# Borrowed from https://github.com/openai/guided-diffusion
from abc import abstractmethod

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


class GroupNorm32(nn.GroupNorm):
    def forward(self, x):
        return super().forward(x.float()).type(x.dtype)


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)


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 update_ema(target_params, source_params, rate=0.99):
    """
    Update target parameters to be closer to those of source parameters using
    an exponential moving average.

    :param target_params: the target parameter sequence.
    :param source_params: the source parameter sequence.
    :param rate: the EMA rate (closer to 1 means slower).
    """
    for targ, src in zip(target_params, source_params):
        targ.detach().mul_(rate).add_(src, alpha=1 - rate)


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 normalization(channels):
    """
    Make a standard normalization layer.

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


def timestep_embedding(timesteps, dim, max_period=10000):
    """
    Create sinusoidal timestep embeddings.

    :param timesteps: a 1-D Tensor of N indices, one per batch element.
                      These may be fractional.
    :param dim: the dimension of the output.
    :param max_period: controls the minimum frequency of the embeddings.
    :return: an [N x dim] Tensor of positional embeddings.
    """
    half = dim // 2
    freqs = th.exp(
        -math.log(max_period) * th.arange(start=0, end=half, dtype=th.float32) / half
    ).to(device=timesteps.device)
    args = timesteps[:, None].float() * freqs[None]
    embedding = th.cat([th.cos(args), th.sin(args)], dim=-1)
    if dim % 2:
        embedding = th.cat([embedding, th.zeros_like(embedding[:, :1])], dim=-1)
    return embedding


def checkpoint(func, inputs, params, flag):
    """
    Evaluate a function without caching intermediate activations, allowing for
    reduced memory at the expense of extra compute in the backward pass.

    :param func: the function to evaluate.
    :param inputs: the argument sequence to pass to `func`.
    :param params: a sequence of parameters `func` depends on but does not
                   explicitly take as arguments.
    :param flag: if False, disable gradient checkpointing.
    """
    if flag:
        args = tuple(inputs) + tuple(params)
        return CheckpointFunction.apply(func, len(inputs), *args)
    else:
        return func(*inputs)


class CheckpointFunction(th.autograd.Function):
    @staticmethod
    def forward(ctx, run_function, length, *args):
        ctx.run_function = run_function
        ctx.input_tensors = list(args[:length])
        ctx.input_params = list(args[length:])
        with th.no_grad():
            output_tensors = ctx.run_function(*ctx.input_tensors)
        return output_tensors

    @staticmethod
    def backward(ctx, *output_grads):
        ctx.input_tensors = [x.detach().requires_grad_(True) for x in ctx.input_tensors]
        with th.enable_grad():
            # Fixes a bug where the first op in run_function modifies the
            # Tensor storage in place, which is not allowed for detach()'d
            # Tensors.
            shallow_copies = [x.view_as(x) for x in ctx.input_tensors]
            output_tensors = ctx.run_function(*shallow_copies)
        input_grads = th.autograd.grad(
            output_tensors,
            ctx.input_tensors + ctx.input_params,
            output_grads,
            allow_unused=True,
        )
        del ctx.input_tensors
        del ctx.input_params
        del output_tensors
        return (None, None) + input_grads


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(
            th.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 = th.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):
        for layer in self:
            if isinstance(layer, TimestepBlock):
                x = layer(x, emb)
            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):
        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=1)

    def forward(self, x):
        assert x.shape[1] == self.channels
        if self.dims == 3:
            out = F.interpolate(
                x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
            )
        else:
            out = F.interpolate(x, scale_factor=2, mode="nearest")
        if x.shape[-1] == x.shape[-2] == 3:
            # upsampling layer transform [3x3] to [6x6]. Manually paddding it to make [7x7]
            out = F.pad(out, (1, 0, 1, 0))
        if self.use_conv:
            out = self.conv(out)
        return out


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):
        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=1
            )
        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):
        """
        Apply the block to a Tensor, conditioned on a timestep embedding.
        :param x: an [N x C x ...] Tensor of features.
        :param emb: an [N x emb_channels] Tensor of timestep embeddings.
        :return: an [N x C x ...] Tensor of outputs.
        """
        return checkpoint(
            self._forward, (x, emb), self.parameters(), self.use_checkpoint
        )

    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 = th.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)
        if use_new_attention_order:
            # split qkv before split heads
            self.attention = QKVAttention(self.num_heads)
        else:
            # 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):
        return checkpoint(self._forward, (x,), self.parameters(), True)

    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)


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 += th.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 = th.einsum(
            "bct,bcs->bts", q * scale, k * scale
        )  # More stable with f16 than dividing afterwards
        weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
        a = th.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 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 = th.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 = th.softmax(weight.float(), dim=-1).type(weight.dtype)
        a = th.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)


class UNetModel(nn.Module):
    """
    The full UNet model with attention and timestep embedding.
    :param in_channels: channels in the input Tensor.
    :param emb_dim: base dimension of timestep embedding.
    :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,
        time_emb_factor=4,
        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,
    ):
        super().__init__()

        if num_heads_upsample == -1:
            num_heads_upsample = num_heads

        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 = th.float16 if use_fp16 else th.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 * time_emb_factor
        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)

