improved_model_arch.py

from imports import *

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d

class Residual(nn.Module):
    def __init__(self, fn):
        super().__init__()
        self.fn = fn

    def forward(self, x, *args, **kwargs):
        return self.fn(x, *args, **kwargs) + x

def Upsample(dim):
    return nn.ConvTranspose2d(dim, dim, 4, 2, 1)

def Downsample(dim):
    return nn.Conv2d(dim, dim, 4, 2, 1)

class SinusoidalPositionEmbeddings(nn.Module):
  def __init__(self, dim):
    super().__init__()
    self.dim = dim

  def forward(self, t):
    device = t.device
    half_dim = self.dim//2
    embeddings = math.log(10000)/(half_dim - 1)
    embeddings = torch.exp(torch.arange(half_dim, device = device)*-embeddings)
    embeddings = t[:, None] * embeddings[None, :]
    embeddings = torch.cat((embeddings.sin(), embeddings.cos()), dim=-1)
    return embeddings


class Block(nn.Module):
  def __init__(self, dim, dim_out, groups = 8):
    super().__init__()
    self.conv = nn.Conv2d(dim, dim_out, 3, padding=1)
    self.norm = nn.GroupNorm(groups, dim_out)
    self.act = nn.SiLU()

  def forward(self, x, scale_shift = None):
    x= self.norm(self.conv(x))

    if exists(scale_shift):
      scale, shift = scale_shift
      x = x*(scale + 1) + shift

    x = self.act(x)
    return x

class ResnetBlock(nn.Module):
  def __init__(self, dim, dim_out, *, time_emb_dim=None, groups = 8):
    super().__init__()
    if exists(time_emb_dim):
      self.mlp = (nn.Sequential(nn.SiLU(), nn.Linear(time_emb_dim, dim_out)))

    else:
      self.mlp = (None)

    self.block1 = Block(dim, dim_out, groups = groups)
    self.block2 = Block(dim_out, dim_out, groups = groups)
    if dim != dim_out:
      self.res_conv = nn.Conv2d(dim, dim_out, 1)
    else:
      self.res_conv = nn.Identity()

  def forward(self, x, time_emb = None):
    h = self.block1(x)

    if exists(self.mlp) and exists(time_emb):
      time_emb = self.mlp(time_emb)
      h = rearrange(time_emb, "b c -> b c 1 1") + h

    h = self.block2(h)
    return h + self.res_conv(x)

class LinearAttention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32):
        super().__init__()
        self.scale = dim_head**-0.5
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias=False)

        self.to_out = nn.Sequential(nn.Conv2d(hidden_dim, dim, 1),
                                    nn.GroupNorm(1, dim))

    def forward(self, x):
        b, c, h, w = x.shape
        qkv = self.to_qkv(x).chunk(3, dim=1)
        q, k, v = map(
            lambda t: rearrange(t, "b (h c) x y -> b h c (x y)", h=self.heads), qkv
        )

        q = q.softmax(dim=-2)
        k = k.softmax(dim=-1)

        q = q * self.scale
        context = torch.einsum("b h d n, b h e n -> b h d e", k, v)

        out = torch.einsum("b h d e, b h d n -> b h e n", context, q)
        out = rearrange(out, "b h c (x y) -> b (h c) x y", h=self.heads, x=h, y=w)
        return self.to_out(out)

class PreNorm(nn.Module):
    def __init__(self, dim, fn):
        super().__init__()
        self.fn = fn
        self.norm = nn.GroupNorm(1, dim)

    def forward(self, x):
        x = self.norm(x)
        return self.fn(x)

class Unet(nn.Module):
    def __init__(
        self,
        dim,
        init_dim=None,
        out_dim=None,
        dim_mults=(1, 2, 4, 8),
        channels=3,
        with_time_emb=True,
        resnet_block_groups=8,
    ):
        super().__init__()

        # determine dimensions
        self.channels = channels

        init_dim = default(init_dim, dim // 3 * 2)
        self.init_conv = nn.Conv2d(channels, init_dim, 7, padding=3)

        dims = [init_dim, *map(lambda m: dim * m, dim_mults)] #scales the dimensions at different levels of the unet
        in_out = list(zip(dims[:-1], dims[1:]))

        block_klass = partial(ResnetBlock, groups=resnet_block_groups)

        # time embeddings
        if with_time_emb:
            time_dim = dim * 4
            self.time_mlp = nn.Sequential(
                SinusoidalPositionEmbeddings(dim),
                nn.Linear(dim, time_dim),
                nn.GELU(),
                nn.Linear(time_dim, time_dim),
            )
        else:
            time_dim = None
            self.time_mlp = None

        # layers
        self.downs = nn.ModuleList([])
        self.ups = nn.ModuleList([])
        num_resolutions = len(in_out)

        for ind, (dim_in, dim_out) in enumerate(in_out):
            is_last = ind >= (num_resolutions - 1)

            self.downs.append(
                nn.ModuleList(
                    [
                        block_klass(dim_in, dim_out, time_emb_dim=time_dim),
                        block_klass(dim_out, dim_out, time_emb_dim=time_dim),
                        Residual(PreNorm(dim_out, LinearAttention(dim_out))),
                        Downsample(dim_out) if not is_last else nn.Identity(),
                    ]
                )
            )

        mid_dim = dims[-1]
        self.mid_block1 = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)
        self.mid_attn = Residual(PreNorm(mid_dim, LinearAttention(mid_dim)))
        self.mid_block2 = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)

        for ind, (dim_in, dim_out) in enumerate(reversed(in_out[1:])):
            is_last = ind >= (num_resolutions - 1)

            self.ups.append(
                nn.ModuleList(
                    [
                        block_klass(dim_out * 2, dim_in, time_emb_dim=time_dim),
                        block_klass(dim_in, dim_in, time_emb_dim=time_dim),
                        Residual(PreNorm(dim_in, LinearAttention(dim_in))),
                        Upsample(dim_in) if not is_last else nn.Identity(),
                    ]
                )
            )

        out_dim = default(out_dim, channels)
        self.final_conv = nn.Sequential(
            block_klass(dim, dim), nn.Conv2d(dim, out_dim, 1)
        )

    def forward(self, x, time):
        x = self.init_conv(x)

        t = self.time_mlp(time) if exists(self.time_mlp) else None

        h = []

        # downsample
        for block1, block2, attn, downsample in self.downs:
            x = block1(x, t)
            x = block2(x, t)
            x = attn(x)
            h.append(x)
            x = downsample(x)

        # bottleneck
        x = self.mid_block1(x, t)
        x = self.mid_attn(x)
        x = self.mid_block2(x, t)

        # upsample
        for block1, block2, attn, upsample in self.ups:
            x = torch.cat((x, h.pop()), dim=1)
            x = block1(x, t)
            x = block2(x, t)
            x = attn(x)
            x = upsample(x)

        return self.final_conv(x)