Spaces:
Running
on
Zero
Running
on
Zero
File size: 8,912 Bytes
5bec700 |
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 |
import os
from contextlib import contextmanager
import torch
import numpy as np
from einops import rearrange
import torch.nn.functional as F
import pytorch_lightning as pl
from lvdm.modules.networks.ae_modules import Encoder, Decoder
from lvdm.distributions import DiagonalGaussianDistribution
from utils.utils import instantiate_from_config
class AutoencoderKL(pl.LightningModule):
def __init__(
self,
ddconfig,
lossconfig,
embed_dim,
ckpt_path=None,
ignore_keys=[],
image_key="image",
colorize_nlabels=None,
monitor=None,
test=False,
logdir=None,
input_dim=4,
test_args=None,
):
super().__init__()
self.image_key = image_key
self.encoder = Encoder(**ddconfig)
self.decoder = Decoder(**ddconfig)
self.loss = instantiate_from_config(lossconfig)
assert ddconfig["double_z"]
self.quant_conv = torch.nn.Conv2d(2 * ddconfig["z_channels"], 2 * embed_dim, 1)
self.post_quant_conv = torch.nn.Conv2d(embed_dim, ddconfig["z_channels"], 1)
self.embed_dim = embed_dim
self.input_dim = input_dim
self.test = test
self.test_args = test_args
self.logdir = logdir
if colorize_nlabels is not None:
assert type(colorize_nlabels) == int
self.register_buffer("colorize", torch.randn(3, colorize_nlabels, 1, 1))
if monitor is not None:
self.monitor = monitor
if ckpt_path is not None:
self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys)
if self.test:
self.init_test()
def init_test(
self,
):
self.test = True
save_dir = os.path.join(self.logdir, "test")
if "ckpt" in self.test_args:
ckpt_name = (
os.path.basename(self.test_args.ckpt).split(".ckpt")[0]
+ f"_epoch{self._cur_epoch}"
)
self.root = os.path.join(save_dir, ckpt_name)
else:
self.root = save_dir
if "test_subdir" in self.test_args:
self.root = os.path.join(save_dir, self.test_args.test_subdir)
self.root_zs = os.path.join(self.root, "zs")
self.root_dec = os.path.join(self.root, "reconstructions")
self.root_inputs = os.path.join(self.root, "inputs")
os.makedirs(self.root, exist_ok=True)
if self.test_args.save_z:
os.makedirs(self.root_zs, exist_ok=True)
if self.test_args.save_reconstruction:
os.makedirs(self.root_dec, exist_ok=True)
if self.test_args.save_input:
os.makedirs(self.root_inputs, exist_ok=True)
assert self.test_args is not None
self.test_maximum = getattr(self.test_args, "test_maximum", None)
self.count = 0
self.eval_metrics = {}
self.decodes = []
self.save_decode_samples = 2048
def init_from_ckpt(self, path, ignore_keys=list()):
sd = torch.load(path, map_location="cpu")
try:
self._cur_epoch = sd["epoch"]
sd = sd["state_dict"]
except:
self._cur_epoch = "null"
keys = list(sd.keys())
for k in keys:
for ik in ignore_keys:
if k.startswith(ik):
print("Deleting key {} from state_dict.".format(k))
del sd[k]
self.load_state_dict(sd, strict=False)
# self.load_state_dict(sd, strict=True)
print(f"Restored from {path}")
def encode(self, x, **kwargs):
h = self.encoder(x)
moments = self.quant_conv(h)
posterior = DiagonalGaussianDistribution(moments)
return posterior
def decode(self, z, **kwargs):
z = self.post_quant_conv(z)
dec = self.decoder(z)
return dec
def forward(self, input, sample_posterior=True):
posterior = self.encode(input)
if sample_posterior:
z = posterior.sample()
else:
z = posterior.mode()
dec = self.decode(z)
