Spaces:
Sleeping
Sleeping
File size: 12,845 Bytes
b725c5a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 |
# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import argparse
from tqdm import tqdm
import torch
import numpy as np
from torch.utils.data import DataLoader
from torch.nn.parallel import DistributedDataParallel
from optimizer.optimizers import Eve, ScaledAdam
from schedulers.scheduler import NoamScheduler, Eden
from models.tts.valle.valle_dataset import (
VALLEDataset,
VALLECollator,
VariableSampler,
batch_by_size,
)
from models.tts.base import TTSTrainer
from models.tts.valle.valle import VALLE
class VALLETrainer(TTSTrainer):
def __init__(self, args, cfg):
TTSTrainer.__init__(self, args, cfg)
def _build_model(self):
model = VALLE(self.cfg.model)
return model
def _build_dataset(self):
return VALLEDataset, VALLECollator
def _build_optimizer(self):
if self.args.train_stage:
if isinstance(self.model, DistributedDataParallel):
model = self.model.module
else:
model = self.model
model_parameters = model.stage_parameters(self.args.train_stage)
else:
model_parameters = self.model.parameters()
if self.cfg.train.optimizer == "ScaledAdam":
parameters_names = []
if self.args.train_stage != 0:
parameters_names.append(
[
name_param_pair[0]
for name_param_pair in model.stage_named_parameters(
self.args.train_stage
)
]
)
else:
parameters_names.append(
[name_param_pair[0] for name_param_pair in model.named_parameters()]
)
optimizer = ScaledAdam(
model_parameters,
lr=self.cfg.train.base_lr,
betas=(0.9, 0.95),
clipping_scale=2.0,
parameters_names=parameters_names,
show_dominant_parameters=False,
clipping_update_period=1000,
)
elif self.cfg.train.optimizer == "Eve":
optimizer = Eve(
model_parameters,
lr=self.cfg.train.base_lr,
betas=(0.9, 0.98),
target_rms=0.1,
)
elif self.cfg.train.optimizer == "AdamW":
optimizer = torch.optim.AdamW(
model_parameters,
lr=self.cfg.train.base_lr,
betas=(0.9, 0.95),
weight_decay=1e-2,
eps=1e-8,
)
elif self.cfg.train.optimizer == "Adam":
optimizer = torch.optim.Adam(
model_parameters,
lr=self.cfg.train.base_lr,
betas=(0.9, 0.95),
eps=1e-8,
)
else:
raise NotImplementedError()
return optimizer
def _build_scheduler(self):
if self.cfg.train.scheduler.lower() == "eden":
scheduler = Eden(
self.optimizer, 5000, 4, warmup_batches=self.cfg.train.warmup_steps
)
elif self.cfg.train.scheduler.lower() == "noam":
scheduler = NoamScheduler(
self.cfg.train.base_lr,
self.optimizer,
self.cfg.model.decoder_dim,
warmup_steps=self.cfg.train.warmup_steps,
)
elif self.cfg.train.scheduler.lower() == "cosine":
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
self.cfg.train.warmup_steps,
self.optimizer,
eta_min=self.cfg.train.base_lr,
)
else:
raise NotImplementedError(f"{self.cfg.train.scheduler}")
return scheduler
def _train_epoch(self):
r"""Training epoch. Should return average loss of a batch (sample) over
one epoch. See ``train_loop`` for usage.
"""
if isinstance(self.model, dict):
for key in self.model.keys():
self.model[key].train()
else:
self.model.train()
epoch_sum_loss: float = 0.0
epoch_losses: dict = {}
epoch_step: int = 0
for batch in tqdm(
self.train_dataloader,
desc=f"Training Epoch {self.epoch}",
unit="batch",
colour="GREEN",
leave=False,
dynamic_ncols=True,
smoothing=0.04,
disable=not self.accelerator.is_main_process,
):
# Do training step and BP
with self.accelerator.accumulate(self.model):
total_loss, train_losses = self._train_step(batch)
self.accelerator.backward(total_loss)
self.optimizer.step()
self.optimizer.zero_grad()
self.batch_count += 1
if self.batch_count % self.cfg.train.gradient_accumulation_step == 0:
if self.cfg.train.optimizer not in ["ScaledAdam", "Eve"]:
torch.nn.utils.clip_grad_norm_(self.model.parameters(), 1.0)
for k in range(self.cfg.train.gradient_accumulation_step):
if isinstance(self.scheduler, Eden):
self.scheduler.step_batch(self.step)
else:
self.scheduler.step()
epoch_sum_loss += total_loss.detach().cpu().item()
if isinstance(train_losses, dict):
for key, value in train_losses.items():
if key not in epoch_losses.keys():
epoch_losses[key] = value
else:
epoch_losses[key] += value
if isinstance(train_losses, dict):
for key, loss in train_losses.items():
self.accelerator.log(
{"Step/Train {}".format(key): "{:.6f}".format(loss)},
step=self.step,
)
else:
self.accelerator.log(
{"Step/Train Loss": loss},
step=self.step,
)
self.accelerator.log(
{"Step/lr": self.scheduler.get_last_lr()[0]},
step=self.step,
)
# print loss every log_epoch_step steps
# if epoch_step % self.cfg.train.log_epoch_step == 0:
# for key, loss in train_losses.items():
# self.logger.info("Step/Train {}: {:.6f}".format(key, loss))
# print("Step/Train {}: {:.6f}".format(key, loss))
self.step += 1
