mirror of
https://github.com/kohya-ss/sd-scripts.git
synced 2026-04-06 13:47:06 +00:00
Merge pull request #305 from kohya-ss/dev
config file, lr scheduler, weighted prompt for sample gen etc.
This commit is contained in:
Kohya S
GitHub
76
README.md
76
README.md
@@ -127,60 +127,36 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
|
||||
|
||||
## Change History
|
||||
|
||||
|
||||
- 19 Mar. 2023, 2023/3/19:
|
||||
- Add a function to load training config with `.toml` to each training script. Thanks to Linaqruf for this great contribution!
|
||||
- Specify `.toml` file with `--config_file`. `.toml` file has `key=value` entries. Keys are same as command line options. See [#241](https://github.com/kohya-ss/sd-scripts/pull/241) for details.
|
||||
- All sub-sections are combined to a single dictionary (the section names are ignored.)
|
||||
- Omitted arguments are the default values for command line arguments.
|
||||
- Command line args override the arguments in `.toml`.
|
||||
- With `--output_config` option, you can output current command line options to the `.toml` specified with`--config_file`. Please use as a template.
|
||||
- Add `--lr_scheduler_type` and `--lr_scheduler_args` arguments for custom LR scheduler to each training script. Thanks to Isotr0py! [#271](https://github.com/kohya-ss/sd-scripts/pull/271)
|
||||
- Same as the optimizer.
|
||||
- Add sample image generation with weight and no length limit. Thanks to mio2333! [#288](https://github.com/kohya-ss/sd-scripts/pull/288)
|
||||
- `( )`, `(xxxx:1.2)` and `[ ]` can be used.
|
||||
- Fix exception on training model in diffusers format with `train_network.py` Thanks to orenwang! [#290](https://github.com/kohya-ss/sd-scripts/pull/290)
|
||||
|
||||
- 各学習スクリプトでコマンドライン引数の代わりに`.toml` ファイルで引数を指定できるようになりました。Linaqrufの多大な貢献に感謝します。
|
||||
- `--config_file` で `.toml` ファイルを指定してください。ファイルは `key=value` 形式の行で指定し、key はコマンドラインオプションと同じです。詳細は [#241](https://github.com/kohya-ss/sd-scripts/pull/241) をご覧ください。
|
||||
- ファイル内のサブセクションはすべて無視されます。
|
||||
- 省略した引数はコマンドライン引数のデフォルト値になります。
|
||||
- コマンドライン引数で `.toml` の設定を上書きできます。
|
||||
- `--output_config` オプションを指定すると、現在のコマンドライン引数を`--config_file` オプションで指定した `.toml` ファイルに出力します。ひな形としてご利用ください。
|
||||
- 任意のスケジューラを使うための `--lr_scheduler_type` と `--lr_scheduler_args` オプションを各学習スクリプトに追加しました。Isotr0py氏に感謝します。 [#271](https://github.com/kohya-ss/sd-scripts/pull/271)
|
||||
- 任意のオプティマイザ指定と同じ形式です。
|
||||
- 学習中のサンプル画像出力でプロンプトの重みづけができるようになりました。また長さ制限も緩和されています。mio2333氏に感謝します。 [#288](https://github.com/kohya-ss/sd-scripts/pull/288)
|
||||
- `( )`、 `(xxxx:1.2)` や `[ ]` が使えます。
|
||||
- `train_network.py` でローカルのDiffusersモデルを指定した時のエラーを修正しました。orenwang氏に感謝します。 [#290](https://github.com/kohya-ss/sd-scripts/pull/290)
|
||||
|
||||
- 11 Mar. 2023, 2023/3/11:
|
||||
- Fix `svd_merge_lora.py` causes an error about the device.
|
||||
- `svd_merge_lora.py` でデバイス関連のエラーが発生する不具合を修正しました。
|
||||
- 10 Mar. 2023, 2023/3/10: release v0.5.1
|
||||
- Fix to LoRA modules in the model are same to the previous (before 0.5.0) if Conv2d-3x3 is disabled (no `conv_dim` arg, default).
|
||||
- Conv2D with kernel size 1x1 in ResNet modules were accidentally included in v0.5.0.
|
||||
- Trained models with v0.5.0 will work with Web UI's built-in LoRA and Additional Networks extension.
|
||||
- Fix an issue that dim (rank) of LoRA module is limited to the in/out dimensions of the target Linear/Conv2d (in case of the dim > 320).
|
||||
- `resize_lora.py` now have a feature to `dynamic resizing` which means each LoRA module can have different ranks (dims). Thanks to mgz-dev for this great work!
|
||||
- The appropriate rank is selected based on the complexity of each module with an algorithm specified in the command line arguments. For details: https://github.com/kohya-ss/sd-scripts/pull/243
|
||||
- Multiple GPUs training is finally supported in `train_network.py`. Thanks to ddPn08 to solve this long running issue!
|
||||
- Dataset with fine-tuning method (with metadata json) now works without images if `.npz` files exist. Thanks to rvhfxb!
|
||||
- `train_network.py` can work if the current directory is not the directory where the script is in. Thanks to mio2333!
|
||||
- Fix `extract_lora_from_models.py` and `svd_merge_lora.py` doesn't work with higher rank (>320).
|
||||
|
||||
- LoRAのConv2d-3x3拡張を行わない場合（`conv_dim` を指定しない場合）、以前（v0.5.0）と同じ構成になるよう修正しました。
|
||||
- ResNetのカーネルサイズ1x1のConv2dが誤って対象になっていました。
|
||||
- ただv0.5.0で学習したモデルは Additional Networks 拡張、およびWeb UIのLoRA機能で問題なく使えると思われます。
|
||||
- LoRAモジュールの dim (rank) が、対象モジュールの次元数以下に制限される不具合を修正しました（320より大きい dim を指定した場合）。
|
||||
- `resize_lora.py` に `dynamic resizing` （リサイズ後の各LoRAモジュールが異なるrank (dim) を持てる機能）を追加しました。mgz-dev 氏の貢献に感謝します。
|
||||
- 適切なランクがコマンドライン引数で指定したアルゴリズムにより自動的に選択されます。詳細はこちらをご覧ください: https://github.com/kohya-ss/sd-scripts/pull/243
|
||||
- `train_network.py` でマルチGPU学習をサポートしました。長年の懸案を解決された ddPn08 氏に感謝します。
|
||||
- fine-tuning方式のデータセット（メタデータ.jsonファイルを使うデータセット）で `.npz` が存在するときには画像がなくても動作するようになりました。rvhfxb 氏に感謝します。
|
||||
- 他のディレクトリから `train_network.py` を呼び出しても動作するよう変更しました。 mio2333 氏に感謝します。
|
||||
- `extract_lora_from_models.py` および `svd_merge_lora.py` が320より大きいrankを指定すると動かない不具合を修正しました。
|
||||
|
||||
- 9 Mar. 2023, 2023/3/9: release v0.5.0
|
||||
- There may be problems due to major changes. If you cannot revert back to the previous version when problems occur, please do not update for a while.
|
||||
- Minimum metadata (module name, dim, alpha and network_args) is recorded even with `--no_metadata`, issue https://github.com/kohya-ss/sd-scripts/issues/254
|
||||
- `train_network.py` supports LoRA for Conv2d-3x3 (extended to conv2d with a kernel size not 1x1).
