src/controlnet_aux/mlsd/models/mbv2_mlsd_large.py [9:26]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class BlockTypeA(nn.Module):
    def __init__(self, in_c1, in_c2, out_c1, out_c2, upscale = True):
        super(BlockTypeA, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(in_c2, out_c2, kernel_size=1),
            nn.BatchNorm2d(out_c2),
            nn.ReLU(inplace=True)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(in_c1, out_c1, kernel_size=1),
            nn.BatchNorm2d(out_c1),
            nn.ReLU(inplace=True)
        )
        self.upscale = upscale

    def forward(self, a, b):
        b = self.conv1(b)
        a = self.conv2(a)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/controlnet_aux/mlsd/models/mbv2_mlsd_tiny.py [9:26]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class BlockTypeA(nn.Module):
    def __init__(self, in_c1, in_c2, out_c1, out_c2, upscale = True):
        super(BlockTypeA, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(in_c2, out_c2, kernel_size=1),
            nn.BatchNorm2d(out_c2),
            nn.ReLU(inplace=True)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(in_c1, out_c1, kernel_size=1),
            nn.BatchNorm2d(out_c1),
            nn.ReLU(inplace=True)
        )
        self.upscale = upscale

    def forward(self, a, b):
        b = self.conv1(b)
        a = self.conv2(a)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -