mirror of
https://github.com/kohya-ss/sd-scripts.git
synced 2026-04-09 06:45:09 +00:00
format with black
This commit is contained in:
Kohya S
707
fine_tune.py
707
fine_tune.py
@@ -5,7 +5,7 @@ import argparse
|
||||
import gc
|
||||
import math
|
||||
import os
|
||||
import toml
|
||||
import toml
|
||||
|
||||
from tqdm import tqdm
|
||||
import torch
|
||||
@@ -16,371 +16,416 @@ from diffusers import DDPMScheduler
|
||||
import library.train_util as train_util
|
||||
import library.config_util as config_util
|
||||
from library.config_util import (
|
||||
ConfigSanitizer,
|
||||
BlueprintGenerator,
|
||||
ConfigSanitizer,
|
||||
BlueprintGenerator,
|
||||
)
|
||||
|
||||
|
||||
def collate_fn(examples):
|
||||
return examples[0]
|
||||
return examples[0]
|
||||
|
||||
|
||||
def train(args):
|
||||
train_util.verify_training_args(args)
|
||||
train_util.prepare_dataset_args(args, True)
|
||||
train_util.verify_training_args(args)
|
||||
train_util.prepare_dataset_args(args, True)
|
||||
|
||||
cache_latents = args.cache_latents
|
||||
cache_latents = args.cache_latents
|
||||
|
||||
if args.seed is not None:
|
||||
set_seed(args.seed) # 乱数系列を初期化する
|
||||
if args.seed is not None:
|
||||
set_seed(args.seed) # 乱数系列を初期化する
|
||||
|
||||
tokenizer = train_util.load_tokenizer(args)
|
||||
tokenizer = train_util.load_tokenizer(args)
|
||||
|
||||
blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, True, True))
|
||||
if args.dataset_config is not None:
|
||||
print(f"Load dataset config from {args.dataset_config}")
|
||||
user_config = config_util.load_user_config(args.dataset_config)
|
||||
ignored = ["train_data_dir", "in_json"]
|
||||
if any(getattr(args, attr) is not None for attr in ignored):
|
||||
print("ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(', '.join(ignored)))
|
||||
else:
|
||||
user_config = {
|
||||
"datasets": [{
|
||||
"subsets": [{
|
||||
"image_dir": args.train_data_dir,
|
||||
"metadata_file": args.in_json,
|
||||
}]
|
||||
}]
|
||||
}
|
||||
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group)
|
||||
return
|
||||
if len(train_dataset_group) == 0:
|
||||
print("No data found. Please verify the metadata file and train_data_dir option. / 画像がありません。メタデータおよびtrain_data_dirオプションを確認してください。")
|
||||
return
|
||||
|
||||
if cache_latents:
|
||||
assert train_dataset_group.is_latent_cacheable(), "when caching latents, either color_aug or random_crop cannot be used / latentをキャッシュするときはcolor_augとrandom_cropは使えません"
|
||||
|
||||
# acceleratorを準備する
|
||||
print("prepare accelerator")
|
||||
accelerator, unwrap_model = train_util.prepare_accelerator(args)
|
||||
|
||||
# mixed precisionに対応した型を用意しておき適宜castする
|
||||
weight_dtype, save_dtype = train_util.prepare_dtype(args)
|
||||
|
||||
# モデルを読み込む
|
||||
text_encoder, vae, unet, load_stable_diffusion_format = train_util.load_target_model(args, weight_dtype)
|
||||
|
||||
# verify load/save model formats
|
||||
if load_stable_diffusion_format:
|
||||
src_stable_diffusion_ckpt = args.pretrained_model_name_or_path
|
||||
src_diffusers_model_path = None
|
||||
else:
|
||||
src_stable_diffusion_ckpt = None
|
||||
src_diffusers_model_path = args.pretrained_model_name_or_path
|
||||
|
||||
if args.save_model_as is None:
|
||||
save_stable_diffusion_format = load_stable_diffusion_format
|
||||
use_safetensors = args.use_safetensors
|
||||
else:
|
||||
save_stable_diffusion_format = args.save_model_as.lower() == 'ckpt' or args.save_model_as.lower() == 'safetensors'
|
||||
use_safetensors = args.use_safetensors or ("safetensors" in args.save_model_as.lower())
|
||||
|
||||
# Diffusers版のxformers使用フラグを設定する関数
|
||||
def set_diffusers_xformers_flag(model, valid):
