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_deconv_layer(self,
num_layers,
num_filters,
num_kernels,
stage=1):
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)'
deconv_layers = []
for i in range(num_layers):
deconv_layer = []
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)
deconv_layer.append(fc)
deconv_layer.append(nn.BatchNorm2d(planes, momentum=BN_MOMENTUM))
deconv_layer.append(nn.ReLU(inplace=True))
deconv_layer.append(up)
deconv_layer.append(nn.BatchNorm2d(planes, momentum=BN_MOMENTUM))
deconv_layer.append(nn.ReLU(inplace=True))
deconv_layer_i = nn.Sequential(*deconv_layer)
if stage == 1:
layer_name = 'stage_one_deconv_layer{}'.format(i + 1)
else:
layer_name = 'stage_two_deconv_layer{}'.format(i + 1)
self.add_module(layer_name, deconv_layer_i)
deconv_layers.append(layer_name)
self.inplanes = planes
return deconv_layers
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)