Merge branch 'dev' into dev_device_support

sdxl_train_control_net_lllite_old.py

@@ -39,6 +39,12 @@ from library.custom_train_functions import (
     apply_debiased_estimation,
 )
 import networks.control_net_lllite as control_net_lllite
+from library.utils import setup_logging, add_logging_arguments
+
+setup_logging()
+import logging
+
+logger = logging.getLogger(__name__)
 
 
 # TODO 他のスクリプトと共通化する
@@ -72,11 +78,11 @@ def train(args):
     # データセットを準備する
     blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, False, True, True))
     if use_user_config:
-        print(f"Load dataset config from {args.dataset_config}")
+        logger.info(f"Load dataset config from {args.dataset_config}")
         user_config = config_util.load_user_config(args.dataset_config)
         ignored = ["train_data_dir", "conditioning_data_dir"]
         if any(getattr(args, attr) is not None for attr in ignored):
-            print(
+            logger.warning(
                 "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)
                 )
@@ -108,7 +114,7 @@ def train(args):
         train_util.debug_dataset(train_dataset_group)
         return
     if len(train_dataset_group) == 0:
-        print(
+        logger.error(
             "No data found. Please verify arguments (train_data_dir must be the parent of folders with images) / 画像がありません。引数指定を確認してください（train_data_dirには画像があるフォルダではなく、画像があるフォルダの親フォルダを指定する必要があります）"
         )
         return
@@ -118,7 +124,9 @@ def train(args):
             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"
     else:
-        print("WARNING: random_crop is not supported yet for ControlNet training / ControlNetの学習ではrandom_cropはまだサポートされていません")
+        logger.warning(
+            "WARNING: random_crop is not supported yet for ControlNet training / ControlNetの学習ではrandom_cropはまだサポートされていません"
+        )
 
     if args.cache_text_encoder_outputs:
         assert (
@@ -126,7 +134,7 @@ def train(args):
         ), "when caching Text Encoder output, either caption_dropout_rate, shuffle_caption, token_warmup_step or caption_tag_dropout_rate cannot be used / Text Encoderの出力をキャッシュするときはcaption_dropout_rate, shuffle_caption, token_warmup_step, caption_tag_dropout_rateは使えません"
 
     # acceleratorを準備する
-    print("prepare accelerator")
+    logger.info("prepare accelerator")
     accelerator = train_util.prepare_accelerator(args)
     is_main_process = accelerator.is_main_process
 
@@ -195,8 +203,8 @@ def train(args):
     accelerator.print("prepare optimizer, data loader etc.")
 
     trainable_params = list(network.prepare_optimizer_params())
-    print(f"trainable params count: {len(trainable_params)}")
-    print(f"number of trainable parameters: {sum(p.numel() for p in trainable_params if p.requires_grad)}")
+    logger.info(f"trainable params count: {len(trainable_params)}")
+    logger.info(f"number of trainable parameters: {sum(p.numel() for p in trainable_params if p.requires_grad)}")
 
     _, _, optimizer = train_util.get_optimizer(args, trainable_params)
 
@@ -218,7 +226,9 @@ def train(args):
         args.max_train_steps = args.max_train_epochs * math.ceil(
             len(train_dataloader) / accelerator.num_processes / args.gradient_accumulation_steps
         )
-        accelerator.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}")
+        accelerator.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}"
+        )
 
     # データセット側にも学習ステップを送信
     train_dataset_group.set_max_train_steps(args.max_train_steps)
@@ -291,8 +301,10 @@ def train(args):
     accelerator.print(f"  num reg images / 正則化画像の数: {train_dataset_group.num_reg_images}")
     accelerator.print(f"  num batches per epoch / 1epochのバッチ数: {len(train_dataloader)}")
     accelerator.print(f"  num epochs / epoch数: {num_train_epochs}")
-    accelerator.print(f"  batch size per device / バッチサイズ: {', '.join([str(d.batch_size) for d in train_dataset_group.datasets])}")
-    # 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}")
+    accelerator.print(
+        f"  batch size per device / バッチサイズ: {', '.join([str(d.batch_size) for d in train_dataset_group.datasets])}"
+    )
+    # logger.info(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}")
     accelerator.print(f"  gradient accumulation steps / 勾配を合計するステップ数 = {args.gradient_accumulation_steps}")
     accelerator.print(f"  total optimization steps / 学習ステップ数: {args.max_train_steps}")
 
@@ -511,12 +523,13 @@ def train(args):
         ckpt_name = train_util.get_last_ckpt_name(args, "." + args.save_model_as)
         save_model(ckpt_name, network, global_step, num_train_epochs, force_sync_upload=True)
 
-        print("model saved.")
+        logger.info("model saved.")
 
 
 def setup_parser() -> argparse.ArgumentParser:
     parser = argparse.ArgumentParser()
 
+    add_logging_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)
@@ -532,8 +545,12 @@ def setup_parser() -> argparse.ArgumentParser:
         choices=[None, "ckpt", "pt", "safetensors"],
         help="format to save the model (default is .safetensors) / モデル保存時の形式（デフォルトはsafetensors）",
     )
-    parser.add_argument("--cond_emb_dim", type=int, default=None, help="conditioning embedding dimension / 条件付け埋め込みの次元数")
-    parser.add_argument("--network_weights", type=str, default=None, help="pretrained weights for network / 学習するネットワークの初期重み")
+    parser.add_argument(
+        "--cond_emb_dim", type=int, default=None, help="conditioning embedding dimension / 条件付け埋め込みの次元数"
+    )
+    parser.add_argument(
+        "--network_weights", type=str, default=None, help="pretrained weights for network / 学習するネットワークの初期重み"
+    )
     parser.add_argument("--network_dim", type=int, default=None, help="network dimensions (rank) / モジュールの次元数")
     parser.add_argument(
         "--network_dropout",