return dec, posterior
def get_input(self, batch, k):
x = batch[k]
if x.dim() == 5 and self.input_dim == 4:
b, c, t, h, w = x.shape
self.b = b
self.t = t
x = rearrange(x, "b c t h w -> (b t) c h w")
return x
def training_step(self, batch, batch_idx, optimizer_idx):
inputs = self.get_input(batch, self.image_key)
reconstructions, posterior = self(inputs)
if optimizer_idx == 0:
# train encoder+decoder+logvar
aeloss, log_dict_ae = self.loss(
inputs,
reconstructions,
posterior,
optimizer_idx,
self.global_step,
last_layer=self.get_last_layer(),
split="train",
)
self.log(
"aeloss",
aeloss,
prog_bar=True,
logger=True,
on_step=True,
on_epoch=True,
)
self.log_dict(
log_dict_ae, prog_bar=False, logger=True, on_step=True, on_epoch=False
)
return aeloss
if optimizer_idx == 1:
# train the discriminator
discloss, log_dict_disc = self.loss(
inputs,
reconstructions,
posterior,
optimizer_idx,
self.global_step,
last_layer=self.get_last_layer(),
split="train",
)
self.log(
"discloss",
discloss,
prog_bar=True,
logger=True,
on_step=True,
on_epoch=True,
)
self.log_dict(
log_dict_disc, prog_bar=False, logger=True, on_step=True, on_epoch=False
)
return discloss
def validation_step(self, batch, batch_idx):
inputs = self.get_input(batch, self.image_key)
reconstructions, posterior = self(inputs)
aeloss, log_dict_ae = self.loss(
inputs,
reconstructions,
posterior,
0,
self.global_step,
last_layer=self.get_last_layer(),
split="val",
)
discloss, log_dict_disc = self.loss(
inputs,
reconstructions,
posterior,
1,
self.global_step,
last_layer=self.get_last_layer(),
split="val",
)
self.log("val/rec_loss", log_dict_ae["val/rec_loss"])
self.log_dict(log_dict_ae)
self.log_dict(log_dict_disc)
return self.log_dict
def configure_optimizers(self):
lr = self.learning_rate
opt_ae = torch.optim.Adam(
list(self.encoder.parameters())
+ list(self.decoder.parameters())
+ list(self.quant_conv.parameters())
+ list(self.post_quant_conv.parameters()),
lr=lr,
betas=(0.5, 0.9),
)
opt_disc = torch.optim.Adam(
self.loss.discriminator.parameters(), lr=lr, betas=(0.5, 0.9)
)
return [opt_ae, opt_disc], []
def get_last_layer(self):
return self.decoder.conv_out.weight
@torch.no_grad()
def log_images(self, batch, only_inputs=False, **kwargs):
log = dict()
x = self.get_input(batch, self.image_key)
x = x.to(self.device)
if not only_inputs:
xrec, posterior = self(x)
if x.shape[1] > 3:
# colorize with random projection
assert xrec.shape[1] > 3
x = self.to_rgb(x)
xrec = self.to_rgb(xrec)
log["samples"] = self.decode(torch.randn_like(posterior.sample()))
log["reconstructions"] = xrec
log["inputs"] = x
return log
def to_rgb(self, x):
assert self.image_key == "segmentation"
if not hasattr(self, "colorize"):
self.register_buffer("colorize", torch.randn(3, x.shape[1], 1, 1).to(x))
x = F.conv2d(x, weight=self.colorize)
x = 2.0 * (x - x.min()) / (x.max() - x.min()) - 1.0
return x
class IdentityFirstStage(torch.nn.Module):
def __init__(self, *args, vq_interface=False, **kwargs):
self.vq_interface = vq_interface # TODO: Should be true by default but check to not break older stuff
super().__init__()
def encode(self, x, *args, **kwargs):
return x
def decode(self, x, *args, **kwargs):
return x
def quantize(self, x, *args, **kwargs):
if self.vq_interface:
return x, None, [None, None, None]
return x
def forward(self, x, *args, **kwargs):
return x
|