        ch = input_ch = int(channel_mult[0] * model_channels)
        self.input_blocks = nn.ModuleList(
            [TimestepEmbedSequential(conv_nd(dims, in_channels, ch, 3, padding=1))]
        )
        self._feature_size = ch
        input_block_chans = [ch]
        ds = 1
        for level, mult in enumerate(channel_mult):
            for _ in range(num_res_blocks):
                layers = [
                    ResBlock(
                        ch,
                        time_embed_dim,
                        dropout,
                        out_channels=int(mult * model_channels),
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = int(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.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=int(model_channels * mult),
                        dims=dims,
                        use_checkpoint=use_checkpoint,
                        use_scale_shift_norm=use_scale_shift_norm,
                    )
                ]
                ch = int(model_channels * mult)
                if ds in attention_resolutions:
                    layers.append(
                        AttentionBlock(
                            ch,
                            use_checkpoint=use_checkpoint,
                            num_heads=num_heads_upsample,
                            num_head_channels=num_head_channels,
                            use_new_attention_order=use_new_attention_order,
                        )
                    )
                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, input_ch, out_channels, 3, padding=1)),
        )

    def forward(self, model_input, timesteps, y=None):
        """
        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 y: an [N] Tensor of labels, if class-conditional.
        :return: an [N x C x ...] Tensor of outputs.
        """

        x = model_input["noised_rgb"]

        assert (y is not None) == (
            self.num_classes is not None
        ), "must specify y if and only if the model is class-conditional"

        hs = []
        emb = self.time_embed(timestep_embedding(timesteps, self.model_channels))
        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)
            hs.append(h)
        h = self.middle_block(h, emb)
        for module in self.output_blocks:
            h = th.cat([h, hs.pop()], dim=1)
            h = module(h, emb)
        h = h.type(x.dtype)
        out = self.out(h)

        # format (todo factorize)
        return {
                "eps": out[:,[0,1,2]],
                "rgb": out[:,[3,4,5]].tanh(),
                "alpha": out[:,[6]],
                "shape_type": out[:,[7]],
                "shape_nocs": out[:,[8,9]],
                "undistorted_rgb": out[:,[10,11,12]].tanh(),
                "undistorted_alpha": out[:,[13]],
                "undistorted_shape_type": out[:,[14]],
                "undistorted_shape_nocs": out[:,[15,16]],
        }


def UNetBig(
    image_size,
    in_channels=3,
    out_channels=3,
    base_width=192,
    num_classes=None,
):
    if image_size == 128:
        channel_mult = (1, 1, 2, 3, 4)
    elif image_size == 64:
        channel_mult = (1, 2, 3, 4)
    elif image_size == 32:
        channel_mult = (1, 2, 2, 2)
    elif image_size == 28:
        channel_mult = (1, 2, 2, 2)
    else:
        raise ValueError(f"unsupported image size: {image_size}")

    attention_ds = []
    if image_size == 28:
        attention_resolutions = "28,14,7"
    else:
        attention_resolutions = "32,16,8"
    for res in attention_resolutions.split(","):
        attention_ds.append(image_size // int(res))

    return UNetModel(
        image_size=image_size,
        in_channels=in_channels,
        out_channels=out_channels,
        num_res_blocks=3,
        model_channels=base_width,
        attention_resolutions=tuple(attention_ds),
        dropout=0.1,
        channel_mult=channel_mult,
        num_classes=num_classes,
        use_checkpoint=False,
        use_fp16=False,
        num_heads=4,
        num_head_channels=64,
        num_heads_upsample=-1,
        use_scale_shift_norm=True,
        resblock_updown=True,
        use_new_attention_order=True,
    )


def UNet(
    image_size,
    in_channels=3,
    out_channels=3,
    base_width=64,
    num_classes=None,
):
    if image_size == 128:
        channel_mult = (1, 1, 2, 3, 4)
    elif image_size == 64:
        channel_mult = (1, 2, 3, 4)
    elif image_size == 32:
        channel_mult = (1, 2, 2, 2)
    elif image_size == 28:
        channel_mult = (1, 2, 2, 2)
    else:
        raise ValueError(f"unsupported image size: {image_size}")

    attention_ds = []
    if image_size == 28:
        attention_resolutions = "28,14,7"
    else:
        attention_resolutions = "32,16,8"
    for res in attention_resolutions.split(","):
        attention_ds.append(image_size // int(res))

    return UNetModel(
        image_size=image_size,
        in_channels=in_channels,
        model_channels=base_width,
        out_channels=out_channels,
        num_res_blocks=3,
        attention_resolutions=tuple(attention_ds),
        dropout=0.1,
        channel_mult=channel_mult,
        num_classes=num_classes,
        use_checkpoint=False,
        use_fp16=False,
        num_heads=4,
        num_head_channels=64,
        num_heads_upsample=-1,
        use_scale_shift_norm=True,
        resblock_updown=True,
        use_new_attention_order=True,
    )


def UNetSmall(
    image_size,
    in_channels=3,
    out_channels=3,
    base_width=32,
    num_classes=None,
):
    if image_size == 128:
        channel_mult = (1, 1, 2, 3, 4)
    elif image_size == 64:
        channel_mult = (1, 2, 3, 4)
    elif image_size == 32:
        channel_mult = (1, 2, 2, 2)
    elif image_size == 28:
        channel_mult = (1, 2, 2, 2)
    else:
        raise ValueError(f"unsupported image size: {image_size}")

    attention_ds = []
    if image_size == 28:
        attention_resolutions = "28,14,7"
    else:
        attention_resolutions = "32,16,8"
    for res in attention_resolutions.split(","):
        attention_ds.append(image_size // int(res))

    return UNetModel(
        image_size=image_size,
        in_channels=in_channels,
        model_channels=base_width,
        out_channels=out_channels,
        num_res_blocks=2,
        attention_resolutions=tuple(attention_ds),
        time_emb_factor=2,
        dropout=0.1,
        channel_mult=channel_mult,
        num_classes=num_classes,
        use_checkpoint=False,
        use_fp16=False,
        num_heads=4,
        num_head_channels=32,
        num_heads_upsample=-1,
        use_scale_shift_norm=True,
        resblock_updown=True,
        use_new_attention_order=True,
    )