unet_ldm.py

import math
from abc import abstractmethod
from inspect import isfunction

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F


try:
    from einops import rearrange, repeat
except:
    print("Einops is not installed")
    pass

from ..configuration_utils import ConfigMixin
from ..modeling_utils import ModelMixin
from .embeddings import get_timestep_embedding


def exists(val):
    return val is not None


def uniq(arr):
    return {el: True for el in arr}.keys()


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


def max_neg_value(t):
    return -torch.finfo(t.dtype).max


def init_(tensor):
    dim = tensor.shape[-1]
    std = 1 / math.sqrt(dim)
    tensor.uniform_(-std, std)
    return tensor


# feedforward
class GEGLU(nn.Module):
    def __init__(self, dim_in, dim_out):
        super().__init__()
        self.proj = nn.Linear(dim_in, dim_out * 2)

    def forward(self, x):
        x, gate = self.proj(x).chunk(2, dim=-1)
        return x * F.gelu(gate)


class FeedForward(nn.Module):
    def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.0):
        super().__init__()
        inner_dim = int(dim * mult)
        dim_out = default(dim_out, dim)
        project_in = nn.Sequential(nn.Linear(dim, inner_dim), nn.GELU()) if not glu else GEGLU(dim, inner_dim)

        self.net = nn.Sequential(project_in, nn.Dropout(dropout), nn.Linear(inner_dim, dim_out))

    def forward(self, x):
        return self.net(x)


def zero_module(module):
    """
    Zero out the parameters of a module and return it.
    """
    for p in module.parameters():
        p.detach().zero_()
    return module


def Normalize(in_channels):
    return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)


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

    def forward(self, x):
        b, c, h, w = x.shape
        qkv = self.to_qkv(x)
        q, k, v = rearrange(qkv, "b (qkv heads c) h w -> qkv b heads c (h w)", heads=self.heads, qkv=3)
        k = k.softmax(dim=-1)
        context = torch.einsum("bhdn,bhen->bhde", k, v)
        out = torch.einsum("bhde,bhdn->bhen", context, q)
        out = rearrange(out, "b heads c (h w) -> b (heads c) h w", heads=self.heads, h=h, w=w)
        return self.to_out(out)


class SpatialSelfAttention(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        self.in_channels = in_channels

        self.norm = Normalize(in_channels)
        self.q = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
        self.k = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
        self.v = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)
        self.proj_out = torch.nn.Conv2d(in_channels, in_channels, kernel_size=1, stride=1, padding=0)

    def forward(self, x):
        h_ = x
        h_ = self.norm(h_)
        q = self.q(h_)
        k = self.k(h_)
        v = self.v(h_)

        # compute attention
        b, c, h, w = q.shape
        q = rearrange(q, "b c h w -> b (h w) c")
        k = rearrange(k, "b c h w -> b c (h w)")
        w_ = torch.einsum("bij,bjk->bik", q, k)

        w_ = w_ * (int(c) ** (-0.5))
        w_ = torch.nn.functional.softmax(w_, dim=2)

        # attend to values
        v = rearrange(v, "b c h w -> b c (h w)")
        w_ = rearrange(w_, "b i j -> b j i")
        h_ = torch.einsum("bij,bjk->bik", v, w_)
        h_ = rearrange(h_, "b c (h w) -> b c h w", h=h)
        h_ = self.proj_out(h_)

        return x + h_


class CrossAttention(nn.Module):
    def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.0):
        super().__init__()
        inner_dim = dim_head * heads
        context_dim = default(context_dim, query_dim)

        self.scale = dim_head**-0.5
        self.heads = heads

        self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
        self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
        self.to_v = nn.Linear(context_dim, inner_dim, bias=False)

        self.to_out = nn.Sequential(nn.Linear(inner_dim, query_dim), nn.Dropout(dropout))

    def forward(self, x, context=None, mask=None):
        h = self.heads

        q = self.to_q(x)
        context = default(context, x)
        k = self.to_k(context)
        v = self.to_v(context)

        q, k, v = map(lambda t: rearrange(t, "b n (h d) -> (b h) n d", h=h), (q, k, v))

        sim = torch.einsum("b i d, b j d -> b i j", q, k) * self.scale

        if exists(mask):
            mask = rearrange(mask, "b ... -> b (...)")
            max_neg_value = -torch.finfo(sim.dtype).max
            mask = repeat(mask, "b j -> (b h) () j", h=h)
            sim.masked_fill_(~mask, max_neg_value)

        # attention, what we cannot get enough of
        attn = sim.softmax(dim=-1)

        out = torch.einsum("b i j, b j d -> b i d", attn, v)
        out = rearrange(out, "(b h) n d -> b n (h d)", h=h)
        return self.to_out(out)


class BasicTransformerBlock(nn.Module):
    def __init__(self, dim, n_heads, d_head, dropout=0.0, context_dim=None, gated_ff=True, checkpoint=True):
        super().__init__()
        self.attn1 = CrossAttention(
            query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout
        )  # is a self-attention
        self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
        self.attn2 = CrossAttention(
            query_dim=dim, context_dim=context_dim, heads=n_heads, dim_head=d_head, dropout=dropout
        )  # is self-attn if context is none
        self.norm1 = nn.LayerNorm(dim)
        self.norm2 = nn.LayerNorm(dim)
        self.norm3 = nn.LayerNorm(dim)
        self.checkpoint = checkpoint

    def forward(self, x, context=None):
        x = self.attn1(self.norm1(x)) + x
        x = self.attn2(self.norm2(x), context=context) + x
        x = self.ff(self.norm3(x)) + x
        return x


class SpatialTransformer(nn.Module):
    """
    Transformer block for image-like data.
    First, project the input (aka embedding)
    and reshape to b, t, d.
    Then apply standard transformer action.
    Finally, reshape to image
    """

    def __init__(self, in_channels, n_heads, d_head, depth=1, dropout=0.0, context_dim=None):
        super().__init__()
        self.in_channels = in_channels
        inner_dim = n_heads * d_head
        self.norm = Normalize(in_channels)

        self.proj_in = nn.Conv2d(in_channels, inner_dim, kernel_size=1, stride=1, padding=0)

        self.transformer_blocks = nn.ModuleList(
            [
                BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim)
                for d in range(depth)
            ]
        )

        self.proj_out = zero_module(nn.Conv2d(inner_dim, in_channels, kernel_size=1, stride=1, padding=0))

    def forward(self, x, context=None):
        # note: if no context is given, cross-attention defaults to self-attention
        b, c, h, w = x.shape
        x_in = x
        x = self.norm(x)
        x = self.proj_in(x)
        x = rearrange(x, "b c h w -> b (h w) c")
        for block in self.transformer_blocks:
            x = block(x, context=context)
        x = rearrange(x, "b (h w) c -> b c h w", h=h, w=w)
        x = self.proj_out(x)
        return x + x_in


def convert_module_to_f16(l):
    """
    Convert primitive modules to float16.
    """
    if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)):
        l.weight.data = l.weight.data.half()
        if l.bias is not None:
            l.bias.data = l.bias.data.half()


def convert_module_to_f32(l):
    """
    Convert primitive modules to float32, undoing convert_module_to_f16().
    """
    if isinstance(l, (nn.Conv1d, nn.Conv2d, nn.Conv3d)):
        l.weight.data = l.weight.data.float()
        if l.bias is not None:
            l.bias.data = l.bias.data.float()


def avg_pool_nd(dims, *args, **kwargs):
    """
    Create a 1D, 2D, or 3D average pooling module.
    """
    if dims == 1:
        return nn.AvgPool1d(*args, **kwargs)
    elif dims == 2:
        return nn.AvgPool2d(*args, **kwargs)
    elif dims == 3:
        return nn.AvgPool3d(*args, **kwargs)
    raise ValueError(f"unsupported dimensions: {dims}")


def conv_nd(dims, *args, **kwargs):
    """
    Create a 1D, 2D, or 3D convolution module.
    """
    if dims == 1:
        return nn.Conv1d(*args, **kwargs)
    elif dims == 2:
        return nn.Conv2d(*args, **kwargs)
    elif dims == 3:
        return nn.Conv3d(*args, **kwargs)
    raise ValueError(f"unsupported dimensions: {dims}")


def linear(*args, **kwargs):
    """
    Create a linear module.
    """
    return nn.Linear(*args, **kwargs)


class GroupNorm32(nn.GroupNorm):
    def __init__(self, num_groups, num_channels, swish, eps=1e-5):
        super().__init__(num_groups=num_groups, num_channels=num_channels, eps=eps)
        self.swish = swish

    def forward(self, x):
        y = super().forward(x.float()).to(x.dtype)
        if self.swish == 1.0:
            y = F.silu(y)
        elif self.swish:
            y = y * F.sigmoid(y * float(self.swish))
        return y


def normalization(channels, swish=0.0):
    """
    Make a standard normalization layer, with an optional swish activation.

    :param channels: number of input channels.
    :return: an nn.Module for normalization.
    """
    return GroupNorm32(num_channels=channels, num_groups=32, swish=swish)


## go
class AttentionPool2d(nn.Module):
    """
    Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py
    """

    def __init__(
        self,
        spacial_dim: int,
        embed_dim: int,
        num_heads_channels: int,
        output_dim: int = None,
    ):
        super().__init__()
        self.positional_embedding = nn.Parameter(torch.randn(embed_dim, spacial_dim**2 + 1) / embed_dim**0.5)
        self.qkv_proj = conv_nd(1, embed_dim, 3 * embed_dim, 1)
        self.c_proj = conv_nd(1, embed_dim, output_dim or embed_dim, 1)
        self.num_heads = embed_dim // num_heads_channels
        self.attention = QKVAttention(self.num_heads)

    def forward(self, x):
        b, c, *_spatial = x.shape
        x = x.reshape(b, c, -1)  # NC(HW)
        x = torch.cat([x.mean(dim=-1, keepdim=True), x], dim=-1)  # NC(HW+1)
        x = x + self.positional_embedding[None, :, :].to(x.dtype)  # NC(HW+1)
        x = self.qkv_proj(x)
        x = self.attention(x)
        x = self.c_proj(x)
        return x[:, :, 0]


class TimestepBlock(nn.Module):
    """
    Any module where forward() takes timestep embeddings as a second argument.
    """

    @abstractmethod
    def forward(self, x, emb):
        """
        Apply the module to `x` given `emb` timestep embeddings.
        """


class TimestepEmbedSequential(nn.Sequential, TimestepBlock):
    """
    A sequential module that passes timestep embeddings to the children that
    support it as an extra input.
    """

    def forward(self, x, emb, context=None):
        for layer in self:
            if isinstance(layer, TimestepBlock):
                x = layer(x, emb)
            elif isinstance(layer, SpatialTransformer):
                x = layer(x, context)
            else:
                x = layer(x)
        return x


class Upsample(nn.Module):
    """
    An upsampling layer with an optional convolution.
    :param channels: channels in the inputs and outputs.
    :param use_conv: a bool determining if a convolution is applied.
    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
                 upsampling occurs in the inner-two dimensions.
    """

    def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        if use_conv:
            self.conv = conv_nd(dims, self.channels, self.out_channels, 3, padding=padding)

    def forward(self, x):
        assert x.shape[1] == self.channels
        if self.dims == 3:
            x = F.interpolate(x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest")
        else:
            x = F.interpolate(x, scale_factor=2, mode="nearest")
        if self.use_conv:
            x = self.conv(x)
        return x


class Downsample(nn.Module):
    """
    A downsampling layer with an optional convolution.
    :param channels: channels in the inputs and outputs.
    :param use_conv: a bool determining if a convolution is applied.
    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
                 downsampling occurs in the inner-two dimensions.
    """

    def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
        super().__init__()
        self.channels = channels
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.dims = dims
        stride = 2 if dims != 3 else (1, 2, 2)
        if use_conv:
            self.op = conv_nd(dims, self.channels, self.out_channels, 3, stride=stride, padding=padding)
        else:
            assert self.channels == self.out_channels
            self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)

    def forward(self, x):
        assert x.shape[1] == self.channels
        return self.op(x)


class ResBlock(TimestepBlock):
    """
    A residual block that can optionally change the number of channels.
    :param channels: the number of input channels.
    :param emb_channels: the number of timestep embedding channels.
    :param dropout: the rate of dropout.
    :param out_channels: if specified, the number of out channels.
    :param use_conv: if True and out_channels is specified, use a spatial
        convolution instead of a smaller 1x1 convolution to change the
        channels in the skip connection.
    :param dims: determines if the signal is 1D, 2D, or 3D.
    :param use_checkpoint: if True, use gradient checkpointing on this module.
    :param up: if True, use this block for upsampling.
    :param down: if True, use this block for downsampling.
    """

    def __init__(
        self,
        channels,
        emb_channels,
        dropout,
        out_channels=None,
        use_conv=False,
        use_scale_shift_norm=False,
        dims=2,
        use_checkpoint=False,
        up=False,
        down=False,
    ):
        super().__init__()
        self.channels = channels
        self.emb_channels = emb_channels
        self.dropout = dropout
        self.out_channels = out_channels or channels
        self.use_conv = use_conv
        self.use_checkpoint = use_checkpoint
        self.use_scale_shift_norm = use_scale_shift_norm

        self.in_layers = nn.Sequential(
            normalization(channels),
            nn.SiLU(),
            conv_nd(dims, channels, self.out_channels, 3, padding=1),
        )

        self.updown = up or down

        if up:
            self.h_upd = Upsample(channels, False, dims)
            self.x_upd = Upsample(channels, False, dims)
        elif down:
            self.h_upd = Downsample(channels, False, dims)
            self.x_upd = Downsample(channels, False, dims)
        else:
            self.h_upd = self.x_upd = nn.Identity()

        self.emb_layers = nn.Sequential(
            nn.SiLU(),
            linear(
                emb_channels,
                2 * self.out_channels if use_scale_shift_norm else self.out_channels,
            ),
        )
        self.out_layers = nn.Sequential(
            normalization(self.out_channels),
            nn.SiLU(),
            nn.Dropout(p=dropout),
            zero_module(conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1)),
        )

        if self.out_channels == channels:
            self.skip_connection = nn.Identity()
        elif use_conv:
            self.skip_connection = conv_nd(dims, channels, self.out_channels, 3, padding=1)
        else:
            self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)

    def forward(self, x, emb):
        if self.updown:
            in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1]
            h = in_rest(x)
            h = self.h_upd(h)
            x = self.x_upd(x)
            h = in_conv(h)
        else:
            h = self.in_layers(x)
        emb_out = self.emb_layers(emb).type(h.dtype)
        while len(emb_out.shape) < len(h.shape):
            emb_out = emb_out[..., None]
        if self.use_scale_shift_norm:
            out_norm, out_rest = self.out_layers[0], self.out_layers[1:]
            scale, shift = torch.chunk(emb_out, 2, dim=1)
            h = out_norm(h) * (1 + scale) + shift
            h = out_rest(h)
        else:
            h = h + emb_out
            h = self.out_layers(h)
        return self.skip_connection(x) + h


class AttentionBlock(nn.Module):
    """
    An attention block that allows spatial positions to attend to each other.
    Originally ported from here, but adapted to the N-d case.
    https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/models/unet.py#L66.
    """

    def __init__(
        self,
        channels,
        num_heads=1,
        num_head_channels=-1,
        use_checkpoint=False,
        use_new_attention_order=False,
    ):
        super().__init__()
        self.channels = channels
        if num_head_channels == -1:
            self.num_heads = num_heads
        else:
            assert (
                channels % num_head_channels == 0
            ), f"q,k,v channels {channels} is not divisible by num_head_channels {num_head_channels}"
            self.num_heads = channels // num_head_channels
        self.use_checkpoint = use_checkpoint
        self.norm = normalization(channels)
        self.qkv = conv_nd(1, channels, channels * 3, 1)
        # split heads before split qkv
        self.attention = QKVAttentionLegacy(self.num_heads)

        self.proj_out = zero_module(conv_nd(1, channels, channels, 1))

    def forward(self, x):
        b, c, *spatial = x.shape
        x = x.reshape(b, c, -1)
        qkv = self.qkv(self.norm(x))
        h = self.attention(qkv)
        h = self.proj_out(h)
        return (x + h).reshape(b, c, *spatial)


class QKVAttention(nn.Module):
    """
    A module which performs QKV attention and splits in a different order.
    """

    def __init__(self, n_heads):
        super().__init__()
        self.n_heads = n_heads

    def forward(self, qkv):
        """
        Apply QKV attention.
        :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs.
        :return: an [N x (H * C) x T] tensor after attention.
        """
        bs, width, length = qkv.shape
        assert width % (3 * self.n_heads) == 0
        ch = width // (3 * self.n_heads)
        q, k, v = qkv.chunk(3, dim=1)
        scale = 1 / math.sqrt(math.sqrt(ch))
        weight = torch.einsum(
            "bct,bcs->bts",
            (q * scale).view(bs * self.n_heads, ch, length),
            (k * scale).view(bs * self.n_heads, ch, length),
        )  # More stable with f16 than dividing afterwards
        weight = torch.softmax(weight.float(), dim=-1).type(weight.dtype)
        a = torch.einsum("bts,bcs->bct", weight, v.reshape(bs * self.n_heads, ch, length))
        return a.reshape(bs, -1, length)

