ldm/modules/diffusionmodules/model.py

# pytorch_diffusion + derived encoder decoder
import math
import torch
import torch.nn as nn
import torchvision
from torch.nn.modules.utils import _pair, _single
import numpy as np
from einops import rearrange
from typing import Optional, Any

from ldm.modules.attention import MemoryEfficientCrossAttention

try:
    import xformers
    import xformers.ops
    XFORMERS_IS_AVAILBLE = True
except:
    XFORMERS_IS_AVAILBLE = False
    print("No module 'xformers'. Proceeding without it.")


def get_timestep_embedding(timesteps, embedding_dim):
    """
    This matches the implementation in Denoising Diffusion Probabilistic Models:
    From Fairseq.
    Build sinusoidal embeddings.
    This matches the implementation in tensor2tensor, but differs slightly
    from the description in Section 3.5 of "Attention Is All You Need".
    """
    assert len(timesteps.shape) == 1

    half_dim = embedding_dim // 2
    emb = math.log(10000) / (half_dim - 1)
    emb = torch.exp(torch.arange(half_dim, dtype=torch.float32) * -emb)
    emb = emb.to(device=timesteps.device)
    emb = timesteps.float()[:, None] * emb[None, :]
    emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
    if embedding_dim % 2 == 1:  # zero pad
        emb = torch.nn.functional.pad(emb, (0,1,0,0))
    return emb


def nonlinearity(x):
    # swish
    return x*torch.sigmoid(x)


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


class Upsample(nn.Module):
    def __init__(self, in_channels, with_conv):
        super().__init__()
        self.with_conv = with_conv
        if self.with_conv:
            self.conv = torch.nn.Conv2d(in_channels,
                                        in_channels,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)

    def forward(self, x):
        x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
        if self.with_conv:
            x = self.conv(x)
        return x


class Downsample(nn.Module):
    def __init__(self, in_channels, with_conv):
        super().__init__()
        self.with_conv = with_conv
        if self.with_conv:
            # no asymmetric padding in torch conv, must do it ourselves
            self.conv = torch.nn.Conv2d(in_channels,
                                        in_channels,
                                        kernel_size=3,
                                        stride=2,
                                        padding=0)

    def forward(self, x):
        if self.with_conv:
            pad = (0,1,0,1)
            x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
            x = self.conv(x)
        else:
            x = torch.nn.functional.avg_pool2d(x, kernel_size=2, stride=2)
        return x


class ResnetBlock(nn.Module):
    def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
                 dropout, temb_channels=512):
        super().__init__()
        self.in_channels = in_channels
        out_channels = in_channels if out_channels is None else out_channels
        self.out_channels = out_channels
        self.use_conv_shortcut = conv_shortcut

        self.norm1 = Normalize(in_channels)
        self.conv1 = torch.nn.Conv2d(in_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        if temb_channels > 0:
            self.temb_proj = torch.nn.Linear(temb_channels,
                                             out_channels)
        self.norm2 = Normalize(out_channels)
        self.dropout = torch.nn.Dropout(dropout)
        self.conv2 = torch.nn.Conv2d(out_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        
        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                self.conv_shortcut = torch.nn.Conv2d(in_channels,
                                                     out_channels,
                                                     kernel_size=3,
                                                     stride=1,
                                                     padding=1)
            else:
                self.nin_shortcut = torch.nn.Conv2d(in_channels,
                                                    out_channels,
                                                    kernel_size=1,
                                                    stride=1,
                                                    padding=0)

    def forward(self, x, temb):
        h = x
        h = self.norm1(h)
        h = nonlinearity(h)
        h = self.conv1(h)

        if temb is not None:
            h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]

        h = self.norm2(h)
        h = nonlinearity(h)
        h = self.dropout(h)
        h = self.conv2(h)

