def __init__()

in models/convnext.py [0:0]

• 32 lines of code
• 6 McCabe index (conditional complexity)

    def __init__(self, in_chans=3, num_classes=1000, 
                 depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], drop_path_rate=0., 
                 layer_scale_init_value=1e-6, head_init_scale=1.,
                 ):
        super().__init__()

        self.downsample_layers = nn.ModuleList() # stem and 3 intermediate downsampling conv layers
        stem = nn.Sequential(
            nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
            LayerNorm(dims[0], eps=1e-6, data_format="channels_first")
        )
        self.downsample_layers.append(stem)
        for i in range(3):
            downsample_layer = nn.Sequential(
                    LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
                    nn.Conv2d(dims[i], dims[i+1], kernel_size=2, stride=2),
            )
            self.downsample_layers.append(downsample_layer)

        self.stages = nn.ModuleList() # 4 feature resolution stages, each consisting of multiple residual blocks
        dp_rates=[x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] 
        cur = 0
        for i in range(4):
            stage = nn.Sequential(
                *[Block(dim=dims[i], drop_path=dp_rates[cur + j], 
                layer_scale_init_value=layer_scale_init_value) for j in range(depths[i])]
            )
            self.stages.append(stage)
            cur += depths[i]

        self.norm = nn.LayerNorm(dims[-1], eps=1e-6) # final norm layer
        self.head = nn.Linear(dims[-1], num_classes)

        self.apply(self._init_weights)
        self.head.weight.data.mul_(head_init_scale)
        self.head.bias.data.mul_(head_init_scale)