    @staticmethod
    def count_flops(model, _x, y):
        return count_flops_attn(model, _x, y)


def count_flops_attn(model, _x, y):
    """
    A counter for the `thop` package to count the operations in an
    attention operation.
    Meant to be used like:
        macs, params = thop.profile(
            model,
            inputs=(inputs, timestamps),
            custom_ops={QKVAttention: QKVAttention.count_flops},
        )
    """
    b, c, *spatial = y[0].shape
    num_spatial = int(np.prod(spatial))
    # We perform two matmuls with the same number of ops.
    # The first computes the weight matrix, the second computes
    # the combination of the value vectors.
    matmul_ops = 2 * b * (num_spatial**2) * c
    model.total_ops += torch.DoubleTensor([matmul_ops])


class QKVAttentionLegacy(nn.Module):
    """
    A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping
    """

    def __init__(self, n_heads):
        super().__init__()
        self.n_heads = n_heads

    def forward(self, qkv):
        """
        Apply QKV attention.
        :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs.
        :return: an [N x (H * C) x T] tensor after attention.
        """
        bs, width, length = qkv.shape
        assert width % (3 * self.n_heads) == 0
        ch = width // (3 * self.n_heads)
        q, k, v = qkv.reshape(bs * self.n_heads, ch * 3, length).split(ch, dim=1)
        scale = 1 / math.sqrt(math.sqrt(ch))
        weight = torch.einsum("bct,bcs->bts", q * scale, k * scale)  # More stable with f16 than dividing afterwards
        weight = torch.softmax(weight.float(), dim=-1).type(weight.dtype)
        a = torch.einsum("bts,bcs->bct", weight, v)
        return a.reshape(bs, -1, length)

    @staticmethod
    def count_flops(model, _x, y):
        return count_flops_attn(model, _x, y)


class UNetLDMModel(ModelMixin, ConfigMixin):
    """
    The full UNet model with attention and timestep embedding.
    :param in_channels: channels in the input Tensor.
    :param model_channels: base channel count for the model.
    :param out_channels: channels in the output Tensor.
    :param num_res_blocks: number of residual blocks per downsample.
    :param attention_resolutions: a collection of downsample rates at which
        attention will take place. May be a set, list, or tuple.
        For example, if this contains 4, then at 4x downsampling, attention
        will be used.
    :param dropout: the dropout probability.
    :param channel_mult: channel multiplier for each level of the UNet.
    :param conv_resample: if True, use learned convolutions for upsampling and
        downsampling.
    :param dims: determines if the signal is 1D, 2D, or 3D.
    :param num_classes: if specified (as an int), then this model will be
        class-conditional with `num_classes` classes.
    :param use_checkpoint: use gradient checkpointing to reduce memory usage.
    :param num_heads: the number of attention heads in each attention layer.
    :param num_heads_channels: if specified, ignore num_heads and instead use
                               a fixed channel width per attention head.
    :param num_heads_upsample: works with num_heads to set a different number
                               of heads for upsampling. Deprecated.
    :param use_scale_shift_norm: use a FiLM-like conditioning mechanism.
    :param resblock_updown: use residual blocks for up/downsampling.
    :param use_new_attention_order: use a different attention pattern for potentially
                                    increased efficiency.
    """

    def __init__(
        self,
        image_size,
        in_channels,
        model_channels,
        out_channels,
        num_res_blocks,
        attention_resolutions,
        dropout=0,
        channel_mult=(1, 2, 4, 8),
        conv_resample=True,
        dims=2,
        num_classes=None,
        use_checkpoint=False,
        use_fp16=False,
        num_heads=-1,
        num_head_channels=-1,
        num_heads_upsample=-1,
        use_scale_shift_norm=False,
        resblock_updown=False,
        use_new_attention_order=False,
        use_spatial_transformer=False,  # custom transformer support
        transformer_depth=1,  # custom transformer support
        context_dim=None,  # custom transformer support
        n_embed=None,  # custom support for prediction of discrete ids into codebook of first stage vq model
        legacy=True,
    ):
        super().__init__()

        # register all __init__ params with self.register
        self.register_to_config(
            image_size=image_size,
            in_channels=in_channels,
            model_channels=model_channels,
            out_channels=out_channels,
            num_res_blocks=num_res_blocks,
            attention_resolutions=attention_resolutions,
            dropout=dropout,
            channel_mult=channel_mult,
            conv_resample=conv_resample,
            dims=dims,
            num_classes=num_classes,
            use_checkpoint=use_checkpoint,
            use_fp16=use_fp16,
            num_heads=num_heads,
            num_head_channels=num_head_channels,
            num_heads_upsample=num_heads_upsample,
            use_scale_shift_norm=use_scale_shift_norm,
            resblock_updown=resblock_updown,
            use_new_attention_order=use_new_attention_order,
            use_spatial_transformer=use_spatial_transformer,
            transformer_depth=transformer_depth,
            context_dim=context_dim,
            n_embed=n_embed,
            legacy=legacy,
        )

        if use_spatial_transformer:
            assert (
                context_dim is not None
            ), "Fool!! You forgot to include the dimension of your cross-attention conditioning..."

        if context_dim is not None:
            assert (
                use_spatial_transformer
            ), "Fool!! You forgot to use the spatial transformer for your cross-attention conditioning..."

