Spaces:
Runtime error
Runtime error
File size: 10,734 Bytes
f85e212 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 |
from torch import nn, einsum
from einops import rearrange, reduce
import torch
import torch.nn.functional as F
from functools import partial
import math
# -------------------------------- Embeddings ------------------------------------------------------
class SinusoidalPosEmb(nn.Module):
def __init__(self, dim):
super().__init__()
self.dim = dim
def forward(self, x):
device = x.device
half_dim = self.dim // 2
emb = math.log(10000) / (half_dim - 1)
emb = torch.exp(torch.arange(half_dim, device=device) * -emb)
emb = x[:, None] * emb[None, :]
emb = torch.cat((emb.sin(), emb.cos()), dim=-1)
return emb
class LearnedSinusoidalPosEmb(nn.Module):
""" following @crowsonkb 's lead with learned sinusoidal pos emb """
""" https://github.com/crowsonkb/v-diffusion-jax/blob/master/diffusion/models/danbooru_128.py#L8 """
def __init__(self, dim):
super().__init__()
assert (dim % 2) == 0
half_dim = dim // 2
self.weights = nn.Parameter(torch.randn(half_dim))
def forward(self, x):
x = rearrange(x, 'b -> b 1')
freqs = x * rearrange(self.weights, 'd -> 1 d') * 2 * math.pi
fouriered = torch.cat((freqs.sin(), freqs.cos()), dim = -1)
fouriered = torch.cat((x, fouriered), dim = -1)
return fouriered
# -------------------------------------------------------------------
def exists(x):
return x is not None
def default(val, d):
if exists(val):
return val
return d() if callable(d) else d
def l2norm(t):
return F.normalize(t, dim = -1)
class Residual(nn.Module):
def __init__(self, fn):
super().__init__()
self.fn = fn
def forward(self, x, *args, **kwargs):
return self.fn(x, *args, **kwargs) + x
def Upsample(dim, dim_out = None):
return nn.Sequential(
nn.Upsample(scale_factor = 2, mode = 'nearest'),
nn.Conv2d(dim, default(dim_out, dim), 3, padding = 1)
)
def Downsample(dim, dim_out = None):
return nn.Conv2d(dim, default(dim_out, dim), 4, 2, 1)
class WeightStandardizedConv2d(nn.Conv2d):
"""
https://arxiv.org/abs/1903.10520
weight standardization purportedly works synergistically with group normalization
"""
def forward(self, x):
eps = 1e-5 if x.dtype == torch.float32 else 1e-3
weight = self.weight
mean = reduce(weight, 'o ... -> o 1 1 1', 'mean')
var = reduce(weight, 'o ... -> o 1 1 1', partial(torch.var, unbiased = False))
normalized_weight = (weight - mean) * (var + eps).rsqrt()
return F.conv2d(x, normalized_weight, self.bias, self.stride, self.padding, self.dilation, self.groups)
class LayerNorm(nn.Module):
def __init__(self, dim):
super().__init__()
self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
def forward(self, x):
eps = 1e-5 if x.dtype == torch.float32 else 1e-3
var = torch.var(x, dim = 1, unbiased = False, keepdim = True)
mean = torch.mean(x, dim = 1, keepdim = True)
return (x - mean) * (var + eps).rsqrt() * self.g
class PreNorm(nn.Module):
def __init__(self, dim, fn):
super().__init__()
self.fn = fn
self.norm = LayerNorm(dim)
def forward(self, x):
x = self.norm(x)
return self.fn(x)
class Block(nn.Module):
def __init__(self, dim, dim_out, groups = 8):
super().__init__()
self.proj = WeightStandardizedConv2d(dim, dim_out, 3, padding = 1)
self.norm = nn.GroupNorm(groups, dim_out)
self.act = nn.SiLU()
def forward(self, x, scale_shift = None):
x = self.proj(x)
x = self.norm(x)
if exists(scale_shift):
scale, shift = scale_shift
x = x * (scale + 1) + shift
x = self.act(x)
return x
class ResnetBlock(nn.Module):
def __init__(self, dim, dim_out, *, time_emb_dim = None, groups = 8):
super().__init__()
self.mlp = nn.Sequential(
nn.SiLU(),
nn.Linear(time_emb_dim, dim_out * 2)
) if exists(time_emb_dim) else None
self.block1 = Block(dim, dim_out, groups = groups)
self.block2 = Block(dim_out, dim_out, groups = groups)
self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()
def forward(self, x, time_emb = None):
scale_shift = None
if exists(self.mlp) and exists(time_emb):
time_emb = self.mlp(time_emb)
time_emb = rearrange(time_emb, 'b c -> b c 1 1')
scale_shift = time_emb.chunk(2, dim = 1)
h = self.block1(x, scale_shift = scale_shift)
h = self.block2(h)
return h + self.res_conv(x)
class LinearAttention(nn.Module):
def __init__(self, dim, heads = 4, dim_head = 32):
super().__init__()
self.scale = dim_head ** -0.5
self.heads = heads
hidden_dim = dim_head * heads