|
||||
# model.set_use_memory_efficient_attention_xformers(valid) # 次のリリースでなくなりそう
|
||||
# pipeが自動で再帰的にset_use_memory_efficient_attention_xformersを探すんだって(;´Д｀)
|
||||
# U-Netだけ使う時にはどうすればいいのか……仕方ないからコピって使うか
|
||||
# 0.10.2でなんか巻き戻って個別に指定するようになった(;^ω^)
|
||||
|
||||
# Recursively walk through all the children.
|
||||
# Any children which exposes the set_use_memory_efficient_attention_xformers method
|
||||
# gets the message
|
||||
def fn_recursive_set_mem_eff(module: torch.nn.Module):
|
||||
if hasattr(module, "set_use_memory_efficient_attention_xformers"):
|
||||
module.set_use_memory_efficient_attention_xformers(valid)
|
||||
|
||||
for child in module.children():
|
||||
fn_recursive_set_mem_eff(child)
|
||||
|
||||
fn_recursive_set_mem_eff(model)
|
||||
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
if args.diffusers_xformers:
|
||||
print("Use xformers by Diffusers")
|
||||
set_diffusers_xformers_flag(unet, True)
|
||||
else:
|
||||
# Windows版のxformersはfloatで学習できないのでxformersを使わない設定も可能にしておく必要がある
|
||||
print("Disable Diffusers' xformers")
|
||||
set_diffusers_xformers_flag(unet, False)
|
||||
train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers)
|
||||
|
||||
# 学習を準備する
|
||||
if cache_latents:
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
with torch.no_grad():
|
||||
train_dataset_group.cache_latents(vae)
|
||||
vae.to("cpu")
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
gc.collect()
|
||||
|
||||
# 学習を準備する：モデルを適切な状態にする
|
||||
training_models = []
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
training_models.append(unet)
|
||||
|
||||
if args.train_text_encoder:
|
||||
print("enable text encoder training")
|
||||
if args.gradient_checkpointing:
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
training_models.append(text_encoder)
|
||||
else:
|
||||
text_encoder.to(accelerator.device, dtype=weight_dtype)
|
||||
text_encoder.requires_grad_(False) # text encoderは学習しない
|
||||
if args.gradient_checkpointing:
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
text_encoder.train() # required for gradient_checkpointing
|
||||
blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, True, True))
|
||||
if args.dataset_config is not None:
|
||||
print(f"Load dataset config from {args.dataset_config}")
|
||||
user_config = config_util.load_user_config(args.dataset_config)
|
||||
ignored = ["train_data_dir", "in_json"]
|
||||
if any(getattr(args, attr) is not None for attr in ignored):
|
||||
print(
|
||||
"ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
|
||||
", ".join(ignored)
|
||||
)
|
||||
)
|
||||
else:
|
||||
text_encoder.eval()
|
||||
user_config = {
|
||||
"datasets": [
|
||||
{
|
||||
"subsets": [
|
||||
{
|
||||
"image_dir": args.train_data_dir,
|
||||
"metadata_file": args.in_json,
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
|
||||
for m in training_models:
|
||||
m.requires_grad_(True)
|
||||
params = []
|
||||
for m in training_models:
|
||||
params.extend(m.parameters())
|
||||
params_to_optimize = params
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group)
|
||||
return
|
||||
if len(train_dataset_group) == 0:
|
||||
print(
|
||||
"No data found. Please verify the metadata file and train_data_dir option. / 画像がありません。メタデータおよびtrain_data_dirオプションを確認してください。"
|
||||
)
|
||||
return
|
||||
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params=params_to_optimize)
|
||||
if cache_latents:
|
||||
assert (
|
||||
train_dataset_group.is_latent_cacheable()
|
||||
