def __init__(self,
in_channels,
out_channels,
kernel_size=1,
stride=1,
padding=0,
dilation=1,
bias=False,
activate_first=True,
inplace=True):
super(SeparableConv2d, self).__init__()
self.relu0 = nn.ReLU(inplace=inplace)
self.depthwise = nn.Conv2d(in_channels,
in_channels,
kernel_size,
stride,
padding,
dilation,
groups=in_channels,
bias=bias)
self.bn1 = SynchronizedBatchNorm2d(in_channels, momentum=bn_mom)
self.relu1 = nn.ReLU(inplace=True)
self.pointwise = nn.Conv2d(in_channels,
out_channels,
1,
1,
0,
1,
1,
bias=bias)
self.bn2 = SynchronizedBatchNorm2d(out_channels, momentum=bn_mom)
self.relu2 = nn.ReLU(inplace=True)
self.activate_first = activate_first
def __init__(self, in_channel, out_channel, batch_norm, pool):
super(RNN_cell, self).__init__()
self.outchannel = out_channel
conv_R = nn.Conv2d(in_channels=in_channel1,
out_channels=out_channel,
kernel_size=3,
stride=1,
padding=1)
conv_T = nn.Conv2d(in_channels=in_channel2,
out_channels=out_channel,
kernel_size=3,
stride=1,
padding=1)
layers_data = [
conv_R, SynchronizedBatchNorm2d(out_channel)
] #,nn.BatchNorm2d(out_channel * 4), nn.Dropout2d(p=dropout)]
layers_ctrl = [conv_T, SynchronizedBatchNorm2d(out_channel)]
self.conv_data = nn.Sequential(*layers_data)
self.conv_ctrl = nn.Sequential(*layers_ctrl)
self.pool = nn.MaxPool2d(kernel_size=2,
stride=2,
padding=0,
ceil_mode=True)
self.ispool = pool
self.detachout = detachout
def __init__(self,
nInputChannels=3,
n_classes=21,
os=16,
pretrained=False,
_print=True):
if _print:
print("Constructing DeepLabv3+ model...")
print("Number of classes: {}".format(n_classes))
print("Output stride: {}".format(os))
print("Number of Input Channels: {}".format(nInputChannels))
super(DeepLabv3_plus_multi_set, self).__init__()
# Atrous Conv
self.xception_features = Xception(nInputChannels, os, pretrained)
# ASPP
if os == 16:
rates = [1, 6, 12, 18]
elif os == 8:
rates = [1, 12, 24, 36]
else:
raise NotImplementedError
self.aspp1 = ASPP_module_rate0(2048, 256, rate=rates[0])
self.aspp2 = ASPP_module(2048, 256, rate=rates[1])
self.aspp3 = ASPP_module(2048, 256, rate=rates[2])
self.aspp4 = ASPP_module(2048, 256, rate=rates[3])
self.relu = nn.ReLU()
self.global_avg_pool = nn.Sequential(
nn.AdaptiveAvgPool2d((1, 1)),
nn.Conv2d(2048, 256, 1, stride=1, bias=False),
SynchronizedBatchNorm2d(256), nn.ReLU())
self.concat_projection_conv1 = nn.Conv2d(1280, 256, 1, bias=False)
self.concat_projection_bn1 = SynchronizedBatchNorm2d(256)
# adopt [1x1, 48] for channel reduction.
self.feature_projection_conv1 = nn.Conv2d(256, 48, 1, bias=False)
self.feature_projection_bn1 = SynchronizedBatchNorm2d(48)
self.decoder = nn.Sequential(Decoder_module(304, 256),
Decoder_module(256, 256))
self.semantic_aux_cihp = nn.Conv2d(256, 20, kernel_size=1, stride=1)
self.semantic_aux_pascal = nn.Conv2d(256, 7, kernel_size=1, stride=1)
self.semantic_aux_atr = nn.Conv2d(256, 18, kernel_size=1, stride=1)
def __init__(self, config_text, norm_nc, label_nc):
super().__init__()
assert config_text.startswith('spade')
parsed = re.search('spade(\D+)(\d)x\d', config_text)
param_free_norm_type = str(parsed.group(1))
ks = int(parsed.group(2))
if param_free_norm_type == 'instance':
self.param_free_norm = nn.InstanceNorm2d(norm_nc, affine=False)
elif param_free_norm_type == 'syncbatch':
self.param_free_norm = SynchronizedBatchNorm2d(norm_nc, affine=False)
elif param_free_norm_type == 'batch':
self.param_free_norm = nn.BatchNorm2d(norm_nc, affine=False)
else:
raise ValueError('%s is not a recognized param-free norm type in SPADE'
% param_free_norm_type)