|
||||
- Same as a current version of [LoCon](https://github.com/KohakuBlueleaf/LoCon). __Thank you very much KohakuBlueleaf for your help!__
|
||||
- LoCon will be enhanced in the future. Compatibility for future versions is not guaranteed.
|
||||
- Specify `--network_args` option like: `--network_args "conv_dim=4" "conv_alpha=1"`
|
||||
- [Additional Networks extension](https://github.com/kohya-ss/sd-webui-additional-networks) version 0.5.0 or later is required to use 'LoRA for Conv2d-3x3' in Stable Diffusion web UI.
|
||||
- __Stable Diffusion web UI built-in LoRA does not support 'LoRA for Conv2d-3x3' now. Consider carefully whether or not to use it.__
|
||||
- Merging/extracting scripts also support LoRA for Conv2d-3x3.
|
||||
- Free CUDA memory after sample generation to reduce VRAM usage, issue https://github.com/kohya-ss/sd-scripts/issues/260
|
||||
- Empty caption doesn't cause error now, issue https://github.com/kohya-ss/sd-scripts/issues/258
|
||||
- Fix sample generation is crashing in Textual Inversion training when using templates, or if height/width is not divisible by 8.
|
||||
- Update documents (Japanese only).
|
||||
|
||||
- 大きく変更したため不具合があるかもしれません。問題が起きた時にスクリプトを前のバージョンに戻せない場合は、しばらく更新を控えてください。
|
||||
- 最低限のメタデータ（module name, dim, alpha および network_args）が `--no_metadata` オプション指定時にも記録されます。issue https://github.com/kohya-ss/sd-scripts/issues/254
|
||||
- `train_network.py` で LoRAの Conv2d-3x3 拡張に対応しました（カーネルサイズ1x1以外のConv2dにも対象範囲を拡大します）。
|
||||
- 現在のバージョンの [LoCon](https://github.com/KohakuBlueleaf/LoCon) と同一の仕様です。__KohakuBlueleaf氏のご支援に深く感謝します。__
|
||||
- LoCon が将来的に拡張された場合、それらのバージョンでの互換性は保証できません。
|
||||
- `--network_args` オプションを `--network_args "conv_dim=4" "conv_alpha=1"` のように指定してください。
|
||||
- Stable Diffusion web UI での使用には [Additional Networks extension](https://github.com/kohya-ss/sd-webui-additional-networks) のversion 0.5.0 以降が必要です。
|
||||
- __Stable Diffusion web UI の LoRA 機能は LoRAの Conv2d-3x3 拡張に対応していないようです。使用するか否か慎重にご検討ください。__
|
||||
- マージ、抽出のスクリプトについても LoRA の Conv2d-3x3 拡張に対応しました.
|
||||
- サンプル画像生成後にCUDAメモリを解放しVRAM使用量を削減しました。 issue https://github.com/kohya-ss/sd-scripts/issues/260
|
||||
- 空のキャプションが使えるようになりました。 issue https://github.com/kohya-ss/sd-scripts/issues/258
|
||||
- Textual Inversion 学習でテンプレートを使ったとき、height/width が 8 で割り切れなかったときにサンプル画像生成がクラッシュするのを修正しました。
|
||||
- ドキュメント類を更新しました。
|
||||
|
||||
- Sample image generation:
|
||||
A prompt file might look like this, for example
|
||||
|
||||
623
fine_tune.py
623
fine_tune.py
@@ -5,6 +5,7 @@ import argparse
|
||||
import gc
|
||||
import math
|
||||
import os
|
||||
import toml
|
||||
|
||||
from tqdm import tqdm
|
||||
import torch
|
||||
@@ -15,351 +16,391 @@ 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, optimizer, accelerator.num_processes)
|
||||
|
||||
# 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)
|
||||
else:
|
||||
target = noise
|
||||
# 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)
|
||||
|
||||
loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="mean")
|
||||
# resumeする
|
||||
if args.resume is not None:
|
||||
print(f"resume training from state: {args.resume}")
|
||||
accelerator.load_state(args.resume)
|
||||
|
||||
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)
|
||||
# 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
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
# 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}")
|
||||
|
||||
# Checks if the accelerator has performed an optimization step behind the scenes
|
||||
if accelerator.sync_gradients:
|
||||
progress_bar.update(1)
|
||||
global_step += 1
|
||||
progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
|
||||
global_step = 0
|
||||
|
||||
train_util.sample_images(accelerator, args, None, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
noise_scheduler = DDPMScheduler(
|
||||
beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
|
||||
)
|
||||
|
||||
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)
|
||||
if accelerator.is_main_process:
|
||||
accelerator.init_trackers("finetuning")
|
||||
|
||||
# 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)
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
if global_step >= args.max_train_steps:
|
||||
break
|
||||
for m in training_models:
|
||||
m.train()
|
||||
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss/epoch": loss_total / len(train_dataloader)}
|
||||
accelerator.log(logs, step=epoch+1)
|
||||
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]
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
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
|
||||
)
|
||||
|
||||
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)
|
||||
# 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)
|
||||
|
||||
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)
|
||||
# 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()
|
||||
|
||||
accelerator.end_training()
|
||||
# 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)
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
# Predict the noise residual
|
||||
noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
if args.v_parameterization:
|
||||
# v-parameterization training
|
||||
target = noise_scheduler.get_velocity(latents, noise, timesteps)
|
||||
else:
|
||||
target = noise
|
||||
|
||||
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.")