self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias = False)
self.to_out = nn.Sequential(
nn.Conv2d(hidden_dim, dim, 1),
LayerNorm(dim)
)
def forward(self, x):
b, c, h, w = x.shape
qkv = self.to_qkv(x).chunk(3, dim = 1)
q, k, v = map(lambda t: rearrange(t, 'b (h c) x y -> b h c (x y)', h = self.heads), qkv)
q = q.softmax(dim = -2)
k = k.softmax(dim = -1)
q = q * self.scale
v = v / (h * w)
context = torch.einsum('b h d n, b h e n -> b h d e', k, v)
out = torch.einsum('b h d e, b h d n -> b h e n', context, q)
out = rearrange(out, 'b h c (x y) -> b (h c) x y', h = self.heads, x = h, y = w)
return self.to_out(out)
class Attention(nn.Module):
def __init__(self, dim, heads = 4, dim_head = 32, scale = 10):
super().__init__()
self.scale = scale
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).chunk(3, dim = 1)
q, k, v = map(lambda t: rearrange(t, 'b (h c) x y -> b h c (x y)', h = self.heads), qkv)
q, k = map(l2norm, (q, k))
sim = einsum('b h d i, b h d j -> b h i j', q, k) * self.scale
attn = sim.softmax(dim = -1)
out = einsum('b h i j, b h d j -> b h i d', attn, v)
out = rearrange(out, 'b h (x y) d -> b (h d) x y', x = h, y = w)
return self.to_out(out)
class UNet(nn.Module):
def __init__(
self,
dim=32,
init_dim = None,
out_dim = None,
dim_mults=(1, 2, 4, 8),
channels = 3,
self_condition = False,
resnet_block_groups = 8,
learned_variance = False,
learned_sinusoidal_cond = False,
learned_sinusoidal_dim = 16,
**kwargs
):
super().__init__()
# determine dimensions
self.channels = channels
self.self_condition = self_condition
input_channels = channels * (2 if self_condition else 1)
init_dim = default(init_dim, dim)
self.init_conv = nn.Conv2d(input_channels, init_dim, 7, padding = 3)
dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
in_out = list(zip(dims[:-1], dims[1:]))
block_klass = partial(ResnetBlock, groups = resnet_block_groups)
# time embeddings
time_dim = dim * 4
self.learned_sinusoidal_cond = learned_sinusoidal_cond
if learned_sinusoidal_cond:
sinu_pos_emb = LearnedSinusoidalPosEmb(learned_sinusoidal_dim)
fourier_dim = learned_sinusoidal_dim + 1
else:
sinu_pos_emb = SinusoidalPosEmb(dim)
fourier_dim = dim
self.time_mlp = nn.Sequential(
sinu_pos_emb,
nn.Linear(fourier_dim, time_dim),
nn.GELU(),
nn.Linear(time_dim, time_dim)
)
# layers
self.downs = nn.ModuleList([])
self.ups = nn.ModuleList([])
num_resolutions = len(in_out)
for ind, (dim_in, dim_out) in enumerate(in_out):
is_last = ind >= (num_resolutions - 1)
self.downs.append(nn.ModuleList([
block_klass(dim_in, dim_in, time_emb_dim = time_dim),
block_klass(dim_in, dim_in, time_emb_dim = time_dim),
Residual(PreNorm(dim_in, LinearAttention(dim_in))),
Downsample(dim_in, dim_out) if not is_last else nn.Conv2d(dim_in, dim_out, 3, padding = 1)
]))
mid_dim = dims[-1]
self.mid_block1 = block_klass(mid_dim, mid_dim, time_emb_dim = time_dim)
self.mid_attn = Residual(PreNorm(mid_dim, Attention(mid_dim)))
self.mid_block2 = block_klass(mid_dim, mid_dim, time_emb_dim = time_dim)
for ind, (dim_in, dim_out) in enumerate(reversed(in_out)):
is_last = ind == (len(in_out) - 1)
self.ups.append(nn.ModuleList([
block_klass(dim_out + dim_in, dim_out, time_emb_dim = time_dim),
block_klass(dim_out + dim_in, dim_out, time_emb_dim = time_dim),
Residual(PreNorm(dim_out, LinearAttention(dim_out))),
Upsample(dim_out, dim_in) if not is_last else nn.Conv2d(dim_out, dim_in, 3, padding = 1)
]))
default_out_dim = channels * (1 if not learned_variance else 2)
self.out_dim = default(out_dim, default_out_dim)
self.final_res_block = block_klass(dim * 2, dim, time_emb_dim = time_dim)
self.final_conv = nn.Conv2d(dim, self.out_dim, 1)
def forward(self, x, time, condition=None, self_cond=None):
if self.self_condition:
x_self_cond = default(self_cond, lambda: torch.zeros_like(x))
x = torch.cat((x_self_cond, x), dim = 1)
x = self.init_conv(x)
r = x.clone()
t = self.time_mlp(time)
h = []
for block1, block2, attn, downsample in self.downs:
x = block1(x, t)
h.append(x)
x = block2(x, t)
x = attn(x)
h.append(x)
x = downsample(x)
x = self.mid_block1(x, t)
x = self.mid_attn(x)
x = self.mid_block2(x, t)
for block1, block2, attn, upsample in self.ups:
x = torch.cat((x, h.pop()), dim = 1)
x = block1(x, t)
x = torch.cat((x, h.pop()), dim = 1)
x = block2(x, t)
x = attn(x)
x = upsample(x)
x = torch.cat((x, r), dim = 1)
x = self.final_res_block(x, t)
return self.final_conv(x), [] |