Spaces:
Sleeping
Sleeping
| import time | |
| from contextlib import contextmanager | |
| import pytorch_lightning as pl | |
| import torch | |
| import torch.nn.functional as F | |
| from ..modules.diffusionmodules.model import Decoder, Encoder | |
| from ..modules.distributions.distributions import DiagonalGaussianDistribution | |
| from ..util import instantiate_from_config | |
| from .enc_dec_pytorch import Decoder as Mag_Decoder | |
| from .enc_dec_pytorch import Encoder as Mag_Encoder | |
| class AutoencoderKLMagvit(pl.LightningModule): | |
| def __init__(self, | |
| ddconfig, | |
| lossconfig, | |
| embed_dim, | |
| ckpt_path=None, | |
| ignore_keys=[], | |
| image_key="image", | |
| colorize_nlabels=None, | |
| monitor=None, | |
| ): | |
| super().__init__() | |
| self.image_key = image_key | |
| self.encoder = Mag_Encoder() | |
| self.decoder = Mag_Decoder() | |
| self.loss = instantiate_from_config(lossconfig) | |
| self.quant_conv = torch.nn.Conv3d(16, 16, 1) | |
| self.post_quant_conv = torch.nn.Conv3d(8, 8, 1) | |
| self.embed_dim = embed_dim | |
| 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) | |
| def init_from_ckpt(self, path, ignore_keys=list()): | |
| sd = torch.load(path, map_location="cpu")["state_dict"] | |
| 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) | |
| print(f"Restored from {path}") | |
| def encode(self, x): | |
| h = self.encoder(x) | |
| moments = self.quant_conv(h) | |
| posterior = DiagonalGaussianDistribution(moments) | |
| return posterior | |
| def decode(self, z): | |
| z = self.post_quant_conv(z) | |
| dec = self.decoder(z) | |
| return dec | |
| def forward(self, input, sample_posterior=True): | |
| if input.ndim==4: | |
| input = input.unsqueeze(2) | |
| 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.ndim==5: | |
| x = x.permute(0, 4, 1, 2, 3).to(memory_format=torch.contiguous_format).float() | |
| return x | |
| if len(x.shape) == 3: | |
| x = x[..., None] | |
| x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float() | |
| return x | |
| def training_step(self, batch, batch_idx, optimizer_idx): | |
| # tic = time.time() | |
| inputs = self.get_input(batch, self.image_key) | |
| # print(f"get_input time {time.time() - tic}") | |
| # tic = time.time() | |
| reconstructions, posterior = self(inputs) | |
| # print(f"model forward time {time.time() - tic}") | |
| 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) | |
| # print(f"cal loss time {time.time() - tic}") | |
| 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) | |
| # print(f"cal loss time {time.time() - tic}") | |
| return discloss | |
| def validation_step(self, batch, batch_idx): | |
| with torch.no_grad(): | |
| 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 | |
| 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.*(x-x.min())/(x.max()-x.min()) - 1. | |
| return x | |
| class AutoencoderKL(pl.LightningModule): | |
| def __init__(self, | |
| ddconfig, | |
| lossconfig, | |
| embed_dim, | |
| ckpt_path=None, | |
| ignore_keys=[], | |
| image_key="image", | |
| colorize_nlabels=None, | |
| monitor=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 | |
| 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) | |
| def init_from_ckpt(self, path, ignore_keys=list()): | |
| sd = torch.load(path, map_location="cpu")["state_dict"] | |
| 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) | |
| print(f"Restored from {path}") | |
| def encode(self, x): | |
| h = self.encoder(x) | |
| moments = self.quant_conv(h) | |
| posterior = DiagonalGaussianDistribution(moments) | |
| return posterior | |
| def decode(self, z): | |
| 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 len(x.shape) == 3: | |
| x = x[..., None] | |
| x = x.permute(0, 3, 1, 2).to(memory_format=torch.contiguous_format).float() | |
| return x | |
| def training_step(self, batch, batch_idx, optimizer_idx): | |
| # tic = time.time() | |
| inputs = self.get_input(batch, self.image_key) | |
| # print(f"get_input time {time.time() - tic}") | |
| # tic = time.time() | |
| reconstructions, posterior = self(inputs) | |
| # print(f"model forward time {time.time() - tic}") | |
| tic = time.time() | |
| 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) | |
| # print(f"cal loss time {time.time() - tic}") | |
| 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) | |
| # print(f"cal loss time {time.time() - tic}") | |
| return discloss | |
| def validation_step(self, batch, batch_idx): | |
| tic = time.time() | |
| inputs = self.get_input(batch, self.image_key) | |
| print(f"get_input time {time.time() - tic}") | |
| tic = time.time() | |
| reconstructions, posterior = self(inputs) | |
| print(f"val forward time {time.time() - tic}") | |
| tic = time.time() | |
| 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) | |
| print(f"val end time {time.time() - tic}") | |
| 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 | |
| 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.*(x-x.min())/(x.max()-x.min()) - 1. | |
| 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 | |