|
||||
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()
|
||||
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)
|
||||
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")
|
||||
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()
|
||||
train(args)
|
||||
args = parser.parse_args()
|
||||
args = train_util.read_config_from_file(args, parser)
|
||||
|
||||
train(args)
|
||||
|
||||
@@ -4,7 +4,7 @@ from pathlib import Path
|
||||
from typing import List
|
||||
from tqdm import tqdm
|
||||
import library.train_util as train_util
|
||||
|
||||
import os
|
||||
|
||||
def main(args):
|
||||
assert not args.recursive or (args.recursive and args.full_path), "recursive requires full_path / recursiveはfull_pathと同時に指定してください"
|
||||
@@ -29,6 +29,9 @@ def main(args):
|
||||
caption_path = image_path.with_suffix(args.caption_extension)
|
||||
caption = caption_path.read_text(encoding='utf-8').strip()
|
||||
|
||||
if not os.path.exists(caption_path):
|
||||
caption_path = os.path.join(image_path, args.caption_extension)
|
||||
|
||||
image_key = str(image_path) if args.full_path else image_path.stem
|
||||
if image_key not in metadata:
|
||||
metadata[image_key] = {}
|
||||
|
||||
@@ -4,7 +4,7 @@ from pathlib import Path
|
||||
from typing import List
|
||||
from tqdm import tqdm
|
||||
import library.train_util as train_util
|
||||
|
||||
import os
|
||||
|
||||
def main(args):
|
||||
assert not args.recursive or (args.recursive and args.full_path), "recursive requires full_path / recursiveはfull_pathと同時に指定してください"
|
||||
@@ -29,6 +29,9 @@ def main(args):
|
||||
tags_path = image_path.with_suffix(args.caption_extension)
|
||||
tags = tags_path.read_text(encoding='utf-8').strip()
|
||||
|
||||
if not os.path.exists(tags_path):
|
||||
tags_path = os.path.join(image_path, args.caption_extension)
|
||||
|
||||
image_key = str(image_path) if args.full_path else image_path.stem
|
||||
if image_key not in metadata:
|
||||
metadata[image_key] = {}
|
||||
|
||||
1179
library/lpw_stable_diffusion.py
Normal file
1179
library/lpw_stable_diffusion.py
Normal file
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
625
train_db.py
625
train_db.py
@@ -7,6 +7,7 @@ import argparse
|
||||
import itertools
|
||||
import math
|
||||
import os
|
||||
import toml
|
||||
|
||||
from tqdm import tqdm
|
||||
import torch
|
||||
@@ -17,348 +18,392 @@ 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, False)
|
||||
train_util.verify_training_args(args)
|
||||
train_util.prepare_dataset_args(args, False)
|
||||
|
||||
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(True, False, 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", "reg_data_dir"]
|
||||
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": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)
|
||||
}]
|
||||
}
|
||||
blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, False, 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", "reg_data_dir"]
|
||||
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": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)}
|
||||
]
|
||||
}
|
||||
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
|
||||
if args.no_token_padding:
|
||||
train_dataset_group.disable_token_padding()
|
||||
if args.no_token_padding:
|
||||
train_dataset_group.disable_token_padding()
|
||||
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group)
|
||||
return
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group)
|
||||
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"
|
||||
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を準備する
|
||||
print("prepare accelerator")
|
||||
|
||||
if args.gradient_accumulation_steps > 1:
|
||||
print(f"gradient_accumulation_steps is {args.gradient_accumulation_steps}. accelerate does not support gradient_accumulation_steps when training multiple models (U-Net and Text Encoder), so something might be wrong")
|
||||
print(
|
||||
f"gradient_accumulation_stepsが{args.gradient_accumulation_steps}に設定されています。accelerateは複数モデル（U-NetおよびText Encoder）の学習時にgradient_accumulation_stepsをサポートしていないため結果は未知数です")
|
||||
if args.gradient_accumulation_steps > 1:
|
||||
print(
|
||||
f"gradient_accumulation_steps is {args.gradient_accumulation_steps}. accelerate does not support gradient_accumulation_steps when training multiple models (U-Net and Text Encoder), so something might be wrong"
|
||||
)
|
||||
print(
|
||||
f"gradient_accumulation_stepsが{args.gradient_accumulation_steps}に設定されています。accelerateは複数モデル（U-NetおよびText Encoder）の学習時にgradient_accumulation_stepsをサポートしていないため結果は未知数です"
|
||||
)
|
||||
|
||||
accelerator, unwrap_model = train_util.prepare_accelerator(args)
|
||||
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)
|
||||
# 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)
|
||||
# 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
|
||||
# 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())
|
||||
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())
|
||||
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xformers)
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
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
|
||||
train_text_encoder = args.stop_text_encoder_training is None or args.stop_text_encoder_training >= 0
|
||||
unet.requires_grad_(True) # 念のため追加
|
||||
text_encoder.requires_grad_(train_text_encoder)
|
||||
if not train_text_encoder:
|
||||
print("Text Encoder is not trained.")
|
||||
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
if train_text_encoder:
|
||||
trainable_params = (itertools.chain(unet.parameters(), text_encoder.parameters()))
|
||||
else:
|
||||
trainable_params = unet.parameters()
|
||||
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params)
|
||||
|
||||
# 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)
|
||||
|
||||
# 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}")
|
||||
|
||||
if args.stop_text_encoder_training is None:
|
||||
args.stop_text_encoder_training = args.max_train_steps + 1 # do not stop until end
|
||||
|
||||
# lr schedulerを用意する TODO gradient_accumulation_stepsの扱いが何かおかしいかもしれない。後で確認する
|
||||
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,
|
||||
num_cycles=args.lr_scheduler_num_cycles, power=args.lr_scheduler_power)
|
||||
|
||||
# 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)
|
||||
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
if 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 not train_text_encoder:
|
||||
text_encoder.to(accelerator.device, dtype=weight_dtype) # to avoid 'cpu' vs 'cuda' error
|
||||
|
||||
# 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 train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
|
||||
print(f" num reg images / 正則化画像の数: {train_dataset_group.num_reg_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("dreambooth")
|
||||
|
||||
loss_list = []
|
||||
loss_total = 0.0
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
# 指定したステップ数までText Encoderを学習する：epoch最初の状態
|
||||
unet.train()
|
||||
# train==True is required to enable gradient_checkpointing
|
||||
if args.gradient_checkpointing or global_step < args.stop_text_encoder_training:
|
||||
text_encoder.train()
|
||||
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
# 指定したステップ数でText Encoderの学習を止める
|
||||
if global_step == args.stop_text_encoder_training:
|
||||
print(f"stop text encoder training at step {global_step}")
|
||||
if not args.gradient_checkpointing:
|
||||
text_encoder.train(False)
|
||||
text_encoder.requires_grad_(False)
|
||||
|
||||
with accelerator.accumulate(unet):
|
||||
# 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():
|
||||
# latentに変換
|
||||
if cache_latents:
|
||||
latents = batch["latents"].to(accelerator.device)
|
||||
else:
|
||||
latents = vae.encode(batch["images"].to(dtype=weight_dtype)).latent_dist.sample()
|
||||
latents = latents * 0.18215
|
||||
b_size = latents.shape[0]
|
||||
train_dataset_group.cache_latents(vae)
|
||||
vae.to("cpu")
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
gc.collect()
|
||||
|
||||
# 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)
|
||||
# 学習を準備する：モデルを適切な状態にする
|
||||
train_text_encoder = args.stop_text_encoder_training is None or args.stop_text_encoder_training >= 0
|
||||
unet.requires_grad_(True) # 念のため追加
|
||||
text_encoder.requires_grad_(train_text_encoder)
|
||||
if not train_text_encoder:
|
||||
print("Text Encoder is not trained.")
