Method __init__

models/vae.py:162–243

(
        self,
        *,
        ch=128,
        out_ch=3,
        ch_mult=(1, 1, 2, 2, 4),
        num_res_blocks=2,
        attn_resolutions=(16,),
        dropout=0.0,
        resamp_with_conv=True,
        in_channels=3,
        resolution=256,
        z_channels=16,
        double_z=True,
        **ignore_kwargs,
    )

class Encoder(nn.Module):
    def __init__(
        self,
        *,
        ch=128,
        out_ch=3,
        ch_mult=(1, 1, 2, 2, 4),
        num_res_blocks=2,
        attn_resolutions=(16,),
        dropout=0.0,
        resamp_with_conv=True,
        in_channels=3,
        resolution=256,
        z_channels=16,
        double_z=True,
        **ignore_kwargs,
    ):
        super().__init__()
        self.ch = ch
        self.temb_ch = 0
        self.num_resolutions = len(ch_mult)
        self.num_res_blocks = num_res_blocks
        self.resolution = resolution
        self.in_channels = in_channels

        # downsampling
        self.conv_in = torch.nn.Conv2d(
            in_channels, self.ch, kernel_size=3, stride=1, padding=1
        )

        curr_res = resolution
        in_ch_mult = (1,) + tuple(ch_mult)
        self.down = nn.ModuleList()
        for i_level in range(self.num_resolutions):
            block = nn.ModuleList()
            attn = nn.ModuleList()
            block_in = ch * in_ch_mult[i_level]
            block_out = ch * ch_mult[i_level]
            for i_block in range(self.num_res_blocks):
                block.append(
                    ResnetBlock(
                        in_channels=block_in,
                        out_channels=block_out,
                        temb_channels=self.temb_ch,
                        dropout=dropout,
                    )
                )
                block_in = block_out
                if curr_res in attn_resolutions:
                    attn.append(AttnBlock(block_in))
            down = nn.Module()
            down.block = block
            down.attn = attn
            if i_level != self.num_resolutions - 1:
                down.downsample = Downsample(block_in, resamp_with_conv)
                curr_res = curr_res // 2
            self.down.append(down)

        # middle