diff options
Diffstat (limited to 'ldm/modules')
-rw-r--r-- | ldm/modules/attention.py | 261 | ||||
-rw-r--r-- | ldm/modules/diffusionmodules/__init__.py | 0 | ||||
-rw-r--r-- | ldm/modules/diffusionmodules/model.py | 835 | ||||
-rw-r--r-- | ldm/modules/diffusionmodules/openaimodel.py | 961 | ||||
-rw-r--r-- | ldm/modules/diffusionmodules/util.py | 267 | ||||
-rw-r--r-- | ldm/modules/distributions/__init__.py | 0 | ||||
-rw-r--r-- | ldm/modules/distributions/distributions.py | 92 | ||||
-rw-r--r-- | ldm/modules/ema.py | 76 | ||||
-rw-r--r-- | ldm/modules/encoders/__init__.py | 0 | ||||
-rw-r--r-- | ldm/modules/encoders/modules.py | 234 | ||||
-rw-r--r-- | ldm/modules/encoders/xlmr.py | 137 | ||||
-rw-r--r-- | ldm/modules/image_degradation/__init__.py | 2 | ||||
-rw-r--r-- | ldm/modules/image_degradation/bsrgan.py | 730 | ||||
-rw-r--r-- | ldm/modules/image_degradation/bsrgan_light.py | 650 | ||||
-rw-r--r-- | ldm/modules/image_degradation/utils/test.png | bin | 441072 -> 0 bytes | |||
-rw-r--r-- | ldm/modules/image_degradation/utils_image.py | 916 | ||||
-rw-r--r-- | ldm/modules/losses/__init__.py | 1 | ||||
-rw-r--r-- | ldm/modules/losses/contperceptual.py | 111 | ||||
-rw-r--r-- | ldm/modules/losses/vqperceptual.py | 167 | ||||
-rw-r--r-- | ldm/modules/x_transformer.py | 641 |
20 files changed, 0 insertions, 6081 deletions
diff --git a/ldm/modules/attention.py b/ldm/modules/attention.py deleted file mode 100644 index f4eff39c..00000000 --- a/ldm/modules/attention.py +++ /dev/null @@ -1,261 +0,0 @@ -from inspect import isfunction -import math -import torch -import torch.nn.functional as F -from torch import nn, einsum -from einops import rearrange, repeat - -from ldm.modules.diffusionmodules.util import checkpoint - - -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.): - 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.): - 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 = 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 = 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., 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): - return checkpoint(self._forward, (x, context), self.parameters(), self.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., 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
\ No newline at end of file diff --git a/ldm/modules/diffusionmodules/__init__.py b/ldm/modules/diffusionmodules/__init__.py deleted file mode 100644 index e69de29b..00000000 --- a/ldm/modules/diffusionmodules/__init__.py +++ /dev/null diff --git a/ldm/modules/diffusionmodules/model.py b/ldm/modules/diffusionmodules/model.py deleted file mode 100644 index 533e589a..00000000 --- a/ldm/modules/diffusionmodules/model.py +++ /dev/null @@ -1,835 +0,0 @@ -# pytorch_diffusion + derived encoder decoder -import math -import torch -import torch.nn as nn -import numpy as np -from einops import rearrange - -from ldm.util import instantiate_from_config -from ldm.modules.attention import LinearAttention - - -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 LinAttnBlock(LinearAttention): - """to match AttnBlock usage""" - def __init__(self, in_channels): - super().__init__(dim=in_channels, heads=1, dim_head=in_channels) - - -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_ - - -def make_attn(in_channels, attn_type="vanilla"): - assert attn_type in ["vanilla", "linear", "none"], f'attn_type {attn_type} unknown' - print(f"making attention of type '{attn_type}' with {in_channels} in_channels") - if attn_type == "vanilla": - return AttnBlock(in_channels) - elif attn_type == "none": - return nn.Identity(in_channels) - else: - return LinAttnBlock(in_channels) - - -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 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) - - # 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] - 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)) - 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, 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) - - # middle - 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](h, 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 |