        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                x = self.conv_shortcut(x)
            else:
                x = self.nin_shortcut(x)

        return x+h

class ResnetBlock_dcn(nn.Module):
    def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
                 dropout, temb_channels=512):
        super().__init__()
        self.in_channels = in_channels
        out_channels = in_channels if out_channels is None else out_channels
        self.out_channels = out_channels
        self.use_conv_shortcut = conv_shortcut

        self.norm1 = Normalize(in_channels)
        self.conv1 = torch.nn.Conv2d(in_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        self.dcn1 = ModulatedDeformConvPack(out_channels,
                                       out_channels,
                                       kernel_size=3,
                                       stride=1,
                                       padding=1)
        if temb_channels > 0:
            self.temb_proj = torch.nn.Linear(temb_channels,
                                             out_channels)
        self.norm2 = Normalize(out_channels)
        self.dropout = torch.nn.Dropout(dropout)
        self.conv2 = torch.nn.Conv2d(out_channels,
                                     out_channels,
                                     kernel_size=3,
                                     stride=1,
                                     padding=1)
        self.dcn2 = ModulatedDeformConvPack(out_channels,
                                       out_channels,
                                       kernel_size=3,
                                       stride=1,
                                       padding=1)
        
        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                self.conv_shortcut = torch.nn.Conv2d(in_channels,
                                                     out_channels,
                                                     kernel_size=3,
                                                     stride=1,
                                                     padding=1)
            else:
                self.nin_shortcut = torch.nn.Conv2d(in_channels,
                                                    out_channels,
                                                    kernel_size=1,
                                                    stride=1,
                                                    padding=0)

    def forward(self, x,grayx, temb):
        h = x
        h = self.norm1(h)
        h = nonlinearity(h)
        h = self.conv1(h)
        h = self.dcn1(h,grayx)+h

        if temb is not None:
            h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]

        h = self.norm2(h)
        h = nonlinearity(h)
        h = self.dropout(h)
        h = self.conv2(h)
        h = self.dcn2(h,grayx)+h

        if self.in_channels != self.out_channels:
            if self.use_conv_shortcut:
                x = self.conv_shortcut(x)
            else:
                x = self.nin_shortcut(x)

        return x+h
    

class AttnBlock(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 = q.reshape(b,c,h*w)
        q = q.permute(0,2,1)   # b,hw,c
        k = k.reshape(b,c,h*w) # b,c,hw
        w_ = torch.bmm(q,k)     # b,hw,hw    w[b,i,j]=sum_c q[b,i,c]k[b,c,j]
        w_ = w_ * (int(c)**(-0.5))
        w_ = torch.nn.functional.softmax(w_, dim=2)

        # attend to values
        v = v.reshape(b,c,h*w)
        w_ = w_.permute(0,2,1)   # b,hw,hw (first hw of k, second of q)
        h_ = torch.bmm(v,w_)     # b, c,hw (hw of q) h_[b,c,j] = sum_i v[b,c,i] w_[b,i,j]
        h_ = h_.reshape(b,c,h,w)

        h_ = self.proj_out(h_)

        return x+h_

class MemoryEfficientAttnBlock(nn.Module):
    """
        Uses xformers efficient implementation,
        see https://github.com/MatthieuTPHR/diffusers/blob/d80b531ff8060ec1ea982b65a1b8df70f73aa67c/src/diffusers/models/attention.py#L223
        Note: this is a single-head self-attention operation
    """
    #
    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)
        self.attention_op: Optional[Any] = None

    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, k, v = map(lambda x: rearrange(x, 'b c h w -> b (h w) c'), (q, k, v))

        q, k, v = map(
            lambda t: t.unsqueeze(3)
            .reshape(B, t.shape[1], 1, C)
            .permute(0, 2, 1, 3)
            .reshape(B * 1, t.shape[1], C)
            .contiguous(),
            (q, k, v),
        )
        out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op)

        out = (
            out.unsqueeze(0)
            .reshape(B, 1, out.shape[1], C)
            .permute(0, 2, 1, 3)
            .reshape(B, out.shape[1], C)
        )
        out = rearrange(out, 'b (h w) c -> b c h w', b=B, h=H, w=W, c=C)
        out = self.proj_out(out)
        return x+out


