def __init__(self, inchannels, bn_type):
super(EmbedModule, self).__init__()
inter_channels = inchannels // 4
self.conv = nn.Sequential(
nn.Conv2d(inchannels,
inter_channels,
kernel_size=1,
padding=0,
bias=False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels,
inter_channels,
kernel_size=7,
padding=3,
stride=1,
bias=False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(inter_channels),
nn.ReLU(inplace=True),
nn.Conv2d(inter_channels,
inchannels,
kernel_size=1,
padding=0,
bias=False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(inchannels),
nn.ReLU(inplace=True),
)
def __init__(self, block, layers, num_classes=1000, bn_type=None):
self.inplanes = 128
super(CaffeResNet, self).__init__()
self.conv1 = conv3x3(3, 64, stride=2)
self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(64, momentum=0.1)
self.relu1 = nn.ReLU(inplace=True)
self.conv2 = conv3x3(64, 64)
self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(64, momentum=0.1)
self.relu2 = nn.ReLU(inplace=True)
self.conv3 = conv3x3(64, 128)
self.bn3 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(128, momentum=0.1)
self.relu3 = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0], bn_type=bn_type)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, bn_type=bn_type)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2, bn_type=bn_type)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2, bn_type=bn_type)
self.avgpool = nn.AvgPool2d(7, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
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, ModuleHelper.BatchNorm2d(bn_type=bn_type)):
m.weight.data.fill_(1)
m.bias.data.zero_()
def __init__(self, num_class=150, fc_dim=4096, bn_type=None):
super(PPMBilinearDeepsup, self).__init__()
pool_scales = (1, 2, 3, 6)
self.ppm = []
for scale in pool_scales:
self.ppm.append(
nn.Sequential(
nn.AdaptiveAvgPool2d(scale),
nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(512),
nn.ReLU(inplace=True)))
self.ppm = nn.ModuleList(self.ppm)
self.cbr_deepsup = _ConvBatchNormReluBlock(fc_dim // 2,
fc_dim // 4,
3,
1,
bn_type=bn_type)
self.conv_last = nn.Sequential(
nn.Conv2d(fc_dim + len(pool_scales) * 512,
512,
kernel_size=3,
padding=1,
bias=False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(512),
nn.ReLU(inplace=True), nn.Dropout2d(0.1),
nn.Conv2d(512, num_class, kernel_size=1))
self.conv_last_deepsup = nn.Conv2d(fc_dim // 4, num_class, 1, 1, 0)
self.dropout_deepsup = nn.Dropout2d(0.1)
def __init__(self, num_input_features, growth_rate, bn_size, drop_rate,
bn_type):
super(_DenseLayer, self).__init__()
self.add_module(
'norm1',
ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_input_features)),
self.add_module('relu1', nn.ReLU(inplace=True)),
self.add_module(
'conv1',
nn.Conv2d(num_input_features,
bn_size * growth_rate,
kernel_size=1,
stride=1,
bias=False)),
self.add_module(
'norm2',
ModuleHelper.BatchNorm2d(bn_type=bn_type)(bn_size * growth_rate)),
self.add_module('relu2', nn.ReLU(inplace=True)),
self.add_module(
'conv2',
nn.Conv2d(bn_size * growth_rate,
growth_rate,
kernel_size=3,
stride=1,
padding=1,
bias=False)),
self.drop_rate = drop_rate
def __init__(self, input_num, num1, num2, dilation_rate, drop_out,
norm_type):
super(_DenseAsppBlock, self).__init__()
self.add_module('relu1', nn.ReLU(inplace=False)),
self.add_module(
'conv1',
nn.Conv2d(in_channels=input_num, out_channels=num1,
kernel_size=1)),
self.add_module(
'norm2',
ModuleHelper.BatchNorm2d(norm_type=norm_type)(num_features=num1)),
self.add_module('relu2', nn.ReLU(inplace=False)),
self.add_module(
'conv2',
nn.Conv2d(in_channels=num1,
out_channels=num2,
kernel_size=3,
dilation=dilation_rate,
padding=dilation_rate)),
self.add_module(
'norm2',
ModuleHelper.BatchNorm2d(norm_type=norm_type)(
num_features=input_num)),
self.drop_rate = drop_out
def __init__(self, input_nc, ndf=64, n_layers=3, norm_type=None):
"""Construct a PatchGAN discriminator
Parameters:
input_nc (int) -- the number of channels in input images
ndf (int) -- the number of filters in the last conv layer
n_layers (int) -- the number of conv layers in the discriminator
norm_layer -- normalization layer
"""
super(NLayerDiscriminator, self).__init__()
use_bias = (norm_type == 'instancenorm')
kw = 4
padw = 1
sequence = [nn.Conv2d(input_nc, ndf, kernel_size=kw, stride=2, padding=padw), nn.LeakyReLU(0.2, True)]
nf_mult = 1
nf_mult_prev = 1
for n in range(1, n_layers): # gradually increase the number of filters
nf_mult_prev = nf_mult
nf_mult = min(2 ** n, 8)
sequence += [
nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=2, padding=padw, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(ndf * nf_mult),
nn.LeakyReLU(0.2, True)
]
nf_mult_prev = nf_mult
nf_mult = min(2 ** n_layers, 8)
sequence += [
nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=1, padding=padw, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(ndf * nf_mult),
nn.LeakyReLU(0.2, True)
]
sequence += [nn.Conv2d(ndf * nf_mult, 1, kernel_size=kw, stride=1, padding=padw)] # output 1 channel prediction map
self.model = nn.Sequential(*sequence)
def __init__(self, inplanes, planes, stride=1, downsample=None, bn_type=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes)
self.downsample = downsample
self.stride = stride
def freeze_bn(net, norm_type=None):
for m in net.modules():
if isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d) or isinstance(m, nn.BatchNorm3d):
m.eval()
if norm_type is not None:
from models.tools.module_helper import ModuleHelper
if isinstance(m, ModuleHelper.BatchNorm2d(norm_type=norm_type, ret_cls=True)) \
or isinstance(m, ModuleHelper.BatchNorm1d(norm_type=norm_type, ret_cls=True)) \
or isinstance(m, ModuleHelper.BatchNorm3d(norm_type=norm_type, ret_cls=True)):
m.eval()
def __init__(self, inplanes, planes, stride=1, downsample=None, bn_type=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
padding=1, bias=False)
self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes)
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
self.bn3 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def __init__(self,
outer_nc,
inner_nc,
submodule=None,
outermost=False,
innermost=False,
norm_type=None,
use_dropout=False):
super(UNetSkipConnectionBlock, self).__init__()
self.outermost = outermost
downconv = nn.Conv2d(outer_nc,
inner_nc,
kernel_size=4,
stride=2,
padding=1)
downrelu = nn.LeakyReLU(0.2, True)
downnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(inner_nc)
uprelu = nn.ReLU(True)
upnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(outer_nc)
if outermost:
upconv = nn.ConvTranspose2d(inner_nc * 2,
outer_nc,
kernel_size=4,
stride=2,
padding=1)
down = [downconv]
up = [uprelu, upconv, nn.Tanh()]
model = down + [submodule] + up
elif innermost:
upconv = nn.ConvTranspose2d(inner_nc,
outer_nc,
kernel_size=4,
stride=2,
padding=1)
down = [downrelu, downconv]
up = [uprelu, upconv, upnorm]
model = down + up
else:
upconv = nn.ConvTranspose2d(inner_nc * 2,
outer_nc,
kernel_size=4,
stride=2,
padding=1)
down = [downrelu, downconv, downnorm]
up = [uprelu, upconv, upnorm]
if use_dropout:
model = down + [submodule] + up + [nn.Dropout(0.5)]
else:
model = down + [submodule] + up
self.model = nn.Sequential(*model)
def __init__(self, outer_nc, inner_nc, input_nc=None,
submodule=None, outermost=False, innermost=False, norm_type=None, use_dropout=False):
"""Construct a Unet submodule with skip connections.
Parameters:
outer_nc (int) -- the number of filters in the outer conv layer
inner_nc (int) -- the number of filters in the inner conv layer
input_nc (int) -- the number of channels in input images/features
submodule (UnetSkipConnectionBlock) -- previously defined submodules
outermost (bool) -- if this module is the outermost module
innermost (bool) -- if this module is the innermost module
norm_layer -- normalization layer
user_dropout (bool) -- if use dropout layers.