        if num_heads_upsample == -1:
            num_heads_upsample = num_heads

        if num_heads == -1:
            assert num_head_channels != -1, "Either num_heads or num_head_channels has to be set"

        if num_head_channels == -1:
            assert num_heads != -1, "Either num_heads or num_head_channels has to be set"

        self.image_size = image_size
        self.in_channels = in_channels
        self.model_channels = model_channels
        self.out_channels = out_channels
        self.num_res_blocks = num_res_blocks
        self.attention_resolutions = attention_resolutions
        self.dropout = dropout
        self.channel_mult = channel_mult
        self.conv_resample = conv_resample
        self.num_classes = num_classes
        self.use_checkpoint = use_checkpoint
        self.dtype_ = torch.float16 if use_fp16 else torch.float32
        self.num_heads = num_heads
        self.num_head_channels = num_head_channels
        self.num_heads_upsample = num_heads_upsample
        self.predict_codebook_ids = n_embed is not None

        time_embed_dim = model_channels * 4
        self.time_embed = nn.Sequential(
            linear(model_channels, time_embed_dim),
            nn.SiLU(),
            linear(time_embed_dim, time_embed_dim),
        )

        if self.num_classes is not None:
            self.label_emb = nn.Embedding(num_classes, time_embed_dim)

        self.input_blocks = nn.ModuleList(
            [TimestepEmbedSequential(conv_nd(dims, in_channels, model_channels, 3, padding=1))]
        )
        self._feature_size = model_channels
        input_block_chans = [model_channels]
        ch = model_channels
        ds = 1
        for level, mult in enumerate(channel_mult):
            for _ in range(num_res_blocks):
                layers = [
                    ResBlock(
                        ch,
                        time_embed_dim,
                        dropout,
                        out_channels=mult * model_channels,
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = mult * model_channels
                if ds in attention_resolutions:
                    if num_head_channels == -1:
                        dim_head = ch // num_heads
                    else:
                        num_heads = ch // num_head_channels
                        dim_head = num_head_channels
                    if legacy:
                        # num_heads = 1
                        dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
                    layers.append(
                        AttentionBlock(
                            ch,
                            use_checkpoint=use_checkpoint,
                            num_heads=num_heads,
                            num_head_channels=dim_head,
                            use_new_attention_order=use_new_attention_order,
                        )
                        if not use_spatial_transformer
                        else SpatialTransformer(
                            ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
                        )
                    )
                self.input_blocks.append(TimestepEmbedSequential(*layers))
                self._feature_size += ch
                input_block_chans.append(ch)
            if level != len(channel_mult) - 1:
                out_ch = ch
                self.input_blocks.append(
                    TimestepEmbedSequential(
                        ResBlock(
                            ch,
                            time_embed_dim,
                            dropout,
                            out_channels=out_ch,
                            dims=dims,
                            use_checkpoint=use_checkpoint,
                            use_scale_shift_norm=use_scale_shift_norm,
                            down=True,
                        )
                        if resblock_updown
                        else Downsample(ch, conv_resample, dims=dims, out_channels=out_ch)
                    )
                )
                ch = out_ch
                input_block_chans.append(ch)
                ds *= 2
                self._feature_size += ch

        if num_head_channels == -1:
            dim_head = ch // num_heads
        else:
            num_heads = ch // num_head_channels
            dim_head = num_head_channels
        if legacy:
            # num_heads = 1
            dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
        self.middle_block = TimestepEmbedSequential(
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
            AttentionBlock(
                ch,
                use_checkpoint=use_checkpoint,
                num_heads=num_heads,
                num_head_channels=dim_head,
                use_new_attention_order=use_new_attention_order,
            )
            if not use_spatial_transformer
            else SpatialTransformer(ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim),
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
        )
        self._feature_size += ch

        self.output_blocks = nn.ModuleList([])
        for level, mult in list(enumerate(channel_mult))[::-1]:
            for i in range(num_res_blocks + 1):
                ich = input_block_chans.pop()
                layers = [
                    ResBlock(
                        ch + ich,
                        time_embed_dim,
                        dropout,
                        out_channels=model_channels * mult,
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = model_channels * mult
                if ds in attention_resolutions:
                    if num_head_channels == -1:
                        dim_head = ch // num_heads
                    else:
                        num_heads = ch // num_head_channels
                        dim_head = num_head_channels
                    if legacy:
                        # num_heads = 1
                        dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
                    layers.append(
                        AttentionBlock(
                            ch,
                            use_checkpoint=use_checkpoint,
                            num_heads=num_heads_upsample,
                            num_head_channels=dim_head,
                            use_new_attention_order=use_new_attention_order,
                        )
                        if not use_spatial_transformer
                        else SpatialTransformer(
                            ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
                        )
                    )
                if level and i == num_res_blocks:
                    out_ch = ch
                    layers.append(
                        ResBlock(
                            ch,
                            time_embed_dim,
                            dropout,
                            out_channels=out_ch,
                            dims=dims,
                            use_checkpoint=use_checkpoint,
                            use_scale_shift_norm=use_scale_shift_norm,
                            up=True,
                        )
                        if resblock_updown
                        else Upsample(ch, conv_resample, dims=dims, out_channels=out_ch)
                    )
                    ds //= 2
                self.output_blocks.append(TimestepEmbedSequential(*layers))
                self._feature_size += ch