class MemoryEfficientCrossAttentionWrapper(MemoryEfficientCrossAttention):
    def forward(self, x, context=None, mask=None):
        b, c, h, w = x.shape
        x = rearrange(x, 'b c h w -> b (h w) c')
        out = super().forward(x, context=context, mask=mask)
        out = rearrange(out, 'b (h w) c -> b c h w', h=h, w=w, c=c)
        return x + out


def make_attn(in_channels, attn_type="vanilla", attn_kwargs=None):
    assert attn_type in ["vanilla", "vanilla-xformers", "memory-efficient-cross-attn", "linear", "none"], f'attn_type {attn_type} unknown'
    if XFORMERS_IS_AVAILBLE and attn_type == "vanilla":
        attn_type = "vanilla-xformers"
    print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
    if attn_type == "vanilla":
        assert attn_kwargs is None
        return AttnBlock(in_channels)
    elif attn_type == "vanilla-xformers":
        print(f"building MemoryEfficientAttnBlock with {in_channels} in_channels...")
        return MemoryEfficientAttnBlock(in_channels)
    elif type == "memory-efficient-cross-attn":
        attn_kwargs["query_dim"] = in_channels
        return MemoryEfficientCrossAttentionWrapper(**attn_kwargs)
    elif attn_type == "none":
        return nn.Identity(in_channels)
    else:
        raise NotImplementedError()


class Model(nn.Module):
    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
                 resolution, use_timestep=True, use_linear_attn=False, attn_type="vanilla"):
        super().__init__()
        if use_linear_attn: attn_type = "linear"
        self.ch = ch
        self.temb_ch = self.ch*4
        self.num_resolutions = len(ch_mult)
        self.num_res_blocks = num_res_blocks
        self.resolution = resolution
        self.in_channels = in_channels

        self.use_timestep = use_timestep
        if self.use_timestep:
            # timestep embedding
            self.temb = nn.Module()
            self.temb.dense = nn.ModuleList([
                torch.nn.Linear(self.ch,
                                self.temb_ch),
                torch.nn.Linear(self.temb_ch,
                                self.temb_ch),
            ])

        # 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(make_attn(block_in, attn_type=attn_type))
            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
        self.mid = nn.Module()
        self.mid.block_1 = ResnetBlock(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)
        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
        self.mid.block_2 = ResnetBlock(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)

        # 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]
            skip_in = ch*ch_mult[i_level]
            for i_block in range(self.num_res_blocks+1):
                if i_block == self.num_res_blocks:
                    skip_in = ch*in_ch_mult[i_level]
                block.append(ResnetBlock(in_channels=block_in+skip_in,
                                         out_channels=block_out,
                                         temb_channels=self.temb_ch,
                                         dropout=dropout))
                block_in = block_out
                if curr_res in attn_resolutions:
                    attn.append(make_attn(block_in, attn_type=attn_type))
            up = nn.Module()
            up.block = block
            up.attn = attn
            if i_level != 0:
                up.upsample = Upsample(block_in, resamp_with_conv)
                curr_res = curr_res * 2
            self.up.insert(0, up) # prepend to get consistent order

        # end
        self.norm_out = Normalize(block_in)
        self.conv_out = torch.nn.Conv2d(block_in,
                                        out_ch,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)

    def forward(self, x, t=None, context=None):
        #assert x.shape[2] == x.shape[3] == self.resolution
        if context is not None:
            # assume aligned context, cat along channel axis
            x = torch.cat((x, context), dim=1)
        if self.use_timestep:
            # timestep embedding
            assert t is not None
            temb = get_timestep_embedding(t, self.ch)
            temb = self.temb.dense[0](temb)
            temb = nonlinearity(temb)
            temb = self.temb.dense[1](temb)
        else:
            temb = None

        # downsampling
        hs = [self.conv_in(x)]
        for i_level in range(self.num_resolutions):
            for i_block in range(self.num_res_blocks):
                h = self.down[i_level].block[i_block](hs[-1], temb)
                if len(self.down[i_level].attn) > 0:
                    h = self.down[i_level].attn[i_block](h)
                hs.append(h)
            if i_level != self.num_resolutions-1:
                hs.append(self.down[i_level].downsample(hs[-1]))