), "when caching latents, either color_aug or random_crop cannot be used / latentをキャッシュするときはcolor_augとrandom_cropは使えません"
|
||||
|
||||
# dataloaderを準備する
|
||||
# DataLoaderのプロセス数：0はメインプロセスになる
|
||||
n_workers = min(args.max_data_loader_n_workers, os.cpu_count() - 1) # cpu_count-1 ただし最大で指定された数まで
|
||||
train_dataloader = torch.utils.data.DataLoader(
|
||||
train_dataset_group, batch_size=1, shuffle=True, collate_fn=collate_fn, num_workers=n_workers, persistent_workers=args.persistent_data_loader_workers)
|
||||
# acceleratorを準備する
|
||||
print("prepare accelerator")
|
||||
accelerator, unwrap_model = train_util.prepare_accelerator(args)
|
||||
|
||||
# 学習ステップ数を計算する
|
||||
if args.max_train_epochs is not None:
|
||||
args.max_train_steps = args.max_train_epochs * len(train_dataloader)
|
||||
print(f"override steps. steps for {args.max_train_epochs} epochs is / 指定エポックまでのステップ数: {args.max_train_steps}")
|
||||
# mixed precisionに対応した型を用意しておき適宜castする
|
||||
weight_dtype, save_dtype = train_util.prepare_dtype(args)
|
||||
|
||||
# lr schedulerを用意する
|
||||
lr_scheduler = train_util.get_scheduler_fix(args.lr_scheduler, optimizer, num_warmup_steps=args.lr_warmup_steps,
|
||||
num_training_steps=args.max_train_steps * args.gradient_accumulation_steps,
|
||||
num_cycles=args.lr_scheduler_num_cycles, power=args.lr_scheduler_power)
|
||||
# モデルを読み込む
|
||||
text_encoder, vae, unet, load_stable_diffusion_format = train_util.load_target_model(args, weight_dtype)
|
||||
|
||||
# 実験的機能：勾配も含めたfp16学習を行う モデル全体をfp16にする
|
||||
if args.full_fp16:
|
||||
assert args.mixed_precision == "fp16", "full_fp16 requires mixed precision='fp16' / full_fp16を使う場合はmixed_precision='fp16'を指定してください。"
|
||||
print("enable full fp16 training.")
|
||||
unet.to(weight_dtype)
|
||||
text_encoder.to(weight_dtype)
|
||||
# verify load/save model formats
|
||||
if load_stable_diffusion_format:
|
||||
src_stable_diffusion_ckpt = args.pretrained_model_name_or_path
|
||||
src_diffusers_model_path = None
|
||||
else:
|
||||
src_stable_diffusion_ckpt = None
|
||||
src_diffusers_model_path = args.pretrained_model_name_or_path
|
||||
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
if args.train_text_encoder:
|
||||
unet, text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
|
||||
unet, text_encoder, optimizer, train_dataloader, lr_scheduler)
|
||||
else:
|
||||
unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(unet, optimizer, train_dataloader, lr_scheduler)
|
||||
if args.save_model_as is None:
|
||||
save_stable_diffusion_format = load_stable_diffusion_format
|
||||
use_safetensors = args.use_safetensors
|
||||
else:
|
||||
save_stable_diffusion_format = args.save_model_as.lower() == "ckpt" or args.save_model_as.lower() == "safetensors"
|
||||
use_safetensors = args.use_safetensors or ("safetensors" in args.save_model_as.lower())
|
||||
|
||||
# 実験的機能：勾配も含めたfp16学習を行う PyTorchにパッチを当ててfp16でのgrad scaleを有効にする
|
||||
if args.full_fp16:
|
||||
train_util.patch_accelerator_for_fp16_training(accelerator)
|
||||
# Diffusers版のxformers使用フラグを設定する関数
|
||||
def set_diffusers_xformers_flag(model, valid):
|
||||
# model.set_use_memory_efficient_attention_xformers(valid) # 次のリリースでなくなりそう
|
||||
# pipeが自動で再帰的にset_use_memory_efficient_attention_xformersを探すんだって(;´Д｀)
|
||||
# U-Netだけ使う時にはどうすればいいのか……仕方ないからコピって使うか
|
||||
# 0.10.2でなんか巻き戻って個別に指定するようになった(;^ω^)
|
||||
|
||||
# resumeする
|
||||
if args.resume is not None:
|
||||
print(f"resume training from state: {args.resume}")
|
||||
accelerator.load_state(args.resume)