# The dimension of the intermediate embedding space. Yes, hardcoded.
nhidden = 128
pw = ks // 2
self.mlp_shared = nn.Sequential(
nn.Conv2d(label_nc, nhidden, kernel_size=ks, padding=pw),
nn.ReLU()
)
self.mlp_gamma = nn.Conv2d(nhidden, norm_nc, kernel_size=ks, padding=pw)
self.mlp_beta = nn.Conv2d(nhidden, norm_nc, kernel_size=ks, padding=pw)
def add_norm_layer(layer):
nonlocal norm_type
if norm_type.startswith('spectral'):
layer = spectral_norm(layer)
subnorm_type = norm_type[len('spectral'):]
if subnorm_type == 'none' or len(subnorm_type) == 0:
return layer
# remove bias in the previous layer, which is meaningless
# since it has no effect after normalization
if getattr(layer, 'bias', None) is not None:
delattr(layer, 'bias')
layer.register_parameter('bias', None)
if subnorm_type == 'batch':
norm_layer = nn.BatchNorm2d(get_out_channel(layer), affine=True)
elif subnorm_type == 'sync_batch':
norm_layer = SynchronizedBatchNorm2d(get_out_channel(layer), affine=True)
elif subnorm_type == 'instance':
norm_layer = nn.InstanceNorm2d(get_out_channel(layer), affine=False)
else:
raise ValueError('normalization layer %s is not recognized' % subnorm_type)
return nn.Sequential(layer, norm_layer)
def __init__(self, opt, norm_nc):
super().__init__()
self.param_free_norm = SynchronizedBatchNorm2d(norm_nc, affine=False)
# number of internal filters for generating scale/bias
nhidden = 128
# size of kernels
kernal_size = 3
# padding size
padding = kernal_size // 2
self.mlp_shared = nn.Sequential(
nn.Conv2d(opt['label_nc'],
nhidden,
kernel_size=kernal_size,
padding=padding), nn.ReLU())
self.mlp_gamma = nn.Conv2d(nhidden,
norm_nc,
kernel_size=kernal_size,
padding=padding)
self.mlp_beta = nn.Conv2d(nhidden,
norm_nc,
kernel_size=kernal_size,
padding=padding)
def _make_layer(self, net_dict, batch_norm=False):
layers = []
length = len(net_dict)
for i in range(length):
one_layer = net_dict[i]
key = one_layer.keys()[0]
v = one_layer[key]
if 'pool' in key:
layers += [
nn.MaxPool2d(kernel_size=v[0], stride=v[1], padding=v[2])
]
else:
conv2d = nn.Conv2d(in_channels=v[0],
out_channels=v[1],
kernel_size=v[2],
stride=v[3],
padding=v[4])
if batch_norm:
layers += [
conv2d,
SynchronizedBatchNorm2d(v[1]),
nn.ReLU(inplace=True)
]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
return nn.Sequential(*layers)
def __init__(
self,
in_channels,
n_filters,
k_size,
stride,
padding,
bias=True,
dilation=1,
is_batchnorm=True,
):
super(conv2DBatchNorm, self).__init__()
conv_mod = nn.Conv2d(int(in_channels),
int(n_filters),
kernel_size=k_size,
padding=padding,
stride=stride,
bias=bias,
dilation=dilation,)
if is_batchnorm:
self.cb_unit = nn.Sequential(conv_mod, SynchronizedBatchNorm2d(int(n_filters)))
else:
self.cb_unit = nn.Sequential(conv_mod)
def __init__(self,
in_filters,
out_filters,
strides=1,
atrous=None,
grow_first=True,
activate_first=True,
inplace=True):
super(Block, self).__init__()
if atrous == None:
atrous = [1] * 3
elif isinstance(atrous, int):
atrous_list = [atrous] * 3
atrous = atrous_list
idx = 0
self.head_relu = True
if out_filters != in_filters or strides != 1:
self.skip = nn.Conv2d(in_filters,
out_filters,
1,
stride=strides,
bias=False)
self.skipbn = SynchronizedBatchNorm2d(out_filters, momentum=bn_mom)
self.head_relu = False
else:
self.skip = None