        # middle
        h = hs[-1]
        h = self.mid.block_1(h, temb)
        h = self.mid.attn_1(h)
        h = self.mid.block_2(h, temb)

        # upsampling
        for i_level in reversed(range(self.num_resolutions)):
            for i_block in range(self.num_res_blocks+1):
                h = self.up[i_level].block[i_block](
                    torch.cat([h, hs.pop()], dim=1), temb)
                if len(self.up[i_level].attn) > 0:
                    h = self.up[i_level].attn[i_block](h)
            if i_level != 0:
                h = self.up[i_level].upsample(h)

        # end
        h = self.norm_out(h)
        h = nonlinearity(h)
        h = self.conv_out(h)
        return h

    def get_last_layer(self):
        return self.conv_out.weight


class Encoder(nn.Module):
    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
                 resolution, z_channels, double_z=True, use_linear_attn=False, attn_type="vanilla",
                 **ignore_kwargs):
        super().__init__()
        if use_linear_attn: attn_type = "linear"
        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.in_ch_mult = in_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(make_attn(block_in, attn_type=attn_type))
            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
        self.mid = nn.Module()
        self.mid.block_1 = ResnetBlock(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)
        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
        self.mid.block_2 = ResnetBlock(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)

        # end
        self.norm_out = Normalize(block_in)
        self.conv_out = torch.nn.Conv2d(block_in,
                                        2*z_channels if double_z else z_channels,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)

    def forward(self, x):
        # timestep embedding
        temb = None

        # downsampling
        hs = [self.conv_in(x)]
        for i_level in range(self.num_resolutions):
            for i_block in range(self.num_res_blocks):
                h = self.down[i_level].block[i_block](hs[-1], temb)
                if len(self.down[i_level].attn) > 0:
                    h = self.down[i_level].attn[i_block](h)
                hs.append(h)
            if i_level != self.num_resolutions-1:
                hs.append(self.down[i_level].downsample(hs[-1]))

        # middle
        h = hs[-1]
        h = self.mid.block_1(h, temb)
        h = self.mid.attn_1(h)
        h = self.mid.block_2(h, temb)

        # end
        h = self.norm_out(h)
        h = nonlinearity(h)
        h = self.conv_out(h)
        return h

class ModulatedDeformConv(nn.Module):
    
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 stride=1,
                 padding=0,
                 dilation=1,
                 groups=1,
                 deformable_groups=1,
                 bias=True):
        super(ModulatedDeformConv, self).__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = _pair(kernel_size)
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.groups = groups
        self.deformable_groups = deformable_groups
        self.with_bias = bias
        # enable compatibility with nn.Conv2d
        self.transposed = False
        self.output_padding = _single(0)

        self.weight = nn.Parameter(torch.Tensor(out_channels, in_channels // groups, *self.kernel_size))
        if bias:
            self.bias = nn.Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.init_weights()

    def init_weights(self):
        n = self.in_channels
        for k in self.kernel_size:
            n *= k
        stdv = 1. / math.sqrt(n)
        self.weight.data.uniform_(-stdv, stdv)
        if self.bias is not None:
            self.bias.data.zero_()

    # def forward(self, x, offset, mask):
    #     return torchvision.ops.con(x, offset, mask, self.weight, self.bias, self.stride, self.padding, self.dilation,
    #                                  self.groups, self.deformable_groups)


class ModulatedDeformConvPack(ModulatedDeformConv):
    """A ModulatedDeformable Conv Encapsulation that acts as normal Conv layers.