|
||||
# Recursively walk through all the children.
|
||||
# Any children which exposes the set_use_memory_efficient_attention_xformers method
|
||||
# gets the message
|
||||
def fn_recursive_set_mem_eff(module: torch.nn.Module):
|
||||
if hasattr(module, "set_use_memory_efficient_attention_xformers"):
|
||||
module.set_use_memory_efficient_attention_xformers(valid)
|
||||
|
||||
# epoch数を計算する
|
||||
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
|
||||
num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
|
||||
if (args.save_n_epoch_ratio is not None) and (args.save_n_epoch_ratio > 0):
|
||||
args.save_every_n_epochs = math.floor(num_train_epochs / args.save_n_epoch_ratio) or 1
|
||||
for child in module.children():
|
||||
fn_recursive_set_mem_eff(child)
|
||||
|
||||
# 学習する
|
||||
total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
|
||||
print("running training / 学習開始")
|
||||
print(f" num examples / サンプル数: {train_dataset_group.num_train_images}")
|
||||
print(f" num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
|
||||
print(f" num epochs / epoch数: {num_train_epochs}")
|
||||
print(f" batch size per device / バッチサイズ: {args.train_batch_size}")
|
||||
print(f" total train batch size (with parallel & distributed & accumulation) / 総バッチサイズ（並列学習、勾配合計含む）: {total_batch_size}")
|
||||
print(f" gradient ccumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
|
||||
print(f" total optimization steps / 学習ステップ数: {args.max_train_steps}")
|
||||
fn_recursive_set_mem_eff(model)
|
||||
|
||||
progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
|
||||
global_step = 0
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
if args.diffusers_xformers:
|
||||
print("Use xformers by Diffusers")
|
||||
set_diffusers_xformers_flag(unet, True)
|
||||
else:
|
||||
# Windows版のxformersはfloatで学習できないのでxformersを使わない設定も可能にしておく必要がある
|
||||
print("Disable Diffusers' xformers")
|
||||
set_diffusers_xformers_flag(unet, False)
|
||||
train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers)
|
||||
|
||||
noise_scheduler = DDPMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear",
|
||||
num_train_timesteps=1000, clip_sample=False)
|
||||
# 学習を準備する
|
||||
if cache_latents:
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
with torch.no_grad():
|
||||
train_dataset_group.cache_latents(vae)
|
||||
vae.to("cpu")
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
gc.collect()
|
||||
|
||||
if accelerator.is_main_process:
|
||||
accelerator.init_trackers("finetuning")
|
||||
# 学習を準備する：モデルを適切な状態にする
|
||||
training_models = []
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
training_models.append(unet)
|
||||
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
if args.train_text_encoder:
|
||||
print("enable text encoder training")
|
||||
if args.gradient_checkpointing:
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
training_models.append(text_encoder)
|
||||
else:
|
||||
text_encoder.to(accelerator.device, dtype=weight_dtype)
|
||||
text_encoder.requires_grad_(False) # text encoderは学習しない
|
||||
if args.gradient_checkpointing:
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
text_encoder.train() # required for gradient_checkpointing
|
||||
else:
|
||||