|
||||
|
||||
# Get the text embedding for conditioning
|
||||
with torch.set_grad_enabled(global_step < args.stop_text_encoder_training):
|
||||
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)
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
|
||||
# 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()
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
|
||||
# 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)
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
if train_text_encoder:
|
||||
trainable_params = itertools.chain(unet.parameters(), text_encoder.parameters())
|
||||
else:
|
||||
trainable_params = unet.parameters()
|
||||
|
||||
# Predict the noise residual
|
||||
noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params)
|
||||
|
||||
if args.v_parameterization:
|
||||
# v-parameterization training
|
||||
target = noise_scheduler.get_velocity(latents, noise, timesteps)
|
||||
else:
|
||||
target = noise
|
||||
# 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,
|
||||
)
|
||||
|
||||
loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="none")
|
||||
loss = loss.mean([1, 2, 3])
|
||||
# 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}")
|
||||
|
||||
loss_weights = batch["loss_weights"] # 各sampleごとのweight
|
||||
loss = loss * loss_weights
|
||||
if args.stop_text_encoder_training is None:
|
||||
args.stop_text_encoder_training = args.max_train_steps + 1 # do not stop until end
|
||||
|
||||
loss = loss.mean() # 平均なのでbatch_sizeで割る必要なし
|
||||
# lr schedulerを用意する TODO gradient_accumulation_stepsの扱いが何かおかしいかもしれない。後で確認する
|
||||
lr_scheduler = train_util.get_scheduler_fix(args, optimizer, accelerator.num_processes)
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
if train_text_encoder:
|
||||
params_to_clip = (itertools.chain(unet.parameters(), text_encoder.parameters()))
|
||||
else:
|
||||
params_to_clip = unet.parameters()
|
||||
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
|
||||
# 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)
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
if 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)
|
||||
|
||||
# Checks if the accelerator has performed an optimization step behind the scenes
|
||||
if accelerator.sync_gradients:
|
||||
progress_bar.update(1)
|
||||
global_step += 1
|
||||
if not train_text_encoder:
|
||||
text_encoder.to(accelerator.device, dtype=weight_dtype) # to avoid 'cpu' vs 'cuda' error
|
||||
|
||||
train_util.sample_images(accelerator, args, None, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
# 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)
|
||||
|
||||
current_loss = loss.detach().item()
|
||||
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)
|
||||
# resumeする
|
||||
if args.resume is not None:
|
||||
print(f"resume training from state: {args.resume}")
|
||||
accelerator.load_state(args.resume)
|
||||
|
||||
if epoch == 0:
|
||||
loss_list.append(current_loss)
|
||||
else:
|
||||
loss_total -= loss_list[step]
|
||||
loss_list[step] = current_loss
|
||||
loss_total += current_loss
|
||||
avr_loss = loss_total / len(loss_list)
|
||||
logs = {"loss": avr_loss} # , "lr": lr_scheduler.get_last_lr()[0]}
|
||||
progress_bar.set_postfix(**logs)
|
||||
# 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
|
||||
|
||||
if global_step >= args.max_train_steps:
|
||||
break
|
||||
# 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 train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
|
||||
print(f" num reg images / 正則化画像の数: {train_dataset_group.num_reg_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}")
|
||||
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss/epoch": loss_total / len(loss_list)}
|
||||
accelerator.log(logs, step=epoch+1)
|
||||
progress_bar = tqdm(range(args.max_train_steps), smoothing=0, disable=not accelerator.is_local_main_process, desc="steps")
|
||||
global_step = 0
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
noise_scheduler = DDPMScheduler(
|
||||
beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
|
||||
)
|
||||
|
||||
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)
|
||||
if accelerator.is_main_process:
|
||||
accelerator.init_trackers("dreambooth")
|
||||
|
||||
train_util.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet)
|
||||
loss_list = []
|
||||
loss_total = 0.0
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
is_main_process = accelerator.is_main_process
|
||||
if is_main_process:
|
||||
unet = unwrap_model(unet)
|
||||
text_encoder = unwrap_model(text_encoder)
|
||||
# 指定したステップ数までText Encoderを学習する：epoch最初の状態
|
||||
unet.train()
|
||||
# train==True is required to enable gradient_checkpointing
|
||||
if args.gradient_checkpointing or global_step < args.stop_text_encoder_training:
|
||||
text_encoder.train()
|
||||
|
||||
accelerator.end_training()
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
# 指定したステップ数でText Encoderの学習を止める
|
||||
if global_step == args.stop_text_encoder_training:
|
||||
print(f"stop text encoder training at step {global_step}")
|
||||
if not args.gradient_checkpointing:
|
||||
text_encoder.train(False)
|
||||
text_encoder.requires_grad_(False)
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
with accelerator.accumulate(unet):
|
||||
with torch.no_grad():
|
||||
# latentに変換
|
||||
if cache_latents:
|
||||
latents = batch["latents"].to(accelerator.device)
|
||||
else:
|
||||
latents = vae.encode(batch["images"].to(dtype=weight_dtype)).latent_dist.sample()
|
||||
latents = latents * 0.18215
|
||||
b_size = latents.shape[0]
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
# 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)
|
||||
|
||||
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.")
|
||||
# Get the text embedding for conditioning
|
||||
with torch.set_grad_enabled(global_step < args.stop_text_encoder_training):
|
||||
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 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="none")
|
||||
loss = loss.mean([1, 2, 3])
|
||||
|
||||
loss_weights = batch["loss_weights"] # 各sampleごとのweight
|
||||
loss = loss * loss_weights
|
||||
|
||||
loss = loss.mean() # 平均なのでbatch_sizeで割る必要なし
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
if train_text_encoder:
|
||||
params_to_clip = itertools.chain(unet.parameters(), text_encoder.parameters())
|
||||
else:
|
||||
params_to_clip = unet.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()
|
||||
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)
|
||||
|
||||
if epoch == 0:
|
||||
loss_list.append(current_loss)
|
||||
else:
|
||||
loss_total -= loss_list[step]
|
||||
loss_list[step] = current_loss
|
||||
loss_total += current_loss
|
||||
avr_loss = loss_total / len(loss_list)
|
||||
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(loss_list)}
|
||||
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()
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, True, False, True)
|
||||
train_util.add_training_arguments(parser, True)
|
||||
train_util.add_sd_saving_arguments(parser)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, True, False, True)
|
||||
train_util.add_training_arguments(parser, True)
|
||||
train_util.add_sd_saving_arguments(parser)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
|
||||
parser.add_argument("--no_token_padding", action="store_true",
|
||||
help="disable token padding (same as Diffuser's DreamBooth) / トークンのpaddingを無効にする（Diffusers版DreamBoothと同じ動作）")
|
||||
parser.add_argument("--stop_text_encoder_training", type=int, default=None,
|
||||
help="steps to stop text encoder training, -1 for no training / Text Encoderの学習を止めるステップ数、-1で最初から学習しない")
|
||||
parser.add_argument(
|
||||
"--no_token_padding",