    Args:
        in_channels (int): Same as nn.Conv2d.
        out_channels (int): Same as nn.Conv2d.
        kernel_size (int or tuple[int]): Same as nn.Conv2d.
        stride (int or tuple[int]): Same as nn.Conv2d.
        padding (int or tuple[int]): Same as nn.Conv2d.
        dilation (int or tuple[int]): Same as nn.Conv2d.
        groups (int): Same as nn.Conv2d.
        bias (bool or str): If specified as `auto`, it will be decided by the
            norm_cfg. Bias will be set as True if norm_cfg is None, otherwise
            False.
    """

    _version = 2

    def __init__(self, *args, **kwargs):
        super(ModulatedDeformConvPack, self).__init__(*args, **kwargs)

        self.conv_offset = nn.Conv2d(
            self.in_channels+4,
            self.deformable_groups * 3 * self.kernel_size[0] * self.kernel_size[1],
            kernel_size=self.kernel_size,
            stride=_pair(self.stride),
            padding=_pair(self.padding),
            dilation=_pair(self.dilation),
            bias=True)
        self.init_weights()

    def init_weights(self):
        super(ModulatedDeformConvPack, self).init_weights()
        if hasattr(self, 'conv_offset'):
            self.conv_offset.weight.data.zero_()
            self.conv_offset.bias.data.zero_()

    def forward(self, x, gray_content):
        out = self.conv_offset(torch.cat((x,gray_content),dim=1))
        o1, o2, mask = torch.chunk(out, 3, dim=1)
        offset = torch.cat((o1, o2), dim=1)
        mask = torch.sigmoid(mask)
        
        # return modulated_deform_conv(x, offset, mask, self.weight, self.bias, self.stride, self.padding, self.dilation,
        #                              self.groups, self.deformable_groups)
        return torchvision.ops.deform_conv2d(x, offset, self.weight, self.bias, self.stride, self.padding,
                                             self.dilation, mask)


# class SecondOrderDeformableAlignment(ModulatedDeformConvPack):
#     """Second-order deformable alignment module.

#     Args:
#         in_channels (int): Same as nn.Conv2d.
#         out_channels (int): Same as nn.Conv2d.
#         kernel_size (int or tuple[int]): Same as nn.Conv2d.
#         stride (int or tuple[int]): Same as nn.Conv2d.
#         padding (int or tuple[int]): Same as nn.Conv2d.
#         dilation (int or tuple[int]): Same as nn.Conv2d.
#         groups (int): Same as nn.Conv2d.
#         bias (bool or str): If specified as `auto`, it will be decided by the
#             norm_cfg. Bias will be set as True if norm_cfg is None, otherwise
#             False.
#         max_residue_magnitude (int): The maximum magnitude of the offset
#             residue (Eq. 6 in paper). Default: 10.
#     """

#     def __init__(self, *args, **kwargs):
#         self.max_residue_magnitude = kwargs.pop('max_residue_magnitude', 10)

#         super(SecondOrderDeformableAlignment, self).__init__(*args, **kwargs)

#         self.conv_offset = nn.Sequential(
#             nn.Conv2d(3 * self.out_channels + 4, self.out_channels, 3, 1, 1),
#             nn.LeakyReLU(negative_slope=0.1, inplace=True),
#             nn.Conv2d(self.out_channels, self.out_channels, 3, 1, 1),
#             nn.LeakyReLU(negative_slope=0.1, inplace=True),
#             nn.Conv2d(self.out_channels, self.out_channels, 3, 1, 1),
#             nn.LeakyReLU(negative_slope=0.1, inplace=True),
#             nn.Conv2d(self.out_channels, 27 * self.deformable_groups, 3, 1, 1),
#         )

#         self.init_offset()

#     def init_offset(self):

#         def _constant_init(module, val, bias=0):
#             if hasattr(module, 'weight') and module.weight is not None:
#                 nn.init.constant_(module.weight, val)
#             if hasattr(module, 'bias') and module.bias is not None:
#                 nn.init.constant_(module.bias, bias)

#         _constant_init(self.conv_offset[-1], val=0, bias=0)

#     def forward(self, x, extra_feat, flow_1, flow_2):
#         extra_feat = torch.cat([extra_feat, flow_1, flow_2], dim=1)
#         out = self.conv_offset(extra_feat)
#         o1, o2, mask = torch.chunk(out, 3, dim=1)