text_encoder.eval()
|
||||
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
|
||||
for m in training_models:
|
||||
m.train()
|
||||
m.requires_grad_(True)
|
||||
params = []
|
||||
for m in training_models:
|
||||
params.extend(m.parameters())
|
||||
params_to_optimize = params
|
||||
|
||||
loss_total = 0
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
with accelerator.accumulate(training_models[0]): # 複数モデルに対応していない模様だがとりあえずこうしておく
|
||||
with torch.no_grad():
|
||||
if "latents" in batch and batch["latents"] is not None:
|
||||
latents = batch["latents"].to(accelerator.device)
|
||||
else:
|
||||
# latentに変換
|
||||
latents = vae.encode(batch["images"].to(dtype=weight_dtype)).latent_dist.sample()
|
||||
latents = latents * 0.18215
|
||||
b_size = latents.shape[0]
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params=params_to_optimize)
|
||||
|
||||
with torch.set_grad_enabled(args.train_text_encoder):
|
||||
# Get the text embedding for conditioning
|
||||
input_ids = batch["input_ids"].to(accelerator.device)
|
||||
encoder_hidden_states = train_util.get_hidden_states(
|
||||
args, input_ids, tokenizer, text_encoder, None if not args.full_fp16 else weight_dtype)
|
||||
# dataloaderを準備する
|
||||
# DataLoaderのプロセス数：0はメインプロセスになる
|
||||
n_workers = min(args.max_data_loader_n_workers, os.cpu_count() - 1) # cpu_count-1 ただし最大で指定された数まで
|
||||
train_dataloader = torch.utils.data.DataLoader(
|
||||
train_dataset_group,
|
||||
batch_size=1,
|
||||
shuffle=True,
|
||||
collate_fn=collate_fn,
|
||||
num_workers=n_workers,
|
||||
persistent_workers=args.persistent_data_loader_workers,
|
||||
)
|
||||
|
||||
# Sample noise that we'll add to the latents
|
||||
noise = torch.randn_like(latents, device=latents.device)
|
||||
if args.noise_offset:
|
||||
# https://www.crosslabs.org//blog/diffusion-with-offset-noise
|
||||
noise += args.noise_offset * torch.randn((latents.shape[0], latents.shape[1], 1, 1), device=latents.device)
|
||||
# 学習ステップ数を計算する
|
||||
if args.max_train_epochs is not None:
|
||||
args.max_train_steps = args.max_train_epochs * len(train_dataloader)
|
||||
print(f"override steps. steps for {args.max_train_epochs} epochs is / 指定エポックまでのステップ数: {args.max_train_steps}")
|
||||
|
||||
# Sample a random timestep for each image
|
||||
timesteps = torch.randint(0, noise_scheduler.config.num_train_timesteps, (b_size,), device=latents.device)
|
||||
timesteps = timesteps.long()
|
||||
# lr schedulerを用意する
|
||||
lr_scheduler = train_util.get_scheduler_fix(
|
||||
args.lr_scheduler,
|
||||
optimizer,
|
||||
num_warmup_steps=args.lr_warmup_steps,
|
||||
num_training_steps=args.max_train_steps * args.gradient_accumulation_steps,
|
||||
num_cycles=args.lr_scheduler_num_cycles,
|
||||
power=args.lr_scheduler_power,
|
||||
)
|
||||
|
||||
# Add noise to the latents according to the noise magnitude at each timestep
|
||||
# (this is the forward diffusion process)
|
||||
noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
|
||||
# 実験的機能：勾配も含めたfp16学習を行う モデル全体をfp16にする
|
||||
if args.full_fp16:
|
||||
assert (
|
||||
args.mixed_precision == "fp16"
|
||||
), "full_fp16 requires mixed precision='fp16' / full_fp16を使う場合はmixed_precision='fp16'を指定してください。"
|
||||
print("enable full fp16 training.")