epoch_step += 1
self.accelerator.wait_for_everyone()
epoch_sum_loss = (
epoch_sum_loss
/ len(self.train_dataloader)
* self.cfg.train.gradient_accumulation_step
)
for key in epoch_losses.keys():
epoch_losses[key] = (
epoch_losses[key]
/ len(self.train_dataloader)
* self.cfg.train.gradient_accumulation_step
)
return epoch_sum_loss, epoch_losses
def _train_step(self, batch, is_training=True):
text_tokens = batch["phone_seq"].to(self.device)
text_tokens_lens = batch["phone_len"].to(self.device)
assert text_tokens.ndim == 2
audio_features = batch["acoustic_token"].to(self.device)
audio_features_lens = batch["target_len"].to(self.device)
assert audio_features.ndim == 3
with torch.set_grad_enabled(is_training):
loss, losses = self.model(
x=text_tokens,
x_lens=text_tokens_lens,
y=audio_features,
y_lens=audio_features_lens,
train_stage=self.args.train_stage,
)
assert loss.requires_grad == is_training
loss_dict = {}
frames_sum = (audio_features_lens).sum()
avg_loss = loss / frames_sum
loss_dict["loss"] = avg_loss.detach().cpu().item()
for l in losses:
loss_dict[l] = losses[l].detach().cpu().item() / frames_sum.item()
return avg_loss, loss_dict
def _valid_step(self, batch):
valid_losses = {}
total_loss = 0
valid_stats = {}
total_loss, valid_losses = self._train_step(
batch=batch,
is_training=False,
)
assert total_loss.requires_grad is False
total_loss = total_loss.detach().cpu().item()
return total_loss, valid_losses, valid_stats
def add_arguments(parser: argparse.ArgumentParser):
parser.add_argument(
"--train_stage",
type=int,
default="1",
help="0: train all modules, 1: AR Decoder, 2: NAR Decoder",
)
def _build_dataloader(self):
if not self.cfg.train.use_dynamic_batchsize:
return super()._build_dataloader()
if len(self.cfg.dataset) > 1:
raise Exception("use_dynamic_batchsize only supports single dataset now.")
Dataset, Collator = self._build_dataset()
train_dataset = Dataset(
self.cfg, self.cfg.dataset[0], is_valid=False
) # TODO: support use_dynamic_batchsize for more than one datasets.
train_collate = Collator(self.cfg)
batch_sampler = batch_by_size(
train_dataset.num_frame_indices,
train_dataset.get_num_frames,
max_tokens=self.cfg.train.max_tokens * self.accelerator.num_processes,
max_sentences=self.cfg.train.max_sentences * self.accelerator.num_processes,
required_batch_size_multiple=self.accelerator.num_processes,
)
np.random.seed(1234)
np.random.shuffle(batch_sampler)
print(batch_sampler[:1])
batches = [
x[self.accelerator.local_process_index :: self.accelerator.num_processes]
for x in batch_sampler
if len(x) % self.accelerator.num_processes == 0
]
train_loader = DataLoader(
train_dataset,
collate_fn=train_collate,
num_workers=self.cfg.train.dataloader.num_worker,
batch_sampler=VariableSampler(
batches, drop_last=False, use_random_sampler=True
),
pin_memory=False,
)
self.accelerator.wait_for_everyone()
valid_dataset = Dataset(self.cfg, self.cfg.dataset[0], is_valid=True)
valid_collate = Collator(self.cfg)
batch_sampler = batch_by_size(
valid_dataset.num_frame_indices,
valid_dataset.get_num_frames,
max_tokens=self.cfg.train.max_tokens * self.accelerator.num_processes,
max_sentences=self.cfg.train.max_sentences * self.accelerator.num_processes,
required_batch_size_multiple=self.accelerator.num_processes,
)
batches = [
x[self.accelerator.local_process_index :: self.accelerator.num_processes]
for x in batch_sampler
if len(x) % self.accelerator.num_processes == 0
]
valid_loader = DataLoader(
valid_dataset,
collate_fn=valid_collate,
num_workers=self.cfg.train.dataloader.num_worker,
batch_sampler=VariableSampler(batches, drop_last=False),
pin_memory=False,
)
self.accelerator.wait_for_everyone()
return train_loader, valid_loader
def _accelerator_prepare(self):
if not self.cfg.train.use_dynamic_batchsize:
(
self.train_dataloader,
self.valid_dataloader,
) = self.accelerator.prepare(
self.train_dataloader,
self.valid_dataloader,
)
if isinstance(self.model, dict):
for key in self.model.keys():
self.model[key] = self.accelerator.prepare(self.model[key])
else:
self.model = self.accelerator.prepare(self.model)
if isinstance(self.optimizer, dict):
for key in self.optimizer.keys():
self.optimizer[key] = self.accelerator.prepare(self.optimizer[key])
else:
self.optimizer = self.accelerator.prepare(self.optimizer)
if isinstance(self.scheduler, dict):
for key in self.scheduler.keys():
self.scheduler[key] = self.accelerator.prepare(self.scheduler[key])
else:
self.scheduler = self.accelerator.prepare(self.scheduler)
|