#         # offset
#         offset = self.max_residue_magnitude * torch.tanh(torch.cat((o1, o2), dim=1))
#         offset_1, offset_2 = torch.chunk(offset, 2, dim=1)
#         offset_1 = offset_1 + flow_1.flip(1).repeat(1, offset_1.size(1) // 2, 1, 1)
#         offset_2 = offset_2 + flow_2.flip(1).repeat(1, offset_2.size(1) // 2, 1, 1)
#         offset = torch.cat([offset_1, offset_2], dim=1)

#         # mask
#         mask = torch.sigmoid(mask)

#         return torchvision.ops.deform_conv2d(x, offset, self.weight, self.bias, self.stride, self.padding,
#                                              self.dilation, mask)
                
class Decoder(nn.Module):
    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
                 resolution, z_channels, give_pre_end=False, tanh_out=False, use_linear_attn=False,
                 attn_type="vanilla", **ignorekwargs):
        super().__init__()
        if use_linear_attn: attn_type = "linear"
        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
        self.give_pre_end = give_pre_end
        self.tanh_out = tanh_out

        # compute in_ch_mult, block_in and curr_res at lowest res
        in_ch_mult = (1,)+tuple(ch_mult)
        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)
        print("Working with z of shape {} = {} dimensions.".format(
            self.z_shape, np.prod(self.z_shape)))

        # z to block_in
        self.conv_in = torch.nn.Conv2d(z_channels,
                                       block_in,
                                       kernel_size=3,
                                       stride=1,
                                       padding=1)
        
        self.dcn_in = ModulatedDeformConvPack(block_in,
                                       block_in,
                                       kernel_size=3,
                                       stride=1,
                                       padding=1)
        # middle
        self.mid = nn.Module()
        self.mid.block_1 = ResnetBlock_dcn(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)
        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
        self.mid.block_2 = ResnetBlock_dcn(in_channels=block_in,
                                       out_channels=block_in,
                                       temb_channels=self.temb_ch,
                                       dropout=dropout)

        # 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 i_block in range(self.num_res_blocks+1):
                block.append(ResnetBlock(in_channels=block_in,
                                         out_channels=block_out,
                                         temb_channels=self.temb_ch,
                                         dropout=dropout))
                # else:
                #     block.append(ResnetBlock_dcn(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(make_attn(block_in, attn_type=attn_type))
            up = nn.Module()
            up.block = block
            up.attn = attn
            if i_level != 0:
                up.upsample = Upsample(block_in, resamp_with_conv)
                curr_res = curr_res * 2
            self.up.insert(0, up) # prepend to get consistent order

        # end
        self.norm_out = Normalize(block_in)
        self.conv_out = torch.nn.Conv2d(block_in,
                                        out_ch,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)
        # self.dcn_out = ModulatedDeformConvPack(out_ch,
        #                                out_ch,
        #                                kernel_size=3,
        #                                stride=1,
        #                                padding=1)

    def forward(self, z, gray_content_z):
        #assert z.shape[1:] == self.z_shape[1:]
        self.last_z_shape = z.shape

        # timestep embedding
        temb = None

        # z to block_in
        h = self.conv_in(z)
        # print("h",h.shape)
        # print("gray_content_z",gray_content_z.shape)
        h = self.dcn_in(h, gray_content_z)+h

        # middle
        h = self.mid.block_1(h, gray_content_z,temb)
        h = self.mid.attn_1(h)
        h = self.mid.block_2(h, gray_content_z,temb)

        # upsampling
        for i_level in reversed(range(self.num_resolutions)):
            for i_block in range(self.num_res_blocks+1):
                h = self.up[i_level].block[i_block](h, temb)#h, gray_content_z,temb
                if len(self.up[i_level].attn) > 0:
                    h = self.up[i_level].attn[i_block](h)
            if i_level != 0:
                h = self.up[i_level].upsample(h)