self.hook_layer = None
if grow_first:
filters = out_filters
else:
filters = in_filters
self.sepconv1 = SeparableConv2d(in_filters,
filters,
3,
stride=1,
padding=1 * atrous[0],
dilation=atrous[0],
bias=False,
activate_first=activate_first,
inplace=self.head_relu)
self.sepconv2 = SeparableConv2d(filters,
out_filters,
3,
stride=1,
padding=1 * atrous[1],
dilation=atrous[1],
bias=False,
activate_first=activate_first)
self.sepconv3 = SeparableConv2d(out_filters,
out_filters,
3,
stride=strides,
padding=1 * atrous[2],
dilation=atrous[2],
bias=False,
activate_first=activate_first,
inplace=inplace)
def testSyncBatchNorm2DSyncTrain(self):
bn = nn.BatchNorm2d(10)
sync_bn = SynchronizedBatchNorm2d(10)
sync_bn = DataParallelWithCallback(sync_bn, device_ids=[0, 1])
bn.cuda()
sync_bn.cuda()
self._checkBatchNormResult(bn, sync_bn, torch.rand(16, 10, 16, 16), True, cuda=True)
def __init__(self, in_size, out_size, is_batchnorm):
super(unetConv2, self).__init__()
if is_batchnorm:
self.conv1 = nn.Sequential(
nn.Conv2d(in_size, out_size, 3, 1, 0),
SynchronizedBatchNorm2d(out_size),
nn.ReLU(),
)
self.conv2 = nn.Sequential(
nn.Conv2d(out_size, out_size, 3, 1, 0),
SynchronizedBatchNorm2d(out_size),
nn.ReLU(),
)
else:
self.conv1 = nn.Sequential(nn.Conv2d(in_size, out_size, 3, 1, 0), nn.ReLU())
self.conv2 = nn.Sequential(
nn.Conv2d(out_size, out_size, 3, 1, 0), nn.ReLU()
)
def __init__(self, in_channel1, in_channel2, out_channel, pool, detachout, kernel_size, stride, padding):
super(RNN_cell, self).__init__()
self.outchannel = out_channel
conv_data = nn.Conv2d(in_channels=in_channel1, out_channels=out_channel, kernel_size=kernel_size, stride=stride, padding=padding, bias=True)
conv_ctrl = nn.Conv2d(in_channels=in_channel2, out_channels=out_channel, kernel_size=3, stride=1, padding=1, bias=True)
self.pool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1, ceil_mode=False)
if syn_bn:
layers_data = [conv_data, SynchronizedBatchNorm2d(out_channel), torch.nn.ReLU()]
layers_ctrl = [conv_ctrl, SynchronizedBatchNorm2d(out_channel), torch.nn.Sigmoid()]
else:
layers_data = [conv_data, nn.BatchNorm2d(out_channel), torch.nn.ReLU()]
layers_ctrl = [conv_ctrl, nn.BatchNorm2d(out_channel), torch.nn.Sigmoid()]
self.conv_data = nn.Sequential(*layers_data)
self.conv_ctrl = nn.Sequential(*layers_ctrl)
self.ispool = pool
self.detachout = detachout
self.stride = stride
def __init__(self,
inplanes,
planes,
kernel_size=3,
stride=1,
dilation=1,
bias=False,
padding=0):
super(SeparableConv2d_same, self).__init__()
self.depthwise = nn.Conv2d(inplanes,
inplanes,
kernel_size,
stride,
padding,
dilation,
groups=inplanes,
bias=bias)
self.depthwise_bn = SynchronizedBatchNorm2d(inplanes)
self.pointwise = nn.Conv2d(inplanes, planes, 1, 1, 0, 1, 1, bias=bias)
self.pointwise_bn = SynchronizedBatchNorm2d(planes)
def __init__(self, dim_in, dim_out, rate=1, bn_mom=0.1): super(ASPP, self).