn_up16=L.BatchNormalization(512),
concat_conv=L.Convolution2D(512 * 3, 512 * 3, 3, stride=1, pad=1),
bn_concat=L.BatchNormalization(512 * 3),
score_pool=L.Convolution2D(512 * 3, n_class, 1, stride=1, pad=0),
upscore_final=L.Deconvolution2D(self.n_class,
self.n_class,
16,
stride=8,
pad=4),
conv_cp1=L.Convolution2D(512 * 3, 1024, 3, stride=1, pad=1),
bn_cp1=L.BatchNormalization(1024),
# center pose network
conv_cp2=L.Convolution2D(1024, 512, 3, stride=1, pad=1),
bn_cp2=L.BatchNormalization(512),
upscore_cp1=L.Deconvolution2D(512, 16, 8, stride=4, pad=2),
bn_cp3=L.BatchNormalization(16),
upscore_cp2=L.Deconvolution2D(16, 3, 4, stride=2, pad=1),
# origin center pose network
conv_ocp2=L.Convolution2D(1024, 512, 3, stride=1, pad=1),
bn_ocp2=L.BatchNormalization(512),
upscore_ocp1=L.Deconvolution2D(512, 16, 8, stride=4, pad=2),
bn_ocp3=L.BatchNormalization(16),
upscore_ocp2=L.Deconvolution2D(16, 3, 4, stride=2, pad=1),
)
def __init__(self, n_class=36, pretrained_model=None):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
self.n_class = n_class
super(DepthInvariantNetworkRes50FCN, self).__init__(
# resnet50
conv1=L.Convolution2D(3, 64, 7, 2, 3, **kwargs),
bn1=L.BatchNormalization(64),
res2=R.BuildingBlock(3, 64, 64, 256, 1,
**kwargs), # resblock 1/2 -> 1/4
res3=R.BuildingBlock(4, 256, 128, 512, 2,
**kwargs), # resblock 1/4 ->1/8
res4=R.BuildingBlock(6, 512, 256, 1024, 2,
**kwargs), # resblock 1/8 -> 1/16
res5=R.BuildingBlock(3, 1024, 512, 2048, 2,
**kwargs), # resblock 1/16 -> 1/32
upscore1=L.Deconvolution2D(2048, 512, 16, stride=8, pad=4),
upscore2=L.Deconvolution2D(1024, 512, 8, stride=4, pad=2),
upscore3=L.Deconvolution2D(512, 512, 4, stride=2, pad=1),
bn_upscore=L.BatchNormalization(512 * 3),
concat_conv=L.Convolution2D(512 * 3, 1024, 3, stride=1, pad=1),
pool_roi_conv=L.Convolution2D(1024, 1024, 5, stride=5, pad=0),
conv_after_croip=L.Convolution2D(1024, 512, 3, stride=1, pad=1),
bn_croip1=L.BatchNormalization(1024),
bn_croip2=L.BatchNormalization(512),
score_pool=L.Convolution2D(512, n_class, 1, stride=1, pad=0),
upscore_final=L.Deconvolution2D(self.n_class,
self.n_class,
8,
stride=4,
pad=2),
)
def __init__(self, n_class=36, pretrained_model=None):
if pretrained_model:
# As a sampling process is time-consuming,
# we employ a zero initializer for faster computation.
kwargs = {'initialW': constant.Zero()}
else:
# employ default initializers used in the original paper
kwargs = {'initialW': normal.HeNormal(scale=1.0)}
self.n_class = n_class
super(CenterProposalNetworkRes50FCN, self).__init__(
# resnet50
conv1=L.Convolution2D(3, 64, 7, 2, 3, **kwargs),
bn1=L.BatchNormalization(64),
res2=R.BuildingBlock(3, 64, 64, 256, 1, **kwargs),
res3=R.BuildingBlock(4, 256, 128, 512, 2, **kwargs),
res4=R.BuildingBlock(6, 512, 256, 1024, 2, **kwargs),
res5=R.BuildingBlock(3, 1024, 512, 2048, 2, **kwargs),
upscore32=L.Deconvolution2D(2048,
512,
8,
stride=4,
pad=2,
use_cudnn=False),
upscore16=L.Deconvolution2D(1024,
512,
4,
stride=2,
pad=1,
use_cudnn=False),
concat_conv=L.Convolution2D(512 * 3, 512 * 3, 3, stride=1, pad=1),
score_pool=L.Convolution2D(512 * 3, n_class, 1, stride=1, pad=0),
cls_pool=L.Convolution2D(512 * 3, 128, 1, stride=1, pad=0),
upscore_final=L.Deconvolution2D(self.n_class,
self.n_class,
16,
stride=8,
pad=4,
use_cudnn=False),
# depth network
conv_d1_1=L.Convolution2D(1, 64, 3, stride=1, pad=1),
bn_d1_1=L.BatchNormalization(64),
conv_d1_2=L.Convolution2D(64, 64, 3, stride=1, pad=1),
bn_d1_2=L.BatchNormalization(64),
conv_d2=L.Convolution2D(64, 128, 3, stride=1, pad=1),
bn_d2=L.BatchNormalization(128),
conv_d3=L.Convolution2D(128, 256, 3, stride=1, pad=1),
bn_d3=L.BatchNormalization(256),
# center pose network
conv_cp_1=L.Convolution2D(256 + 512 + 128,
1024,
3,
stride=1,
pad=1),
bn_cp_1=L.BatchNormalization(1024),
conv_cp_2=L.Convolution2D(1024, 1024, 3, stride=1, pad=1),
bn_cp_2=L.BatchNormalization(1024),
upscore_cp1=L.Deconvolution2D(1024,
512,
8,
stride=4,
pad=2,
use_cudnn=False),
bn_cp_3=L.BatchNormalization(512),
upscore_cp2=L.Deconvolution2D(512,
3,
4,
stride=2,
pad=1,
use_cudnn=False),
# rotation network
conv_rot_1=L.Convolution2D(256 + 512 + 128,
1024,
3,
stride=1,
pad=1),
bn_rot_1=L.BatchNormalization(1024),
conv_rot_2=L.Convolution2D(1024, 1024, 3, stride=1, pad=1),
bn_rot_2=L.BatchNormalization(1024),
upscore_rot1=L.Deconvolution2D(1024,
512,
8,
stride=4,
pad=2,
use_cudnn=False),
bn_rot_3=L.BatchNormalization(512),
upscore_rot2=L.Deconvolution2D(512,
5,
4,
stride=2,
pad=1,
use_cudnn=False),
)