        # end
        if self.give_pre_end:
            return h

        h = self.norm_out(h)
        h = nonlinearity(h)
        h = self.conv_out(h)
        # print(h.shape)
        # h = self.dcn_out(h,gray_content_z)
        if self.tanh_out:
            h = torch.tanh(h)
        return h


class SimpleDecoder(nn.Module):
    def __init__(self, in_channels, out_channels, *args, **kwargs):
        super().__init__()
        self.model = nn.ModuleList([nn.Conv2d(in_channels, in_channels, 1),
                                     ResnetBlock(in_channels=in_channels,
                                                 out_channels=2 * in_channels,
                                                 temb_channels=0, dropout=0.0),
                                     ResnetBlock(in_channels=2 * in_channels,
                                                out_channels=4 * in_channels,
                                                temb_channels=0, dropout=0.0),
                                     ResnetBlock(in_channels=4 * in_channels,
                                                out_channels=2 * in_channels,
                                                temb_channels=0, dropout=0.0),
                                     nn.Conv2d(2*in_channels, in_channels, 1),
                                     Upsample(in_channels, with_conv=True)])
        # end
        self.norm_out = Normalize(in_channels)
        self.conv_out = torch.nn.Conv2d(in_channels,
                                        out_channels,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)

    def forward(self, x):
        for i, layer in enumerate(self.model):
            if i in [1,2,3]:
                x = layer(x, None)
            else:
                x = layer(x)

        h = self.norm_out(x)
        h = nonlinearity(h)
        x = self.conv_out(h)
        return x


class UpsampleDecoder(nn.Module):
    def __init__(self, in_channels, out_channels, ch, num_res_blocks, resolution,
                 ch_mult=(2,2), dropout=0.0):
        super().__init__()
        # upsampling
        self.temb_ch = 0
        self.num_resolutions = len(ch_mult)
        self.num_res_blocks = num_res_blocks
        block_in = in_channels
        curr_res = resolution // 2 ** (self.num_resolutions - 1)
        self.res_blocks = nn.ModuleList()
        self.upsample_blocks = nn.ModuleList()
        for i_level in range(self.num_resolutions):
            res_block = []
            block_out = ch * ch_mult[i_level]
            for i_block in range(self.num_res_blocks + 1):
                res_block.append(ResnetBlock(in_channels=block_in,
                                         out_channels=block_out,
                                         temb_channels=self.temb_ch,
                                         dropout=dropout))
                block_in = block_out
            self.res_blocks.append(nn.ModuleList(res_block))
            if i_level != self.num_resolutions - 1:
                self.upsample_blocks.append(Upsample(block_in, True))
                curr_res = curr_res * 2

        # end
        self.norm_out = Normalize(block_in)
        self.conv_out = torch.nn.Conv2d(block_in,
                                        out_channels,
                                        kernel_size=3,
                                        stride=1,
                                        padding=1)

    def forward(self, x):
        # upsampling
        h = x
        for k, i_level in enumerate(range(self.num_resolutions)):
            for i_block in range(self.num_res_blocks + 1):
                h = self.res_blocks[i_level][i_block](h, None)
            if i_level != self.num_resolutions - 1:
                h = self.upsample_blocks[k](h)
        h = self.norm_out(h)
        h = nonlinearity(h)
        h = self.conv_out(h)
        return h


class LatentRescaler(nn.Module):
    def __init__(self, factor, in_channels, mid_channels, out_channels, depth=2):
        super().__init__()
        # residual block, interpolate, residual block
        self.factor = factor
        self.conv_in = nn.Conv2d(in_channels,
                                 mid_channels,
                                 kernel_size=3,
                                 stride=1,
                                 padding=1)
        self.res_block1 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
                                                     out_channels=mid_channels,
                                                     temb_channels=0,
                                                     dropout=0.0) for _ in range(depth)])
        self.attn = AttnBlock(mid_channels)
        self.res_block2 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
                                                     out_channels=mid_channels,
                                                     temb_channels=0,
                                                     dropout=0.0) for _ in range(depth)])

        self.conv_out = nn.Conv2d(mid_channels,
                                  out_channels,
                                  kernel_size=1,
                                  )