__init__() self.branch1 = nn.Sequential( nn.Conv2d(dim_in, dim_out, 1, 1, padding=0, dilation=rate,bias=True), SynchronizedBatchNorm2d(dim_out, momentum=bn_mom), nn.ReLU(inplace=True), ) self.branch2 = nn.Sequential( nn.Conv2d(dim_in, dim_out, 3, 1, padding=6*rate, dilation=6*rate,bias=True), SynchronizedBatchNorm2d(dim_out, momentum=bn_mom), nn.ReLU(inplace=True), ) self.branch3 = nn.Sequential( nn.Conv2d(dim_in, dim_out, 3, 1, padding=12*rate, dilation=12*rate,bias=True), SynchronizedBatchNorm2d(dim_out, momentum=bn_mom), nn.ReLU(inplace=True), ) self.branch4 = nn.Sequential( nn.Conv2d(dim_in, dim_out, 3, 1, padding=18*rate, dilation=18*rate,bias=True), SynchronizedBatchNorm2d(dim_out, momentum=bn_mom), nn.ReLU(inplace=True), ) self.branch5_conv = nn.Conv2d(dim_in, dim_out, 1, 1, 0,bias=True) self.branch5_bn = SynchronizedBatchNorm2d(dim_out, momentum=bn_mom) self.branch5_relu = nn.ReLU(inplace=True) self.conv_cat = nn.Sequential( nn.Conv2d(dim_out*5, dim_out, 1, 1, padding=0,bias=True), SynchronizedBatchNorm2d(dim_out, momentum=bn_mom), nn.ReLU(inplace=True), )
def __init__(self, in_channels, n_filters, k_size, stride, padding, bias=True):
super(deconv2DBatchNorm, self).__init__()
self.dcb_unit = nn.Sequential(
nn.ConvTranspose2d(
int(in_channels),
int(n_filters),
kernel_size=k_size,
padding=padding,
stride=stride,
bias=bias,
),
SynchronizedBatchNorm2d(int(n_filters)),
)
def __init__(self,
in_channels,
out_channels,
kernel_size=(3, 3),
stride=(1, 1),
padding=(1, 1)):
super(ConvBn2d, self).__init__()
self.conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
bias=False)
#self.dropout = nn.Dropout2d(p=0.1, inplace=False)
self.bn = SynchronizedBatchNorm2d(out_channels, eps=1e-5, affine=False)
def __init__(self, args, ch, emb_dim):
super().__init__()
if args.norm_g == 'syncbatch':
from sync_batchnorm import SynchronizedBatchNorm2d
self.norm = SynchronizedBatchNorm2d(ch, affine=False)
elif args.norm_g == 'batch':
self.norm = nn.BatchNorm2d(ch, affine=False)
elif args.norm_g == 'instance':
self.norm = nn.InstanceNorm2d(ch, affine=False)
elif args.norm_g == 'none':
self.norm = lambda x: x # Identity
else:
raise
self.fc_gamma = nn.Linear(emb_dim, ch)
self.fc_beta = nn.Linear(emb_dim, ch)
def __init__(self, inplanes, planes, rate=1):
super(ASPP_module_rate0, self).__init__()
if rate == 1:
kernel_size = 1
padding = 0
self.atrous_convolution = nn.Conv2d(inplanes,
planes,
kernel_size=kernel_size,
stride=1,
padding=padding,
dilation=rate,
bias=False)
self.bn = SynchronizedBatchNorm2d(planes, eps=1e-5, affine=True)
self.relu = nn.ReLU()
else:
raise RuntimeError()
def __init__(self, os):
""" Constructor
Args:
num_classes: number of classes
"""
super(Xception, self).__init__()
stride_list = None
if os == 8:
stride_list = [2, 1, 1]
elif os == 16:
stride_list = [2, 2, 1]
else:
raise ValueError(
'xception.py: output stride=%d is not supported.' % os)
self.conv1 = nn.Conv2d(3, 32, 3, 2, 1, bias=False)
self.bn1 = SynchronizedBatchNorm2d(32, momentum=bn_mom)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(32, 64, 3, 1, 1, bias=False)
self.bn2 = SynchronizedBatchNorm2d(64, momentum=bn_mom)
#do relu here
self.block1 = Block(64, 128, 2)
self.block2 = Block(128, 256, stride_list[0], inplace=False)
self.block3 = Block(256, 728, stride_list[1])
rate = 16 // os
self.block4 = Block(728, 728, 1, atrous=rate)
self.block5 = Block(728, 728, 1, atrous=rate)
self.block6 = Block(728, 728, 1, atrous=rate)
self.block7 = Block(728, 728, 1, atrous=rate)
self.block8 = Block(728, 728, 1, atrous=rate)
self.block9 = Block(728, 728, 1, atrous=rate)
self.block10 = Block(728, 728, 1, atrous=rate)
self.block11 = Block(728, 728, 1, atrous=rate)
self.block12 = Block(728, 728, 1, atrous=rate)
