def _make_deconv_layer(self, num_layers, num_filters, num_kernels):
assert num_layers == len(num_filters), \
'ERROR: num_deconv_layers is different len(num_deconv_filters)'
assert num_layers == len(num_kernels), \
'ERROR: num_deconv_layers is different len(num_deconv_filters)'
layers = []
inplanes = 640
for i in range(num_layers):
kernel, padding, output_padding = 4, 1, 0
planes = num_filters[i]
fc = DCN(inplanes, planes,
kernel_size=(3, 3), stride=1,
padding=1, dilation=1, deformable_groups=1)
up = nn.ConvTranspose2d(
in_channels=planes,
out_channels=planes,
kernel_size=kernel,
stride=2,
padding=padding,
output_padding=output_padding,
bias=False)
layers.append(fc)
layers.append(nn.BatchNorm2d(planes, momentum=0.1))
layers.append(nn.ReLU(inplace=True))
layers.append(up)
layers.append(nn.BatchNorm2d(planes, momentum=0.1))
layers.append(nn.ReLU(inplace=True))
inplanes = planes
return nn.Sequential(*layers)
def __init__(self, chi, cho):
super(DeformConv, self).__init__()
self.actf = nn.Sequential(
nn.BatchNorm2d(cho, momentum=BN_MOMENTUM),
nn.ReLU(inplace=True)
)
self.conv = DCN(chi, cho, kernel_size=(3,3), stride=1, padding=1, dilation=1, deformable_groups=1)
def _make_dcn_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.AvgPool2d(kernel_size=stride,
stride=stride,
ceil_mode=True,
count_include_pad=False),
DCN(self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=1),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(
block(self.inplanes,
planes,
stride,
downsample=downsample,
stype='stage',
baseWidth=self.baseWidth,
scale=self.scale))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(
block(self.inplanes,
planes,
baseWidth=self.baseWidth,
scale=self.scale))
return nn.Sequential(*layers)
def __init__(self, in_channels, out_channels):
super(Upsample, self).__init__()
self.conv1 = DCN(in_channels, out_channels,
kernel_size=(3, 3), stride=1,
padding=1, dilation=1, deformable_groups=1)
# self.conv1 = nn.Conv2d(in_channels, out_channels, 3, 1, 1)
self.bn1 = nn.BatchNorm2d(out_channels)
self.conv2 = nn.ConvTranspose2d(out_channels, out_channels, kernel_size=4,
padding=1, stride=2, bias=False)
self.bn2 = nn.BatchNorm2d(out_channels)
self.relu = nn.ReLU(inplace=True)
def _make_deconv_layer(self, num_layers, num_filters, num_kernels):
assert num_layers == len(num_filters), \
'ERROR: num_deconv_layers is different len(num_deconv_filters)'
assert num_layers == len(num_kernels), \
'ERROR: num_deconv_layers is different len(num_deconv_filters)'
layers = []
for i in range(num_layers):
kernel, padding, output_padding = \
self._get_deconv_cfg(num_kernels[i], i)
planes = num_filters[i]
fc = DCN(self.inplanes, planes,
kernel_size=(3,3), stride=1,
padding=1, dilation=1, deformable_groups=1)
# fc = nn.Conv2d(self.inplanes, planes,
# kernel_size=3, stride=1,
# padding=1, dilation=1, bias=False)
# fill_fc_weights(fc)
up = nn.ConvTranspose2d(
in_channels=planes,
out_channels=planes,
kernel_size=kernel,
stride=2,
padding=padding,
output_padding=output_padding,
bias=self.deconv_with_bias)
fill_up_weights(up)
layers.append(fc)
layers.append(nn.BatchNorm2d(planes, momentum=BN_MOMENTUM))
layers.append(nn.ReLU(inplace=True))
layers.append(up)
layers.append(nn.BatchNorm2d(planes, momentum=BN_MOMENTUM))
layers.append(nn.ReLU(inplace=True))
self.inplanes = planes
return nn.Sequential(*layers)