        self.out = nn.Sequential(
            normalization(ch),
            nn.SiLU(),
            zero_module(conv_nd(dims, model_channels, out_channels, 3, padding=1)),
        )
        if self.predict_codebook_ids:
            self.id_predictor = nn.Sequential(
                normalization(ch),
                conv_nd(dims, model_channels, n_embed, 1),
                # nn.LogSoftmax(dim=1)  # change to cross_entropy and produce non-normalized logits
            )

    def convert_to_fp16(self):
        """
        Convert the torso of the model to float16.
        """
        self.input_blocks.apply(convert_module_to_f16)
        self.middle_block.apply(convert_module_to_f16)
        self.output_blocks.apply(convert_module_to_f16)

    def convert_to_fp32(self):
        """
        Convert the torso of the model to float32.
        """
        self.input_blocks.apply(convert_module_to_f32)
        self.middle_block.apply(convert_module_to_f32)
        self.output_blocks.apply(convert_module_to_f32)

    def forward(self, x, timesteps=None, context=None, y=None, **kwargs):
        """
        Apply the model to an input batch.
        :param x: an [N x C x ...] Tensor of inputs.
        :param timesteps: a 1-D batch of timesteps.
        :param context: conditioning plugged in via crossattn
        :param y: an [N] Tensor of labels, if class-conditional.
        :return: an [N x C x ...] Tensor of outputs.
        """
        assert (y is not None) == (
            self.num_classes is not None
        ), "must specify y if and only if the model is class-conditional"
        hs = []
        if not torch.is_tensor(timesteps):
            timesteps = torch.tensor([timesteps], dtype=torch.long, device=x.device)
        t_emb = get_timestep_embedding(timesteps, self.model_channels, flip_sin_to_cos=True, downscale_freq_shift=0)
        emb = self.time_embed(t_emb)

        if self.num_classes is not None:
            assert y.shape == (x.shape[0],)
            emb = emb + self.label_emb(y)

        h = x.type(self.dtype_)
        for module in self.input_blocks:
            h = module(h, emb, context)
            hs.append(h)
        h = self.middle_block(h, emb, context)
        for module in self.output_blocks:
            h = torch.cat([h, hs.pop()], dim=1)
            h = module(h, emb, context)
        h = h.type(x.dtype)
        if self.predict_codebook_ids:
            return self.id_predictor(h)
        else:
            return self.out(h)


class EncoderUNetModel(nn.Module):
    """
    The half UNet model with attention and timestep embedding.
    For usage, see UNet.
    """

    def __init__(
        self,
        image_size,
        in_channels,
        model_channels,
        out_channels,
        num_res_blocks,
        attention_resolutions,
        dropout=0,
        channel_mult=(1, 2, 4, 8),
        conv_resample=True,
        dims=2,
        use_checkpoint=False,
        use_fp16=False,
        num_heads=1,
        num_head_channels=-1,
        num_heads_upsample=-1,
        use_scale_shift_norm=False,
        resblock_updown=False,
        use_new_attention_order=False,
        pool="adaptive",
        *args,
        **kwargs,
    ):
        super().__init__()

        if num_heads_upsample == -1:
            num_heads_upsample = num_heads

        self.in_channels = in_channels
        self.model_channels = model_channels
        self.out_channels = out_channels
        self.num_res_blocks = num_res_blocks
        self.attention_resolutions = attention_resolutions
        self.dropout = dropout
        self.channel_mult = channel_mult
        self.conv_resample = conv_resample
        self.use_checkpoint = use_checkpoint
        self.dtype = torch.float16 if use_fp16 else torch.float32
        self.num_heads = num_heads
        self.num_head_channels = num_head_channels
        self.num_heads_upsample = num_heads_upsample

