def __init__(self, in_planes, out_planes, expansion_factor, stride=1):
super(InvertedResidualBlock, self).__init__()
intermed_planes = in_planes * expansion_factor
self.residual = (in_planes == out_planes) and (stride == 1)
self.output = nn.Sequential(convbnrelu(in_planes, intermed_planes, 1),
convbnrelu(intermed_planes, intermed_planes, 3, stride=stride, groups=intermed_planes),
convbnrelu(intermed_planes, out_planes, 1, act=False))
def __init__(self, num_classes):
super(MBv2, self).__init__()
self.layer1 = convbnrelu(3, self.in_planes, kernel_size=3, stride=2)
c_layer = 2
for t,c,n,s in (self.mobilenet_config):
layers = []
for idx in range(n):
layers.append(InvertedResidualBlock(self.in_planes, c, expansion_factor=t, stride=s if idx == 0 else 1))
self.in_planes = c
setattr(self, 'layer{}'.format(c_layer), nn.Sequential(*layers))
c_layer += 1
## Light-Weight RefineNet ##
self.conv8 = conv1x1(320, 256, bias=False)
self.conv7 = conv1x1(160, 256, bias=False)
self.conv6 = conv1x1(96, 256, bias=False)
self.conv5 = conv1x1(64, 256, bias=False)
self.conv4 = conv1x1(32, 256, bias=False)
self.conv3 = conv1x1(24, 256, bias=False)
self.crp4 = self._make_crp(256, 256, 4)
self.crp3 = self._make_crp(256, 256, 4)
self.crp2 = self._make_crp(256, 256, 4)
self.crp1 = self._make_crp(256, 256, 4)
self.conv_adapt4 = conv1x1(256, 256, bias=False)
self.conv_adapt3 = conv1x1(256, 256, bias=False)
self.conv_adapt2 = conv1x1(256, 256, bias=False)
self.segm = conv3x3(256, num_classes, bias=True)
self.relu = nn.ReLU6(inplace=True)
self._initialize_weights()