"""
super(UnetSkipConnectionBlock, self).__init__()
self.outermost = outermost
use_bias = (norm_type == 'instancenorm')
if input_nc is None:
input_nc = outer_nc
downconv = nn.Conv2d(input_nc, inner_nc, kernel_size=4,
stride=2, padding=1, bias=use_bias)
downrelu = nn.LeakyReLU(0.2, True)
downnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(inner_nc)
uprelu = nn.ReLU(True)
upnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(outer_nc)
if outermost:
upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
kernel_size=4, stride=2,
padding=1)
down = [downconv]
up = [uprelu, upconv, nn.Tanh()]
model = down + [submodule] + up
elif innermost:
upconv = nn.ConvTranspose2d(inner_nc, outer_nc,
kernel_size=4, stride=2,
padding=1, bias=use_bias)
down = [downrelu, downconv]
up = [uprelu, upconv, upnorm]
model = down + up
else:
upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
kernel_size=4, stride=2,
padding=1, bias=use_bias)
down = [downrelu, downconv, downnorm]
up = [uprelu, upconv, upnorm]
if use_dropout:
model = down + [submodule] + up + [nn.Dropout(0.5)]
else:
model = down + [submodule] + up
self.model = nn.Sequential(*model)
def __init__(self,
low_in_channels,
high_in_channels,
key_channels,
value_channels,
out_channels=None,
scale=1,
norm_type=None,
psp_size=(1, 3, 6, 8)):
super(_SelfAttentionBlock, self).__init__()
self.scale = scale
self.in_channels = low_in_channels
self.out_channels = out_channels
self.key_channels = key_channels
self.value_channels = value_channels
if out_channels == None:
self.out_channels = high_in_channels
self.pool = nn.MaxPool2d(kernel_size=(scale, scale))
self.f_key = nn.Sequential(
nn.Conv2d(in_channels=self.in_channels,
out_channels=self.key_channels,
kernel_size=1,
stride=1,
padding=0),
ModuleHelper.BNReLU(self.key_channels, norm_type=norm_type),
)
self.f_query = nn.Sequential(
nn.Conv2d(in_channels=high_in_channels,
out_channels=self.key_channels,
kernel_size=1,
stride=1,
padding=0),
ModuleHelper.BNReLU(self.key_channels, norm_type=norm_type),
)
self.f_value = nn.Conv2d(in_channels=self.in_channels,
out_channels=self.value_channels,
kernel_size=1,
stride=1,
padding=0)
self.W = nn.Conv2d(in_channels=self.value_channels,
out_channels=self.out_channels,
kernel_size=1,
stride=1,
padding=0)
self.psp = PSPModule(psp_size)
nn.init.constant_(self.W.weight, 0)
nn.init.constant_(self.W.bias, 0)
def squeezenet_dilated8(self):
model = DilatedSqueezeNet()
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'),
all_match=False)
return model
def __init__(self, configer):
self.inplanes = 128
super(DeepLabV3, self).__init__()
self.configer = configer
self.num_classes = self.configer.get('data', 'num_classes')
self.backbone = BackboneSelector(configer).get_backbone()
self.head = nn.Sequential(
ASPPModule(2048, bn_type=self.configer.get('network', 'bn_type')),
nn.Conv2d(512,
self.num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True))
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1),
ModuleHelper.BNReLU(512,
bn_type=self.configer.get(
'network', 'bn_type')), nn.Dropout2d(0.1),
nn.Conv2d(512,
self.num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True))
def _make_layer(self, block, planes, blocks, stride=1, norm_type=None):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(planes *
block.expansion),
)
layers = []
layers.append(
block(self.inplanes,
planes,
stride,
downsample,
norm_type=norm_type))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, norm_type=norm_type))
return nn.Sequential(*layers)
def mobilenetv2(self):
model = MobileNetV2()
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'),
all_match=False)
return model
def __init__(self, configer):
super(PSPNet, self).__init__()
self.configer = configer
self.num_classes = self.configer.get('data', 'num_classes')
self.backbone = BackboneSelector(configer).get_backbone()
num_features = self.backbone.get_num_features()
self.dsn = nn.Sequential(
_ConvBatchNormReluBlock(num_features // 2,
num_features // 4,
3,
1,
bn_type=self.configer.get(
'network', 'bn_type')),
nn.Dropout2d(0.1),
nn.Conv2d(num_features // 4, self.num_classes, 1, 1, 0))
self.ppm = PPMBilinearDeepsup(fc_dim=num_features,
bn_type=self.configer.get(
'network', 'bn_type'))
self.cls = nn.Sequential(
nn.Conv2d(num_features + 4 * 512,
512,
kernel_size=3,
padding=1,
bias=False),
ModuleHelper.BNReLU(512,
bn_type=self.configer.get(
'network', 'bn_type')), nn.Dropout2d(0.1),
nn.Conv2d(512, self.num_classes, kernel_size=1))
def __init__(self, configer):
super(DeepLabV3, self).__init__()