|
||||
unet.to(weight_dtype)
|
||||
text_encoder.to(weight_dtype)
|
||||
|
||||
# Predict the noise residual
|
||||
noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
if args.train_text_encoder:
|
||||
unet, text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
|
||||
unet, text_encoder, optimizer, train_dataloader, lr_scheduler
|
||||
)
|
||||
else:
|
||||
unet, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(unet, optimizer, train_dataloader, lr_scheduler)
|
||||
|
||||
if args.v_parameterization:
|
||||
# v-parameterization training
|
||||
target = noise_scheduler.get_velocity(latents, noise, timesteps)
|
||||
# 実験的機能：勾配も含めたfp16学習を行う PyTorchにパッチを当ててfp16でのgrad scaleを有効にする
|
||||
if args.full_fp16:
|
||||
train_util.patch_accelerator_for_fp16_training(accelerator)
|
||||
|
||||
# resumeする
|
||||
if args.resume is not None:
|
||||
print(f"resume training from state: {args.resume}")
|
||||
accelerator.load_state(args.resume)
|
||||
|
||||
# epoch数を計算する
|
||||
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
|
||||
num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
|
||||
if (args.save_n_epoch_ratio is not None) and (args.save_n_epoch_ratio > 0):
|
||||
args.save_every_n_epochs = math.floor(num_train_epochs / args.save_n_epoch_ratio) or 1
|
||||
|
||||
# 学習する
|
||||
total_batch_size = args.train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
|
||||
print("running training / 学習開始")
|
||||
print(f" num examples / サンプル数: {train_dataset_group.num_train_images}")
|
||||
print(f" num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
|
||||
print(f" num epochs / epoch数: {num_train_epochs}")
|
||||
print(f" batch size per device / バッチサイズ: {args.train_batch_size}")
|
||||
print(f" total train batch size (with parallel & distributed & accumulation) / 総バッチサイズ（並列学習、勾配合計含む）: {total_batch_size}")
|
||||
print(f" gradient ccumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
|
||||
print(f" total optimization steps / 学習ステップ数: {args.max_train_steps}")
|
||||
|
||||
progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
|
||||
global_step = 0
|
||||
|
||||
noise_scheduler = DDPMScheduler(
|
||||
beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
|
||||
)
|
||||
|
||||
if accelerator.is_main_process:
|
||||
accelerator.init_trackers("finetuning")
|
||||
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
for m in training_models:
|
||||
m.train()
|
||||
|
||||
loss_total = 0
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
with accelerator.accumulate(training_models[0]): # 複数モデルに対応していない模様だがとりあえずこうしておく
|
||||
with torch.no_grad():
|
||||
if "latents" in batch and batch["latents"] is not None:
|
||||
latents = batch["latents"].to(accelerator.device)
|
||||
else:
|
||||
# latentに変換
|
||||
latents = vae.encode(batch["images"].to(dtype=weight_dtype)).latent_dist.sample()
|
||||
latents = latents * 0.18215
|
||||
b_size = latents.shape[0]
|
||||
|
||||
with torch.set_grad_enabled(args.train_text_encoder):
|
||||
# Get the text embedding for conditioning
|
||||
input_ids = batch["input_ids"].to(accelerator.device)
|
||||
encoder_hidden_states = train_util.get_hidden_states(
|
||||
args, input_ids, tokenizer, text_encoder, None if not args.full_fp16 else weight_dtype
|
||||
)
|
||||
|
||||
# Sample noise that we'll add to the latents
|
||||
noise = torch.randn_like(latents, device=latents.device)
|
||||
if args.noise_offset:
|
||||
# https://www.crosslabs.org//blog/diffusion-with-offset-noise
|
||||
noise += args.noise_offset * torch.randn((latents.shape[0], latents.shape[1], 1, 1), device=latents.device)
|
||||
|
||||
# Sample a random timestep for each image
|
||||
timesteps = torch.randint(0, noise_scheduler.config.num_train_timesteps, (b_size,), device=latents.device)
|
||||
timesteps = timesteps.long()
|
||||
|
||||
# Add noise to the latents according to the noise magnitude at each timestep
|
||||
# (this is the forward diffusion process)
|
||||
noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
|
||||
|
||||
# Predict the noise residual
|
||||
noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
|
||||
|
||||