|
||||
action="store_true",
|
||||
help="disable token padding (same as Diffuser's DreamBooth) / トークンのpaddingを無効にする（Diffusers版DreamBoothと同じ動作）",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--stop_text_encoder_training",
|
||||
type=int,
|
||||
default=None,
|
||||
help="steps to stop text encoder training, -1 for no training / Text Encoderの学習を止めるステップ数、-1で最初から学習しない",
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
train(args)
|
||||
args = parser.parse_args()
|
||||
args = train_util.read_config_from_file(args, parser)
|
||||
|
||||
train(args)
|
||||
|
||||
1186
train_network.py
1186
train_network.py
File diff suppressed because it is too large
Load Diff
@@ -3,6 +3,7 @@ import argparse
|
||||
import gc
|
||||
import math
|
||||
import os
|
||||
import toml
|
||||
|
||||
from tqdm import tqdm
|
||||
import torch
|
||||
@@ -13,8 +14,8 @@ 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,
|
||||
)
|
||||
|
||||
imagenet_templates_small = [
|
||||
@@ -71,456 +72,500 @@ imagenet_style_templates_small = [
|
||||
|
||||
|
||||
def collate_fn(examples):
|
||||
return examples[0]
|
||||
return examples[0]
|
||||
|
||||
|
||||
def train(args):
|
||||
if args.output_name is None:
|
||||
args.output_name = args.token_string
|
||||
use_template = args.use_object_template or args.use_style_template
|
||||
if args.output_name is None:
|
||||
args.output_name = args.token_string
|
||||
use_template = args.use_object_template or args.use_style_template
|
||||
|
||||
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)
|
||||
if args.seed is not None:
|
||||
set_seed(args.seed)
|
||||
|
||||
tokenizer = train_util.load_tokenizer(args)
|
||||
tokenizer = train_util.load_tokenizer(args)
|
||||
|
||||
# acceleratorを準備する
|
||||
print("prepare accelerator")
|
||||
accelerator, unwrap_model = train_util.prepare_accelerator(args)
|
||||
# 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)
|
||||
# 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, _ = train_util.load_target_model(args, weight_dtype)
|
||||
# モデルを読み込む
|
||||
text_encoder, vae, unet, _ = train_util.load_target_model(args, weight_dtype)
|
||||
|
||||
# Convert the init_word to token_id
|
||||
if args.init_word is not None:
|
||||
init_token_ids = tokenizer.encode(args.init_word, add_special_tokens=False)
|
||||
if len(init_token_ids) > 1 and len(init_token_ids) != args.num_vectors_per_token:
|
||||
print(
|
||||
f"token length for init words is not same to num_vectors_per_token, init words is repeated or truncated / 初期化単語のトークン長がnum_vectors_per_tokenと合わないため、繰り返しまたは切り捨てが発生します: length {len(init_token_ids)}")
|
||||
else:
|
||||
init_token_ids = None
|
||||
|
||||
# add new word to tokenizer, count is num_vectors_per_token
|
||||
token_strings = [args.token_string] + [f"{args.token_string}{i+1}" for i in range(args.num_vectors_per_token - 1)]
|
||||
num_added_tokens = tokenizer.add_tokens(token_strings)
|
||||
assert num_added_tokens == args.num_vectors_per_token, f"tokenizer has same word to token string. please use another one / 指定したargs.token_stringは既に存在します。別の単語を使ってください: {args.token_string}"
|
||||
|
||||
token_ids = tokenizer.convert_tokens_to_ids(token_strings)
|
||||
print(f"tokens are added: {token_ids}")
|
||||
assert min(token_ids) == token_ids[0] and token_ids[-1] == token_ids[0] + len(token_ids) - 1, f"token ids is not ordered"
|
||||
assert len(tokenizer) - 1 == token_ids[-1], f"token ids is not end of tokenize: {len(tokenizer)}"
|
||||
|
||||
# Resize the token embeddings as we are adding new special tokens to the tokenizer
|
||||
text_encoder.resize_token_embeddings(len(tokenizer))
|
||||
|
||||
# Initialise the newly added placeholder token with the embeddings of the initializer token
|
||||
token_embeds = text_encoder.get_input_embeddings().weight.data
|
||||
if init_token_ids is not None:
|
||||
for i, token_id in enumerate(token_ids):
|
||||
token_embeds[token_id] = token_embeds[init_token_ids[i % len(init_token_ids)]]
|
||||
# print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
|
||||
|
||||
# load weights
|
||||
if args.weights is not None:
|
||||
embeddings = load_weights(args.weights)
|
||||
assert len(token_ids) == len(
|
||||
embeddings), f"num_vectors_per_token is mismatch for weights / 指定した重みとnum_vectors_per_tokenの値が異なります: {len(embeddings)}"
|
||||
# print(token_ids, embeddings.size())
|
||||
for token_id, embedding in zip(token_ids, embeddings):
|
||||
token_embeds[token_id] = embedding
|
||||
# print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
|
||||
print(f"weighs loaded")
|
||||
|
||||
print(f"create embeddings for {args.num_vectors_per_token} tokens, for {args.token_string}")
|
||||
|
||||
# データセットを準備する
|
||||
blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, True, False))
|
||||
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", "reg_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:
|
||||
use_dreambooth_method = args.in_json is None
|
||||
if use_dreambooth_method:
|
||||
print("Use DreamBooth method.")
|
||||
user_config = {
|
||||
"datasets": [{
|
||||
"subsets": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)
|
||||
}]
|
||||
}
|
||||
# Convert the init_word to token_id
|
||||
if args.init_word is not None:
|
||||
init_token_ids = tokenizer.encode(args.init_word, add_special_tokens=False)
|
||||
if len(init_token_ids) > 1 and len(init_token_ids) != args.num_vectors_per_token:
|
||||
print(
|
||||
f"token length for init words is not same to num_vectors_per_token, init words is repeated or truncated / 初期化単語のトークン長がnum_vectors_per_tokenと合わないため、繰り返しまたは切り捨てが発生します: length {len(init_token_ids)}"
|
||||
)
|
||||
else:
|
||||
print("Train with captions.")
|
||||
user_config = {
|
||||
"datasets": [{
|
||||
"subsets": [{
|
||||
"image_dir": args.train_data_dir,
|
||||
"metadata_file": args.in_json,
|
||||
}]
|
||||
}]
|
||||
}
|
||||
init_token_ids = None
|
||||
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
# add new word to tokenizer, count is num_vectors_per_token
|
||||
token_strings = [args.token_string] + [f"{args.token_string}{i+1}" for i in range(args.num_vectors_per_token - 1)]
|
||||
num_added_tokens = tokenizer.add_tokens(token_strings)
|
||||
assert (
|
||||
num_added_tokens == args.num_vectors_per_token
|
||||
), f"tokenizer has same word to token string. please use another one / 指定したargs.token_stringは既に存在します。別の単語を使ってください: {args.token_string}"
|
||||
|
||||
# make captions: tokenstring tokenstring1 tokenstring2 ...tokenstringn という文字列に書き換える超乱暴な実装
|
||||
if use_template:
|
||||
print("use template for training captions. is object: {args.use_object_template}")
|
||||
templates = imagenet_templates_small if args.use_object_template else imagenet_style_templates_small
|
||||
replace_to = " ".join(token_strings)
|
||||
captions = []
|
||||
for tmpl in templates:
|
||||
captions.append(tmpl.format(replace_to))
|
||||
train_dataset_group.add_replacement("", captions)
|
||||
token_ids = tokenizer.convert_tokens_to_ids(token_strings)
|
||||
print(f"tokens are added: {token_ids}")
|
||||
assert min(token_ids) == token_ids[0] and token_ids[-1] == token_ids[0] + len(token_ids) - 1, f"token ids is not ordered"
|
||||
assert len(tokenizer) - 1 == token_ids[-1], f"token ids is not end of tokenize: {len(tokenizer)}"
|
||||
|
||||
if args.num_vectors_per_token > 1:
|
||||
prompt_replacement = (args.token_string, replace_to)
|
||||
# Resize the token embeddings as we are adding new special tokens to the tokenizer
|
||||
text_encoder.resize_token_embeddings(len(tokenizer))
|
||||
|
||||
# Initialise the newly added placeholder token with the embeddings of the initializer token
|
||||
token_embeds = text_encoder.get_input_embeddings().weight.data
|
||||
if init_token_ids is not None:
|
||||
for i, token_id in enumerate(token_ids):
|
||||
token_embeds[token_id] = token_embeds[init_token_ids[i % len(init_token_ids)]]
|
||||
# print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
|
||||
|
||||
# load weights
|
||||
if args.weights is not None:
|
||||
embeddings = load_weights(args.weights)
|
||||
assert len(token_ids) == len(
|
||||
embeddings
|
||||
), f"num_vectors_per_token is mismatch for weights / 指定した重みとnum_vectors_per_tokenの値が異なります: {len(embeddings)}"
|
||||
# print(token_ids, embeddings.size())
|
||||
for token_id, embedding in zip(token_ids, embeddings):
|
||||
token_embeds[token_id] = embedding
|
||||
# print(token_id, token_embeds[token_id].mean(), token_embeds[token_id].min())
|
||||
print(f"weighs loaded")
|
||||
|
||||
print(f"create embeddings for {args.num_vectors_per_token} tokens, for {args.token_string}")
|
||||
|
||||
# データセットを準備する
|
||||
blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, True, False))
|
||||
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", "reg_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:
|
||||
prompt_replacement = None
|
||||
else:
|
||||
if args.num_vectors_per_token > 1:
|
||||
replace_to = " ".join(token_strings)
|
||||
train_dataset_group.add_replacement(args.token_string, replace_to)
|
||||
prompt_replacement = (args.token_string, replace_to)
|
||||
else:
|
||||
prompt_replacement = None
|
||||
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group, show_input_ids=True)
|
||||
return
|
||||
if len(train_dataset_group) == 0:
|
||||
print("No data found. Please verify arguments / 画像がありません。引数指定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"
|
||||
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
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()
|
||||
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
trainable_params = text_encoder.get_input_embeddings().parameters()
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params)
|
||||
|
||||
# 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)
|
||||
|
||||
# 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}")
|
||||
|
||||
# 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)
|
||||
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
|
||||
text_encoder, optimizer, train_dataloader, lr_scheduler)
|
||||
|
||||
index_no_updates = torch.arange(len(tokenizer)) < token_ids[0]
|
||||
# print(len(index_no_updates), torch.sum(index_no_updates))
|
||||
orig_embeds_params = unwrap_model(text_encoder).get_input_embeddings().weight.data.detach().clone()
|
||||
|
||||
# Freeze all parameters except for the token embeddings in text encoder
|
||||
text_encoder.requires_grad_(True)
|
||||
text_encoder.text_model.encoder.requires_grad_(False)
|
||||
text_encoder.text_model.final_layer_norm.requires_grad_(False)
|
||||
text_encoder.text_model.embeddings.position_embedding.requires_grad_(False)
|
||||
# text_encoder.text_model.embeddings.token_embedding.requires_grad_(True)
|
||||
|
||||
unet.requires_grad_(False)
|
||||
unet.to(accelerator.device, dtype=weight_dtype)
|
||||
if args.gradient_checkpointing: # according to TI example in Diffusers, train is required
|
||||
unet.train()
|
||||
else:
|
||||
unet.eval()
|
||||
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
|
||||
# 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)
|
||||
text_encoder.to(weight_dtype)
|
||||
|
||||
# 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 train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
|
||||
print(f" num reg images / 正則化画像の数: {train_dataset_group.num_reg_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("textual_inversion")
|
||||
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
text_encoder.train()
|
||||
|
||||
loss_total = 0
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
with accelerator.accumulate(text_encoder):
|
||||
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]
|
||||
|
||||
# Get the text embedding for conditioning
|
||||
input_ids = batch["input_ids"].to(accelerator.device)
|
||||
# weight_dtype) use float instead of fp16/bf16 because text encoder is float
|
||||
encoder_hidden_states = train_util.get_hidden_states(args, input_ids, tokenizer, text_encoder, torch.float)
|
||||
|
||||
# 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)
|
||||
use_dreambooth_method = args.in_json is None
|
||||
if use_dreambooth_method:
|
||||
print("Use DreamBooth method.")
|
||||
user_config = {
|
||||
"datasets": [
|
||||
{"subsets": config_util.generate_dreambooth_subsets_config_by_subdirs(args.train_data_dir, args.reg_data_dir)}
|
||||
]
|
||||
}
|
||||
else:
|
||||
target = noise
|
||||
print("Train with captions.")
|
||||
user_config = {
|
||||
"datasets": [
|
||||
{
|
||||
"subsets": [
|
||||
{
|
||||
"image_dir": args.train_data_dir,
|
||||
"metadata_file": args.in_json,
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="none")
|
||||
loss = loss.mean([1, 2, 3])
|
||||
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
|
||||
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
|
||||
|
||||
loss_weights = batch["loss_weights"] # 各sampleごとのweight
|
||||
loss = loss * loss_weights
|
||||
# make captions: tokenstring tokenstring1 tokenstring2 ...tokenstringn という文字列に書き換える超乱暴な実装
|
||||
if use_template:
|
||||
print("use template for training captions. is object: {args.use_object_template}")
|
||||
templates = imagenet_templates_small if args.use_object_template else imagenet_style_templates_small
|
||||
replace_to = " ".join(token_strings)
|
||||
captions = []
|
||||
for tmpl in templates:
|
||||
captions.append(tmpl.format(replace_to))
|
||||
train_dataset_group.add_replacement("", captions)
|
||||
|
||||
loss = loss.mean() # 平均なのでbatch_sizeで割る必要なし
|
||||
if args.num_vectors_per_token > 1:
|
||||
prompt_replacement = (args.token_string, replace_to)
|
||||
else:
|
||||
prompt_replacement = None
|
||||
else:
|
||||
if args.num_vectors_per_token > 1:
|
||||
replace_to = " ".join(token_strings)
|
||||
train_dataset_group.add_replacement(args.token_string, replace_to)
|
||||
prompt_replacement = (args.token_string, replace_to)
|
||||
else:
|
||||
prompt_replacement = None
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
params_to_clip = text_encoder.get_input_embeddings().parameters()
|
||||
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
|
||||
if args.debug_dataset:
|
||||
train_util.debug_dataset(train_dataset_group, show_input_ids=True)
|
||||
return
|
||||
if len(train_dataset_group) == 0:
|
||||
print("No data found. Please verify arguments / 画像がありません。引数指定を確認してください")
|
||||
return
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
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"
|
||||
|
||||
# Let's make sure we don't update any embedding weights besides the newly added token
|
||||
# モデルに xformers とか memory efficient attention を組み込む
|
||||
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():
|
||||
unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = orig_embeds_params[index_no_updates]
|
||||
train_dataset_group.cache_latents(vae)
|
||||
vae.to("cpu")
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
gc.collect()
|
||||
|
||||
# Checks if the accelerator has performed an optimization step behind the scenes
|
||||
if accelerator.sync_gradients:
|
||||
progress_bar.update(1)
|
||||
global_step += 1
|
||||
if args.gradient_checkpointing:
|
||||
unet.enable_gradient_checkpointing()
|
||||
text_encoder.gradient_checkpointing_enable()
|
||||
|
||||
train_util.sample_images(accelerator, args, None, global_step, accelerator.device,
|
||||
vae, tokenizer, text_encoder, unet, prompt_replacement)
|
||||
# 学習に必要なクラスを準備する
|
||||
print("prepare optimizer, data loader etc.")