self.configer = configer
self.backbone = BackboneSelector(configer).get_backbone()
self.backbone = nn.Sequential(
self.backbone.conv1, self.backbone.bn1, self.backbone.relu1,
self.backbone.conv2, self.backbone.bn2, self.backbone.relu2,
self.backbone.conv3, self.backbone.bn3, self.backbone.relu3,
self.backbone.maxpool, self.backbone.layer1, self.backbone.layer2,
self.backbone.layer3)
self.MG_features = _ResidualBlockMulGrid(
inplanes=1024,
midplanes=512,
outplanes=2048,
stride=1,
dilation=2,
mulgrid=self.configer.get('network', 'multi_grid'),
bn_type=self.configer.get('network', 'bn_type'))
pyramids = [6, 12, 18]
self.aspp = _ASPPModule(2048,
256,
pyramids,
bn_type=self.configer.get(
'network', 'bn_type'))
self.fc1 = nn.Sequential(
nn.Conv2d(1280, 256, kernel_size=1), # 256 * 5 = 1280
ModuleHelper.BatchNorm2d(
bn_type=self.configer.get('network', 'bn_type'))(256))
self.fc2 = nn.Conv2d(256,
self.configer.get('data', 'num_classes'),
kernel_size=1)
def __init__(self,
low_in_channels,
high_in_channels,
out_channels,
key_channels,
value_channels,
dropout,
sizes=([1]),
norm_type=None,
psp_size=(1, 3, 6, 8)):
super(AFNB, self).__init__()
self.stages = []
self.norm_type = norm_type
self.psp_size = psp_size
self.stages = nn.ModuleList([
self._make_stage([low_in_channels, high_in_channels], out_channels,
key_channels, value_channels, size)
for size in sizes
])
self.conv_bn_dropout = nn.Sequential(
nn.Conv2d(out_channels + high_in_channels,
out_channels,
kernel_size=1,
padding=0),
ModuleHelper.BatchNorm2d(norm_type=self.norm_type)(out_channels),
nn.Dropout2d(dropout))
def __init__(self, in_channel, out_channel, kernel_size, stride=1, padding=0, dilation=1, groups=1, bn_type=None):
super(ConvBnRelu, self).__init__()
self.conv_bn_relu = nn.Sequential(
nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, dilation, groups,
False),
ModuleHelper.BatchNorm2d(bn_type=bn_type)(out_channel),
nn.ReLU(True))
def build_conv_block(self, dim, padding_type, norm_type, use_dropout,
use_bias):
"""Construct a convolutional block.
Parameters:
dim (int) -- the number of channels in the conv layer.
padding_type (str) -- the name of padding layer: reflect | replicate | zero
norm_layer -- normalization layer
use_dropout (bool) -- if use dropout layers.
use_bias (bool) -- if the conv layer uses bias or not
Returns a conv block (with a conv layer, a normalization layer, and a non-linearity layer (ReLU))
"""
conv_block = []
p = 0
if padding_type == 'reflect':
conv_block += [nn.ReflectionPad2d(1)]
elif padding_type == 'replicate':
conv_block += [nn.ReplicationPad2d(1)]
elif padding_type == 'zero':
p = 1
else:
raise NotImplementedError('padding [%s] is not implemented' %
padding_type)
conv_block += [
nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(dim),
nn.ReLU(True)
]
if use_dropout:
conv_block += [nn.Dropout(0.5)]
p = 0
if padding_type == 'reflect':
conv_block += [nn.ReflectionPad2d(1)]
elif padding_type == 'replicate':
conv_block += [nn.ReplicationPad2d(1)]
elif padding_type == 'zero':
p = 1
else:
raise NotImplementedError('padding [%s] is not implemented' %
padding_type)
conv_block += [
nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(dim)
]
return nn.Sequential(*conv_block)
def __init__(self, inplanes, outplanes, kernel_size, stride, padding, dilation, relu=True, bn_type=None):
super(_ConvBatchNormReluBlock, self).__init__()
self.relu = relu
self.conv = nn.Conv2d(in_channels=inplanes,out_channels=outplanes,
kernel_size=kernel_size, stride=stride, padding = padding,
dilation = dilation, bias=False)
self.bn = ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_features=outplanes)
self.relu_f = nn.ReLU()
def squeezenet(self):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = SqueezeNet()
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
def vgg_bn(self, vgg_cfg=None):
backbone = self.configer.get('network', 'backbone')
model = VGG(cfg_name=backbone, vgg_cfg=vgg_cfg, bn=True)
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'),
all_match=False)
return model
def __init__(self, input_nc, output_nc, ngf=64, norm_type=None, use_dropout=False, n_blocks=6, padding_type='reflect'):
"""Construct a Resnet-based generator
Parameters:
input_nc (int) -- the number of channels in input images
output_nc (int) -- the number of channels in output images
ngf (int) -- the number of filters in the last conv layer
norm_layer -- normalization layer
use_dropout (bool) -- if use dropout layers
n_blocks (int) -- the number of ResNet blocks
padding_type (str) -- the name of padding layer in conv layers: reflect | replicate | zero