if args.v_parameterization:
|
||||
# v-parameterization training
|
||||
target = noise_scheduler.get_velocity(latents, noise, timesteps)
|
||||
else:
|
||||
target = noise
|
||||
|
||||
loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="mean")
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
params_to_clip = []
|
||||
for m in training_models:
|
||||
params_to_clip.extend(m.parameters())
|
||||
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
|
||||
# Checks if the accelerator has performed an optimization step behind the scenes
|
||||
if accelerator.sync_gradients:
|
||||
progress_bar.update(1)
|
||||
global_step += 1
|
||||
|
||||
train_util.sample_images(
|
||||
accelerator, args, None, global_step, accelerator.device, vae, tokenizer, text_encoder, unet
|
||||
)
|
||||
|
||||
current_loss = loss.detach().item() # 平均なのでbatch sizeは関係ないはず
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss": current_loss, "lr": float(lr_scheduler.get_last_lr()[0])}
|
||||
if args.optimizer_type.lower() == "DAdaptation".lower(): # tracking d*lr value
|
||||
logs["lr/d*lr"] = (
|
||||
lr_scheduler.optimizers[0].param_groups[0]["d"] * lr_scheduler.optimizers[0].param_groups[0]["lr"]
|
||||
)
|
||||
accelerator.log(logs, step=global_step)
|
||||
|
||||
# TODO moving averageにする
|
||||
loss_total += current_loss
|
||||
avr_loss = loss_total / (step + 1)
|
||||
logs = {"loss": avr_loss} # , "lr": lr_scheduler.get_last_lr()[0]}
|
||||
progress_bar.set_postfix(**logs)
|
||||
|
||||
if global_step >= args.max_train_steps:
|
||||
break
|
||||
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss/epoch": loss_total / len(train_dataloader)}
|
||||
accelerator.log(logs, step=epoch + 1)
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
|
||||
if args.save_every_n_epochs is not None:
|
||||
src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
|
||||
train_util.save_sd_model_on_epoch_end(
|
||||
args,
|
||||
accelerator,
|
||||
src_path,
|
||||
save_stable_diffusion_format,
|
||||
use_safetensors,
|
||||
save_dtype,
|
||||
epoch,
|
||||
num_train_epochs,
|
||||
global_step,
|
||||
unwrap_model(text_encoder),
|
||||
unwrap_model(unet),
|
||||
vae,
|
||||
)
|
||||
|
||||
train_util.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
|
||||
is_main_process = accelerator.is_main_process
|
||||
if is_main_process:
|
||||
unet = unwrap_model(unet)
|
||||
text_encoder = unwrap_model(text_encoder)
|
||||
|
||||
accelerator.end_training()
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
|
||||
if is_main_process:
|
||||
src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
|
||||
train_util.save_sd_model_on_train_end(
|
||||
args, src_path, save_stable_diffusion_format, use_safetensors, save_dtype, epoch, global_step, text_encoder, unet, vae
|
||||
)
|
||||
print("model saved.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, False, True, True)
|
||||
train_util.add_training_arguments(parser, False)
|
||||
train_util.add_sd_saving_arguments(parser)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
|
||||
parser.add_argument("--diffusers_xformers", action="store_true", help="use xformers by diffusers / Diffusersでxformersを使用する")
|
||||
parser.add_argument("--train_text_encoder", action="store_true", help="train text encoder / text encoderも学習する")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.config_file:
|
||||
config_path = args.config_file + ".toml" if not args.config_file.endswith(".toml") else args.config_file
|
||||
if os.path.exists(config_path):
|
||||
print(f"Loading settings from {config_path}...")
|
||||
with open(config_path, "r") as f:
|
||||
config_dict = toml.load(f)
|
||||
|
||||
ignore_nesting_dict = {}
|
||||
for section_name, section_dict in config_dict.items():
|
||||
for key, value in section_dict.items():
|
||||
ignore_nesting_dict[key] = value
|
||||
|
||||
config_args = argparse.Namespace(**ignore_nesting_dict)
|
||||
args = parser.parse_args(namespace=config_args)
|
||||
args.config_file = args.config_file.split(".")[0]
|
||||
print(args.config_file)
|
||||
else:
|
||||
target = noise
|
||||
print(f"{config_path} not found.")