    def forward(self, x):
        x = self.conv_in(x)
        for block in self.res_block1:
            x = block(x, None)
        x = torch.nn.functional.interpolate(x, size=(int(round(x.shape[2]*self.factor)), int(round(x.shape[3]*self.factor))))
        x = self.attn(x)
        for block in self.res_block2:
            x = block(x, None)
        x = self.conv_out(x)
        return x


class MergedRescaleEncoder(nn.Module):
    def __init__(self, in_channels, ch, resolution, out_ch, num_res_blocks,
                 attn_resolutions, dropout=0.0, resamp_with_conv=True,
                 ch_mult=(1,2,4,8), rescale_factor=1.0, rescale_module_depth=1):
        super().__init__()
        intermediate_chn = ch * ch_mult[-1]
        self.encoder = Encoder(in_channels=in_channels, num_res_blocks=num_res_blocks, ch=ch, ch_mult=ch_mult,
                               z_channels=intermediate_chn, double_z=False, resolution=resolution,
                               attn_resolutions=attn_resolutions, dropout=dropout, resamp_with_conv=resamp_with_conv,
                               out_ch=None)
        self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=intermediate_chn,
                                       mid_channels=intermediate_chn, out_channels=out_ch, depth=rescale_module_depth)

    def forward(self, x):
        x = self.encoder(x)
        x = self.rescaler(x)
        return x


class MergedRescaleDecoder(nn.Module):
    def __init__(self, z_channels, out_ch, resolution, num_res_blocks, attn_resolutions, ch, ch_mult=(1,2,4,8),
                 dropout=0.0, resamp_with_conv=True, rescale_factor=1.0, rescale_module_depth=1):
        super().__init__()
        tmp_chn = z_channels*ch_mult[-1]
        self.decoder = Decoder(out_ch=out_ch, z_channels=tmp_chn, attn_resolutions=attn_resolutions, dropout=dropout,
                               resamp_with_conv=resamp_with_conv, in_channels=None, num_res_blocks=num_res_blocks,
                               ch_mult=ch_mult, resolution=resolution, ch=ch)
        self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=z_channels, mid_channels=tmp_chn,
                                       out_channels=tmp_chn, depth=rescale_module_depth)

    def forward(self, x):
        x = self.rescaler(x)
        x = self.decoder(x)
        return x


class Upsampler(nn.Module):
    def __init__(self, in_size, out_size, in_channels, out_channels, ch_mult=2):
        super().__init__()
        assert out_size >= in_size
        num_blocks = int(np.log2(out_size//in_size))+1
        factor_up = 1.+ (out_size % in_size)
        print(f"Building {self.__class__.__name__} with in_size: {in_size} --> out_size {out_size} and factor {factor_up}")
        self.rescaler = LatentRescaler(factor=factor_up, in_channels=in_channels, mid_channels=2*in_channels,
                                       out_channels=in_channels)
        self.decoder = Decoder(out_ch=out_channels, resolution=out_size, z_channels=in_channels, num_res_blocks=2,
                               attn_resolutions=[], in_channels=None, ch=in_channels,
                               ch_mult=[ch_mult for _ in range(num_blocks)])

    def forward(self, x):
        x = self.rescaler(x)
        x = self.decoder(x)
        return x


class Resize(nn.Module):
    def __init__(self, in_channels=None, learned=False, mode="bilinear"):
        super().__init__()
        self.with_conv = learned
        self.mode = mode
        if self.with_conv:
            print(f"Note: {self.__class__.__name} uses learned downsampling and will ignore the fixed {mode} mode")
            raise NotImplementedError()
            assert in_channels is not None
            # no asymmetric padding in torch conv, must do it ourselves
            self.conv = torch.nn.Conv2d(in_channels,
                                        in_channels,
                                        kernel_size=4,
                                        stride=2,
                                        padding=1)

    def forward(self, x, scale_factor=1.0):
        if scale_factor==1.0:
            return x
        else:
            x = torch.nn.functional.interpolate(x, mode=self.mode, align_corners=False, scale_factor=scale_factor)
        return x