"""
assert(n_blocks >= 0)
super(ResNetGenerator, self).__init__()
use_bias = (norm_type == 'instancenorm')
model = [nn.ReflectionPad2d(3),
nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(ngf),
nn.ReLU(True)]
n_downsampling = 2
for i in range(n_downsampling): # add downsampling layers
mult = 2 ** i
model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1, bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(ngf * mult * 2),
nn.ReLU(True)]
mult = 2 ** n_downsampling
for i in range(n_blocks): # add ResNet blocks
model += [ResnetBlock(ngf * mult, padding_type=padding_type, norm_type=norm_type, use_dropout=use_dropout, use_bias=use_bias)]
for i in range(n_downsampling): # add upsampling layers
mult = 2 ** (n_downsampling - i)
model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2),
kernel_size=3, stride=2,
padding=1, output_padding=1,
bias=use_bias),
ModuleHelper.BatchNorm2d(norm_type=norm_type)(int(ngf * mult / 2)),
nn.ReLU(True)]
model += [nn.ReflectionPad2d(3)]
model += [nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0)]
model += [nn.Tanh()]
self.model = nn.Sequential(*model)
def __init__(self, configer):
super(asymmetric_non_local_network, self).__init__()
self.configer = configer
self.num_classes = self.configer.get('data', 'num_classes')
self.backbone = BackboneSelector(configer).get_backbone()
# low_in_channels, high_in_channels, out_channels, key_channels, value_channels, dropout
self.fusion = AFNB(1024,
2048,
2048,
256,
256,
dropout=0.05,
sizes=([1]),
norm_type=self.configer.get('network', 'norm_type'))
# extra added layers
self.context = nn.Sequential(
nn.Conv2d(2048, 512, kernel_size=3, stride=1, padding=1),
ModuleHelper.BNReLU(512,
norm_type=self.configer.get(
'network', 'norm_type')),
APNB(in_channels=512,
out_channels=512,
key_channels=256,
value_channels=256,
dropout=0.05,
sizes=([1]),
norm_type=self.configer.get('network', 'norm_type')))
self.cls = nn.Conv2d(512,
self.num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True)
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1),
ModuleHelper.BNReLU(512,
norm_type=self.configer.get(
'network', 'norm_type')),
nn.Dropout2d(0.05),
nn.Conv2d(512,
self.num_classes,
kernel_size=1,
stride=1,
padding=0,
bias=True))
def darknet53(self):
"""Constructs a darknet-53 model.
"""
model = DarkNet([1, 2, 8, 8, 4])
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'),
all_match=False)
return model
def resnet34(self, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], deep_base=False,
bn_type=self.configer.get('network', 'bn_type'), **kwargs)
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'))
return model
def deepbase_resnet101(self, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], deep_base=True,
bn_type=self.configer.get('network', 'bn_type'), **kwargs)
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'))
return model
def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16),
num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000, bn_type=None):
super(DenseNet, self).__init__()
# First convolution
self.features = nn.Sequential(OrderedDict([
('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)),
('norm0', ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_init_features)),
('relu0', nn.ReLU(inplace=True)),
('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)),
]))
# Each denseblock
num_features = num_init_features
for i, num_layers in enumerate(block_config):
block = _DenseBlock(num_layers=num_layers, num_input_features=num_features,
bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate, bn_type=bn_type)
self.features.add_module('denseblock%d' % (i + 1), block)
num_features = num_features + num_layers * growth_rate
if i != len(block_config) - 1:
trans = _Transition(num_input_features=num_features,
num_output_features=num_features // 2, bn_type=bn_type)
avg_pool = nn.AvgPool2d(kernel_size=2, stride=2)
self.features.add_module('transition%d' % (i + 1), trans)
self.features.add_module('transition%s_pool' % (i + 1), avg_pool)
num_features = num_features // 2
self.num_features = num_features
# Final batch norm
self.features.add_module('norm5', ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_features))
# Linear layer
self.classifier = nn.Linear(num_features, num_classes)
# Official init from torch repo.
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight)
elif isinstance(m, ModuleHelper.BatchNorm2d(bn_type=bn_type)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.constant_(m.bias, 0)