|
||||
|
||||
loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="mean")
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
params_to_clip = []
|
||||
for m in training_models:
|
||||
params_to_clip.extend(m.parameters())
|
||||
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
|
||||
# Checks if the accelerator has performed an optimization step behind the scenes
|
||||
if accelerator.sync_gradients:
|
||||
progress_bar.update(1)
|
||||
global_step += 1
|
||||
|
||||
train_util.sample_images(accelerator, args, None, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
|
||||
current_loss = loss.detach().item() # 平均なのでbatch sizeは関係ないはず
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss": current_loss, "lr": float(lr_scheduler.get_last_lr()[0])}
|
||||
if args.optimizer_type.lower() == "DAdaptation".lower(): # tracking d*lr value
|
||||
logs["lr/d*lr"] = lr_scheduler.optimizers[0].param_groups[0]['d']*lr_scheduler.optimizers[0].param_groups[0]['lr']
|
||||
accelerator.log(logs, step=global_step)
|
||||
|
||||
# TODO moving averageにする
|
||||
loss_total += current_loss
|
||||
avr_loss = loss_total / (step+1)
|
||||
logs = {"loss": avr_loss} # , "lr": lr_scheduler.get_last_lr()[0]}
|
||||
progress_bar.set_postfix(**logs)
|
||||
|
||||
if global_step >= args.max_train_steps:
|
||||
break
|
||||
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss/epoch": loss_total / len(train_dataloader)}
|
||||
accelerator.log(logs, step=epoch+1)
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
|
||||
if args.save_every_n_epochs is not None:
|
||||
src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
|
||||
train_util.save_sd_model_on_epoch_end(args, accelerator, src_path, save_stable_diffusion_format, use_safetensors,
|
||||
save_dtype, epoch, num_train_epochs, global_step, unwrap_model(text_encoder), unwrap_model(unet), vae)
|
||||
|
||||
train_util.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
|
||||
is_main_process = accelerator.is_main_process
|
||||
if is_main_process:
|
||||
unet = unwrap_model(unet)
|
||||
text_encoder = unwrap_model(text_encoder)
|
||||
|
||||
accelerator.end_training()
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
|
||||
if is_main_process:
|
||||
src_path = src_stable_diffusion_ckpt if save_stable_diffusion_format else src_diffusers_model_path
|
||||
train_util.save_sd_model_on_train_end(args, src_path, save_stable_diffusion_format, use_safetensors,
|
||||
save_dtype, epoch, global_step, text_encoder, unet, vae)
|
||||
print("model saved.")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, False, True, True)
|
||||
train_util.add_training_arguments(parser, False)
|
||||
train_util.add_sd_saving_arguments(parser)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
|
||||
parser.add_argument("--diffusers_xformers", action='store_true',
|
||||
help='use xformers by diffusers / Diffusersでxformersを使用する')
|
||||
parser.add_argument("--train_text_encoder", action="store_true", help="train text encoder / text encoderも学習する")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.config_file:
|
||||
config_path = args.config_file + ".toml" if not args.config_file.endswith(".toml") else args.config_file
|
||||
if os.path.exists(config_path):
|
||||
print(f"Loading settings from {config_path}...")
|
||||
with open(config_path, "r") as f:
|
||||
config_dict = toml.load(f)
|
||||
|
||||
ignore_nesting_dict = {}
|
||||
for section_name, section_dict in config_dict.items():
|
||||
for key, value in section_dict.items():
|
||||
ignore_nesting_dict[key] = value
|
||||
|
||||
config_args = argparse.Namespace(**ignore_nesting_dict)
|
||||
args = parser.parse_args(namespace=config_args)
|
||||
args.config_file = args.config_file.split(".")[0]
|
||||
print(args.config_file)
|
||||
else:
|
||||
print(f"{config_path} not found.")
|
||||
|
||||
train(args)
|
||||
train(args)
|
||||
|
||||
Reference in New Issue
Block a user