|
||||
trainable_params = text_encoder.get_input_embeddings().parameters()
|
||||
_, _, optimizer = train_util.get_optimizer(args, trainable_params)
|
||||
|
||||
current_loss = loss.detach().item()
|
||||
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)
|
||||
# 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,
|
||||
)
|
||||
|
||||
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)
|
||||
# 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}")
|
||||
|
||||
if global_step >= args.max_train_steps:
|
||||
break
|
||||
# lr schedulerを用意する
|
||||
lr_scheduler = train_util.get_scheduler_fix(args, optimizer, accelerator.num_processes)
|
||||
|
||||
if args.logging_dir is not None:
|
||||
logs = {"loss/epoch": loss_total / len(train_dataloader)}
|
||||
accelerator.log(logs, step=epoch+1)
|
||||
# acceleratorがなんかよろしくやってくれるらしい
|
||||
text_encoder, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
|
||||
text_encoder, optimizer, train_dataloader, lr_scheduler
|
||||
)
|
||||
|
||||
accelerator.wait_for_everyone()
|
||||
index_no_updates = torch.arange(len(tokenizer)) < token_ids[0]
|
||||
# print(len(index_no_updates), torch.sum(index_no_updates))
|
||||
orig_embeds_params = unwrap_model(text_encoder).get_input_embeddings().weight.data.detach().clone()
|
||||
|
||||
updated_embs = unwrap_model(text_encoder).get_input_embeddings().weight[token_ids].data.detach().clone()
|
||||
# Freeze all parameters except for the token embeddings in text encoder
|
||||
text_encoder.requires_grad_(True)
|
||||
text_encoder.text_model.encoder.requires_grad_(False)
|
||||
text_encoder.text_model.final_layer_norm.requires_grad_(False)
|
||||
text_encoder.text_model.embeddings.position_embedding.requires_grad_(False)
|
||||
# text_encoder.text_model.embeddings.token_embedding.requires_grad_(True)
|
||||
|
||||
if args.save_every_n_epochs is not None:
|
||||
model_name = train_util.DEFAULT_EPOCH_NAME if args.output_name is None else args.output_name
|
||||
unet.requires_grad_(False)
|
||||
unet.to(accelerator.device, dtype=weight_dtype)
|
||||
if args.gradient_checkpointing: # according to TI example in Diffusers, train is required
|
||||
unet.train()
|
||||
else:
|
||||
unet.eval()
|
||||
|
||||
def save_func():
|
||||
ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, epoch + 1) + '.' + args.save_model_as
|
||||
if not cache_latents:
|
||||
vae.requires_grad_(False)
|
||||
vae.eval()
|
||||
vae.to(accelerator.device, dtype=weight_dtype)
|
||||
|
||||
# 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)
|
||||
text_encoder.to(weight_dtype)
|
||||
|
||||
# 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 train images * repeats / 学習画像の数×繰り返し回数: {train_dataset_group.num_train_images}")
|
||||
print(f" num reg images / 正則化画像の数: {train_dataset_group.num_reg_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("textual_inversion")
|
||||
|
||||
for epoch in range(num_train_epochs):
|
||||
print(f"epoch {epoch+1}/{num_train_epochs}")
|
||||
train_dataset_group.set_current_epoch(epoch + 1)
|
||||
|
||||
text_encoder.train()
|
||||
|
||||
loss_total = 0
|
||||
for step, batch in enumerate(train_dataloader):
|
||||
with accelerator.accumulate(text_encoder):
|
||||
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]
|
||||
|
||||
# Get the text embedding for conditioning
|
||||
input_ids = batch["input_ids"].to(accelerator.device)
|
||||
# weight_dtype) use float instead of fp16/bf16 because text encoder is float
|
||||
encoder_hidden_states = train_util.get_hidden_states(args, input_ids, tokenizer, text_encoder, torch.float)
|
||||
|
||||
# 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="none")
|
||||
loss = loss.mean([1, 2, 3])
|
||||
|
||||
loss_weights = batch["loss_weights"] # 各sampleごとのweight
|
||||
loss = loss * loss_weights
|
||||
|
||||
loss = loss.mean() # 平均なのでbatch_sizeで割る必要なし
|
||||
|
||||
accelerator.backward(loss)
|
||||
if accelerator.sync_gradients and args.max_grad_norm != 0.0:
|
||||
params_to_clip = text_encoder.get_input_embeddings().parameters()
|
||||
accelerator.clip_grad_norm_(params_to_clip, args.max_grad_norm)
|
||||
|
||||
optimizer.step()
|
||||
lr_scheduler.step()
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
|
||||
# Let's make sure we don't update any embedding weights besides the newly added token
|
||||
with torch.no_grad():
|
||||
unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = orig_embeds_params[
|
||||
index_no_updates
|
||||
]
|
||||
|
||||
# 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, prompt_replacement
|
||||
)
|
||||
|
||||
current_loss = loss.detach().item()
|
||||
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)
|
||||
|
||||
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()
|
||||
|
||||
updated_embs = unwrap_model(text_encoder).get_input_embeddings().weight[token_ids].data.detach().clone()
|
||||
|
||||
if args.save_every_n_epochs is not None:
|
||||
model_name = train_util.DEFAULT_EPOCH_NAME if args.output_name is None else args.output_name
|
||||
|
||||
def save_func():
|
||||
ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, epoch + 1) + "." + args.save_model_as
|
||||
ckpt_file = os.path.join(args.output_dir, ckpt_name)
|
||||
print(f"saving checkpoint: {ckpt_file}")
|
||||
save_weights(ckpt_file, updated_embs, save_dtype)
|
||||
|
||||
def remove_old_func(old_epoch_no):
|
||||
old_ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, old_epoch_no) + "." + args.save_model_as
|
||||
old_ckpt_file = os.path.join(args.output_dir, old_ckpt_name)
|
||||
if os.path.exists(old_ckpt_file):
|
||||
print(f"removing old checkpoint: {old_ckpt_file}")
|
||||
os.remove(old_ckpt_file)
|
||||
|
||||
saving = train_util.save_on_epoch_end(args, save_func, remove_old_func, epoch + 1, num_train_epochs)
|
||||
if saving and args.save_state:
|
||||
train_util.save_state_on_epoch_end(args, accelerator, model_name, epoch + 1)
|
||||
|
||||
train_util.sample_images(
|
||||
accelerator, args, epoch + 1, global_step, accelerator.device, vae, tokenizer, text_encoder, unet, prompt_replacement
|
||||
)
|
||||
|
||||
# end of epoch
|
||||
|
||||
is_main_process = accelerator.is_main_process
|
||||
if is_main_process:
|
||||
text_encoder = unwrap_model(text_encoder)
|
||||
|
||||
accelerator.end_training()
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
|
||||
updated_embs = text_encoder.get_input_embeddings().weight[token_ids].data.detach().clone()
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
|
||||
if is_main_process:
|
||||
os.makedirs(args.output_dir, exist_ok=True)
|
||||
|
||||
model_name = train_util.DEFAULT_LAST_OUTPUT_NAME if args.output_name is None else args.output_name
|
||||
ckpt_name = model_name + "." + args.save_model_as
|
||||
ckpt_file = os.path.join(args.output_dir, ckpt_name)
|
||||
print(f"saving checkpoint: {ckpt_file}")
|
||||
|
||||
print(f"save trained model to {ckpt_file}")
|
||||
save_weights(ckpt_file, updated_embs, save_dtype)
|
||||
|
||||
def remove_old_func(old_epoch_no):
|
||||
old_ckpt_name = train_util.EPOCH_FILE_NAME.format(model_name, old_epoch_no) + '.' + args.save_model_as
|
||||
old_ckpt_file = os.path.join(args.output_dir, old_ckpt_name)
|
||||
if os.path.exists(old_ckpt_file):
|
||||
print(f"removing old checkpoint: {old_ckpt_file}")
|
||||
os.remove(old_ckpt_file)
|
||||
|
||||
saving = train_util.save_on_epoch_end(args, save_func, remove_old_func, epoch + 1, num_train_epochs)
|
||||
if saving and args.save_state:
|
||||
train_util.save_state_on_epoch_end(args, accelerator, model_name, epoch + 1)
|
||||
|
||||
train_util.sample_images(accelerator, args, epoch + 1, global_step, accelerator.device,
|
||||
vae, tokenizer, text_encoder, unet, prompt_replacement)
|
||||
|
||||
# end of epoch
|
||||
|
||||
is_main_process = accelerator.is_main_process
|
||||
if is_main_process:
|
||||
text_encoder = unwrap_model(text_encoder)
|
||||
|
||||
accelerator.end_training()
|
||||
|
||||
if args.save_state:
|
||||
train_util.save_state_on_train_end(args, accelerator)
|
||||
|
||||
updated_embs = text_encoder.get_input_embeddings().weight[token_ids].data.detach().clone()
|
||||
|
||||
del accelerator # この後メモリを使うのでこれは消す
|
||||
|
||||
if is_main_process:
|
||||
os.makedirs(args.output_dir, exist_ok=True)
|
||||
|
||||
model_name = train_util.DEFAULT_LAST_OUTPUT_NAME if args.output_name is None else args.output_name
|
||||
ckpt_name = model_name + '.' + args.save_model_as
|
||||
ckpt_file = os.path.join(args.output_dir, ckpt_name)
|
||||
|
||||
print(f"save trained model to {ckpt_file}")
|
||||
save_weights(ckpt_file, updated_embs, save_dtype)
|
||||
print("model saved.")
