Method __init__

flux/modules/autoencoder.py:184–235

(
        self,
        ch: int,
        out_ch: int,
        ch_mult: list[int],
        num_res_blocks: int,
        in_channels: int,
        resolution: int,
        z_channels: int,
    )

class Decoder(nn.Module):
    def __init__(
        self,
        ch: int,
        out_ch: int,
        ch_mult: list[int],
        num_res_blocks: int,
        in_channels: int,
        resolution: int,
        z_channels: int,
    ):
        super().__init__()
        self.ch = ch
        self.num_resolutions = len(ch_mult)
        self.num_res_blocks = num_res_blocks
        self.resolution = resolution
        self.in_channels = in_channels
        self.ffactor = 2 ** (self.num_resolutions - 1)

        # compute in_ch_mult, block_in and curr_res at lowest res
        block_in = ch * ch_mult[self.num_resolutions - 1]
        curr_res = resolution // 2 ** (self.num_resolutions - 1)
        self.z_shape = (1, z_channels, curr_res, curr_res)

        # z to block_in
        self.conv_in = nn.Conv2d(z_channels, block_in, kernel_size=3, stride=1, padding=1)

        # middle
        self.mid = nn.Module()
        self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in)
        self.mid.attn_1 = AttnBlock(block_in)
        self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in)

        # upsampling
        self.up = nn.ModuleList()
        for i_level in reversed(range(self.num_resolutions)):
            block = nn.ModuleList()
            attn = nn.ModuleList()
            block_out = ch * ch_mult[i_level]
            for _ in range(self.num_res_blocks + 1):
                block.append(ResnetBlock(in_channels=block_in, out_channels=block_out))
                block_in = block_out
            up = nn.Module()
            up.block = block
            up.attn = attn
            if i_level != 0:
                up.upsample = Upsample(block_in)
                curr_res = curr_res * 2
            self.up.insert(0, up)  # prepend to get consistent order

        # end
        self.norm_out = nn.GroupNorm(num_groups=32, num_channels=block_in, eps=1e-6, affine=True)
        self.conv_out = nn.Conv2d(block_in, out_ch, kernel_size=3, stride=1, padding=1)

    def forward(self, z: Tensor) -> Tensor:
        # z to block_in