        time_embed_dim = model_channels * 4
        self.time_embed = nn.Sequential(
            linear(model_channels, time_embed_dim),
            nn.SiLU(),
            linear(time_embed_dim, time_embed_dim),
        )

        self.input_blocks = nn.ModuleList(
            [TimestepEmbedSequential(conv_nd(dims, in_channels, model_channels, 3, padding=1))]
        )
        self._feature_size = model_channels
        input_block_chans = [model_channels]
        ch = model_channels
        ds = 1
        for level, mult in enumerate(channel_mult):
            for _ in range(num_res_blocks):
                layers = [
                    ResBlock(
                        ch,
                        time_embed_dim,
                        dropout,
                        out_channels=mult * model_channels,
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = mult * model_channels
                if ds in attention_resolutions:
                    layers.append(
                        AttentionBlock(
                            ch,
                            use_checkpoint=use_checkpoint,
                            num_heads=num_heads,
                            num_head_channels=num_head_channels,
                            use_new_attention_order=use_new_attention_order,
                        )
                    )
                self.input_blocks.append(TimestepEmbedSequential(*layers))
                self._feature_size += ch
                input_block_chans.append(ch)
            if level != len(channel_mult) - 1:
                out_ch = ch
                self.input_blocks.append(
                    TimestepEmbedSequential(
                        ResBlock(
                            ch,
                            time_embed_dim,
                            dropout,
                            out_channels=out_ch,
                            dims=dims,
                            use_checkpoint=use_checkpoint,
                            use_scale_shift_norm=use_scale_shift_norm,
                            down=True,
                        )
                        if resblock_updown
                        else Downsample(ch, conv_resample, dims=dims, out_channels=out_ch)
                    )
                )
                ch = out_ch
                input_block_chans.append(ch)
                ds *= 2
                self._feature_size += ch

        self.middle_block = TimestepEmbedSequential(
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
            AttentionBlock(
                ch,
                use_checkpoint=use_checkpoint,
                num_heads=num_heads,
                num_head_channels=num_head_channels,
                use_new_attention_order=use_new_attention_order,
            ),
            ResBlock(
                ch,
                time_embed_dim,
                dropout,
                dims=dims,
                use_checkpoint=use_checkpoint,
                use_scale_shift_norm=use_scale_shift_norm,
            ),
        )
        self._feature_size += ch
        self.pool = pool
        if pool == "adaptive":
            self.out = nn.Sequential(
                normalization(ch),
                nn.SiLU(),
                nn.AdaptiveAvgPool2d((1, 1)),
                zero_module(conv_nd(dims, ch, out_channels, 1)),
                nn.Flatten(),
            )
        elif pool == "attention":
            assert num_head_channels != -1
            self.out = nn.Sequential(
                normalization(ch),
                nn.SiLU(),
                AttentionPool2d((image_size // ds), ch, num_head_channels, out_channels),
            )
        elif pool == "spatial":
            self.out = nn.Sequential(
                nn.Linear(self._feature_size, 2048),
                nn.ReLU(),
                nn.Linear(2048, self.out_channels),
            )
        elif pool == "spatial_v2":
            self.out = nn.Sequential(
                nn.Linear(self._feature_size, 2048),
                normalization(2048),
                nn.SiLU(),
                nn.Linear(2048, self.out_channels),
            )
        else:
            raise NotImplementedError(f"Unexpected {pool} pooling")

    def convert_to_fp16(self):
        """
        Convert the torso of the model to float16.
        """
        self.input_blocks.apply(convert_module_to_f16)
        self.middle_block.apply(convert_module_to_f16)

    def convert_to_fp32(self):
        """
        Convert the torso of the model to float32.
        """
        self.input_blocks.apply(convert_module_to_f32)
        self.middle_block.apply(convert_module_to_f32)

    def forward(self, x, timesteps):
        """
        Apply the model to an input batch.
        :param x: an [N x C x ...] Tensor of inputs.
        :param timesteps: a 1-D batch of timesteps.
        :return: an [N x K] Tensor of outputs.
        """
        emb = self.time_embed(
            get_timestep_embedding(timesteps, self.model_channels, flip_sin_to_cos=True, downscale_freq_shift=0)
        )

        results = []
        h = x.type(self.dtype)
        for module in self.input_blocks:
            h = module(h, emb)
            if self.pool.startswith("spatial"):
                results.append(h.type(x.dtype).mean(dim=(2, 3)))
        h = self.middle_block(h, emb)
        if self.pool.startswith("spatial"):
            results.append(h.type(x.dtype).mean(dim=(2, 3)))
            h = torch.cat(results, axis=-1)
            return self.out(h)
        else:
            h = h.type(x.dtype)
            return self.out(h)