|
||||
print("model saved.")
|
||||
|
||||
|
||||
def save_weights(file, updated_embs, save_dtype):
|
||||
state_dict = {"emb_params": updated_embs}
|
||||
state_dict = {"emb_params": updated_embs}
|
||||
|
||||
if save_dtype is not None:
|
||||
for key in list(state_dict.keys()):
|
||||
v = state_dict[key]
|
||||
v = v.detach().clone().to("cpu").to(save_dtype)
|
||||
state_dict[key] = v
|
||||
if save_dtype is not None:
|
||||
for key in list(state_dict.keys()):
|
||||
v = state_dict[key]
|
||||
v = v.detach().clone().to("cpu").to(save_dtype)
|
||||
state_dict[key] = v
|
||||
|
||||
if os.path.splitext(file)[1] == '.safetensors':
|
||||
from safetensors.torch import save_file
|
||||
save_file(state_dict, file)
|
||||
else:
|
||||
torch.save(state_dict, file) # can be loaded in Web UI
|
||||
if os.path.splitext(file)[1] == ".safetensors":
|
||||
from safetensors.torch import save_file
|
||||
|
||||
save_file(state_dict, file)
|
||||
else:
|
||||
torch.save(state_dict, file) # can be loaded in Web UI
|
||||
|
||||
|
||||
def load_weights(file):
|
||||
if os.path.splitext(file)[1] == '.safetensors':
|
||||
from safetensors.torch import load_file
|
||||
data = load_file(file)
|
||||
else:
|
||||
# compatible to Web UI's file format
|
||||
data = torch.load(file, map_location='cpu')
|
||||
if type(data) != dict:
|
||||
raise ValueError(f"weight file is not dict / 重みファイルがdict形式ではありません: {file}")
|
||||
if os.path.splitext(file)[1] == ".safetensors":
|
||||
from safetensors.torch import load_file
|
||||
|
||||
if 'string_to_param' in data: # textual inversion embeddings
|
||||
data = data['string_to_param']
|
||||
if hasattr(data, '_parameters'): # support old PyTorch?
|
||||
data = getattr(data, '_parameters')
|
||||
data = load_file(file)
|
||||
else:
|
||||
# compatible to Web UI's file format
|
||||
data = torch.load(file, map_location="cpu")
|
||||
if type(data) != dict:
|
||||
raise ValueError(f"weight file is not dict / 重みファイルがdict形式ではありません: {file}")
|
||||
|
||||
emb = next(iter(data.values()))
|
||||
if type(emb) != torch.Tensor:
|
||||
raise ValueError(f"weight file does not contains Tensor / 重みファイルのデータがTensorではありません: {file}")
|
||||
if "string_to_param" in data: # textual inversion embeddings
|
||||
data = data["string_to_param"]
|
||||
if hasattr(data, "_parameters"): # support old PyTorch?
|
||||
data = getattr(data, "_parameters")
|
||||
|
||||
if len(emb.size()) == 1:
|
||||
emb = emb.unsqueeze(0)
|
||||
emb = next(iter(data.values()))
|
||||
if type(emb) != torch.Tensor:
|
||||
raise ValueError(f"weight file does not contains Tensor / 重みファイルのデータがTensorではありません: {file}")
|
||||
|
||||
return emb
|
||||
if len(emb.size()) == 1:
|
||||
emb = emb.unsqueeze(0)
|
||||
|
||||
return emb
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, True, True, False)
|
||||
train_util.add_training_arguments(parser, True)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
train_util.add_sd_models_arguments(parser)
|
||||
train_util.add_dataset_arguments(parser, True, True, False)
|
||||
train_util.add_training_arguments(parser, True)
|
||||
train_util.add_optimizer_arguments(parser)
|
||||
config_util.add_config_arguments(parser)
|
||||
|
||||
parser.add_argument("--save_model_as", type=str, default="pt", choices=[None, "ckpt", "pt", "safetensors"],
|
||||
help="format to save the model (default is .pt) / モデル保存時の形式（デフォルトはpt）")
|
||||
parser.add_argument(
|
||||
"--save_model_as",
|
||||
type=str,
|
||||
default="pt",
|
||||
choices=[None, "ckpt", "pt", "safetensors"],
|
||||
help="format to save the model (default is .pt) / モデル保存時の形式（デフォルトはpt）",
|
||||
)
|
||||
|
||||
parser.add_argument("--weights", type=str, default=None,
|
||||
help="embedding weights to initialize / 学習するネットワークの初期重み")
|
||||
parser.add_argument("--num_vectors_per_token", type=int, default=1,
|
||||
help='number of vectors per token / トークンに割り当てるembeddingsの要素数')
|
||||
parser.add_argument("--token_string", type=str, default=None,
|
||||
help="token string used in training, must not exist in tokenizer / 学習時に使用されるトークン文字列、tokenizerに存在しない文字であること")
|
||||
parser.add_argument("--init_word", type=str, default=None,
|
||||
help="words to initialize vector / ベクトルを初期化に使用する単語、複数可")
|
||||
parser.add_argument("--use_object_template", action='store_true',
|
||||
help="ignore caption and use default templates for object / キャプションは使わずデフォルトの物体用テンプレートで学習する")
|
||||
parser.add_argument("--use_style_template", action='store_true',
|
||||
help="ignore caption and use default templates for stype / キャプションは使わずデフォルトのスタイル用テンプレートで学習する")
|
||||
parser.add_argument("--weights", type=str, default=None, help="embedding weights to initialize / 学習するネットワークの初期重み")
|
||||
parser.add_argument(
|
||||
"--num_vectors_per_token", type=int, default=1, help="number of vectors per token / トークンに割り当てるembeddingsの要素数"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--token_string",
|
||||
type=str,
|
||||
default=None,
|
||||
help="token string used in training, must not exist in tokenizer / 学習時に使用されるトークン文字列、tokenizerに存在しない文字であること",
|
||||
)
|
||||
parser.add_argument("--init_word", type=str, default=None, help="words to initialize vector / ベクトルを初期化に使用する単語、複数可")
|
||||
parser.add_argument(
|
||||
"--use_object_template",
|
||||
action="store_true",
|
||||
help="ignore caption and use default templates for object / キャプションは使わずデフォルトの物体用テンプレートで学習する",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--use_style_template",
|
||||
action="store_true",
|
||||
help="ignore caption and use default templates for stype / キャプションは使わずデフォルトのスタイル用テンプレートで学習する",
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
train(args)
|
||||
args = parser.parse_args()
|
||||
args = train_util.read_config_from_file(args, parser)
|
||||
|
||||
train(args)
|
||||
|
||||
Reference in New Issue
Block a user