self.block13 = Block(728, 728, 1, atrous=rate)
self.block14 = Block(728, 728, 1, atrous=rate)
self.block15 = Block(728, 728, 1, atrous=rate)
self.block16 = Block(728,
728,
1,
atrous=[1 * rate, 1 * rate, 1 * rate])
self.block17 = Block(728,
728,
1,
atrous=[1 * rate, 1 * rate, 1 * rate])
self.block18 = Block(728,
728,
1,
atrous=[1 * rate, 1 * rate, 1 * rate])
self.block19 = Block(728,
728,
1,
atrous=[1 * rate, 1 * rate, 1 * rate])
self.block20 = Block(728,
1024,
stride_list[2],
atrous=rate,
grow_first=False)
#self.block12=Block(728,1024,2,2,start_with_relu=True,grow_first=False)
self.conv3 = SeparableConv2d(1024,
1536,
3,
1,
1 * rate,
dilation=rate,
activate_first=False)
# self.bn3 = SynchronizedBatchNorm2d(1536, momentum=bn_mom)
self.conv4 = SeparableConv2d(1536,
1536,
3,
1,
1 * rate,
dilation=rate,
activate_first=False)
# self.bn4 = SynchronizedBatchNorm2d(1536, momentum=bn_mom)
#do relu here
self.conv5 = SeparableConv2d(1536,
2048,
3,
1,
1 * rate,
dilation=rate,
activate_first=False)
# self.bn5 = SynchronizedBatchNorm2d(2048, momentum=bn_mom)
self.layers = []
#------- init weights --------
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, inplanes=3, os=16, pretrained=False):
super(Xception, self).__init__()
if os == 16:
entry_block3_stride = 2
middle_block_rate = 1
exit_block_rates = (1, 2)
elif os == 8:
entry_block3_stride = 1
middle_block_rate = 2
exit_block_rates = (2, 4)
else:
raise NotImplementedError
# Entry flow
self.conv1 = nn.Conv2d(inplanes,
32,
3,
stride=2,
padding=1,
bias=False)
self.bn1 = SynchronizedBatchNorm2d(32)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(32, 64, 3, stride=1, padding=1, bias=False)
self.bn2 = SynchronizedBatchNorm2d(64)
self.block1 = Block(64, 128, reps=2, stride=2, start_with_relu=False)
self.block2 = Block2(128,
256,
reps=2,
stride=2,
start_with_relu=True,
grow_first=True)
self.block3 = Block(256,
728,
reps=2,
stride=entry_block3_stride,
start_with_relu=True,
grow_first=True)
# Middle flow
self.block4 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block5 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block6 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block7 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block8 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block9 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block10 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block11 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block12 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block13 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block14 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block15 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block16 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block17 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block18 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
self.block19 = Block(728,
728,
reps=3,
stride=1,
dilation=middle_block_rate,
start_with_relu=True,
grow_first=True)
# Exit flow
self.block20 = Block(728,
1024,
reps=2,
stride=1,
dilation=exit_block_rates[0],
start_with_relu=True,
grow_first=False,
is_last=True)
self.conv3 = SeparableConv2d_aspp(1024,
1536,
3,
stride=1,
dilation=exit_block_rates[1],
padding=exit_block_rates[1])
# self.bn3 = nn.BatchNorm2d(1536)
self.conv4 = SeparableConv2d_aspp(1536,
1536,
3,
stride=1,
dilation=exit_block_rates[1],
padding=exit_block_rates[1])
# self.bn4 = nn.BatchNorm2d(1536)
self.conv5 = SeparableConv2d_aspp(1536,
2048,
3,
stride=1,
dilation=exit_block_rates[1],
padding=exit_block_rates[1])
# self.bn5 = nn.BatchNorm2d(2048)
# Init weights
# self.__init_weight()
# Load pretrained model
if pretrained:
self.__load_xception_pretrained()
def __init__(self, pretrained=True, num_classes=-1):
super(deeplabv3plus, self).__init__()
self.backbone = None
self.backbone_layers = None
input_channel = 2048
self.aspp = ASPP(dim_in=input_channel,
dim_out=256,
rate=16 // 16,
bn_mom=0.0003)
self.dropout1 = nn.Dropout(0.5)
self.upsample4 = nn.UpsamplingBilinear2d(scale_factor=4)
self.upsample_sub = nn.UpsamplingBilinear2d(scale_factor=16 //
8) #16//4
indim = 728
shallow1_dim = 64
self.shortcut_conv1_1 = nn.Sequential(
nn.Conv2d(indim, shallow1_dim, 1, 1, padding=1 // 2, bias=True),
SynchronizedBatchNorm2d(shallow1_dim, momentum=0.0003),
nn.ReLU(inplace=True),
)
self.cat_conv1_1 = nn.Sequential(
nn.Conv2d(256 + shallow1_dim, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(256, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
indim = 256
shallow2_dim = 32
self.shortcut_conv1_2 = nn.Sequential(
nn.Conv2d(indim, shallow2_dim, 1, 1, padding=1 // 2, bias=True),
SynchronizedBatchNorm2d(shallow2_dim, momentum=0.0003),
nn.ReLU(inplace=True),
)
self.cat_conv1_2 = nn.Sequential(
nn.Conv2d(256 + shallow2_dim, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(256, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
# self.predict5x5 = nn.Conv2d(256, 256, 5, 1, padding=2)
self.predict5x5 = nn.Sequential(
nn.Conv2d(256, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.5),
nn.Conv2d(256, 256, 3, 1, padding=1, bias=True),
SynchronizedBatchNorm2d(256, momentum=0.0003),
nn.ReLU(inplace=True),
nn.Dropout(0.1),
)
self.cls_conv = nn.Conv2d(256, 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 = xception.xception(pretrained=pretrained, os=16)
self.backbone_layers = self.backbone.get_layers()
def __init__(self,
inplanes,
planes,
reps,
stride=1,
dilation=1,
start_with_relu=True,
grow_first=True,
is_last=False):
super(Block2, self).__init__()
if planes != inplanes or stride != 1:
self.skip = nn.Conv2d(inplanes,
planes,
1,
stride=stride,
bias=False)
self.skipbn = SynchronizedBatchNorm2d(planes)
else:
self.skip = None
self.relu = nn.ReLU(inplace=True)
rep = []
filters = inplanes
if grow_first:
rep.append(self.relu)
rep.append(
SeparableConv2d_same(inplanes,
planes,
3,
stride=1,
dilation=dilation))
# rep.append(nn.BatchNorm2d(planes))
filters = planes
for i in range(reps - 1):
rep.append(self.relu)
rep.append(
SeparableConv2d_same(filters,
filters,
3,
stride=1,
dilation=dilation))
# rep.append(nn.BatchNorm2d(filters))
if not grow_first:
rep.append(self.relu)
rep.append(
SeparableConv2d_same(inplanes,
planes,
3,
stride=1,
dilation=dilation))
# rep.append(nn.BatchNorm2d(planes))
if not start_with_relu:
rep = rep[1:]
if stride != 1:
self.block2_lastconv = nn.Sequential(*[
self.relu,
SeparableConv2d_same(
planes, planes, 3, stride=2, dilation=dilation)
])
if is_last:
rep.append(SeparableConv2d_same(planes, planes, 3, stride=1))
self.rep = nn.Sequential(*rep)
