Merge branch 'dev' into dev_device_support

sdxl_train.py

@@ -18,6 +18,14 @@ from diffusers import DDPMScheduler
 from library import sdxl_model_util
 
 import library.train_util as train_util
+
+from library.utils import setup_logging, add_logging_arguments
+
+setup_logging()
+import logging
+
+logger = logging.getLogger(__name__)
+
 import library.config_util as config_util
 import library.sdxl_train_util as sdxl_train_util
 from library.config_util import (
@@ -90,7 +98,9 @@ def train(args):
     train_util.prepare_dataset_args(args, True)
     sdxl_train_util.verify_sdxl_training_args(args)
 
-    assert not args.weighted_captions, "weighted_captions is not supported currently / weighted_captionsは現在サポートされていません"
+    assert (
+        not args.weighted_captions
+    ), "weighted_captions is not supported currently / weighted_captionsは現在サポートされていません"
     assert (
         not args.train_text_encoder or not args.cache_text_encoder_outputs
     ), "cache_text_encoder_outputs is not supported when training text encoder / text encoderを学習するときはcache_text_encoder_outputsはサポートされていません"
@@ -115,18 +125,18 @@ def train(args):
     if args.dataset_class is None:
         blueprint_generator = BlueprintGenerator(ConfigSanitizer(True, True, False, True))
         if args.dataset_config is not None:
-            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", "in_json"]
             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)
                     )
                 )
         else:
             if use_dreambooth_method:
-                print("Using DreamBooth method.")
+                logger.info("Using DreamBooth method.")
                 user_config = {
                     "datasets": [
                         {
@@ -137,7 +147,7 @@ def train(args):
                     ]
                 }
             else:
-                print("Training with captions.")
+                logger.info("Training with captions.")
                 user_config = {
                     "datasets": [
                         {
@@ -167,7 +177,7 @@ def train(args):
         train_util.debug_dataset(train_dataset_group, True)
         return
     if len(train_dataset_group) == 0:
-        print(
+        logger.error(
             "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
@@ -183,7 +193,7 @@ 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)
 
     # mixed precisionに対応した型を用意しておき適宜castする
@@ -359,7 +369,9 @@ 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)
@@ -428,7 +440,9 @@ def train(args):
     accelerator.print(f"  num examples / サンプル数: {train_dataset_group.num_train_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])}")
+    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])}"
+    )
     # accelerator.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}"
     # )
@@ -448,7 +462,7 @@ def train(args):
     if accelerator.is_main_process:
         init_kwargs = {}
         if args.wandb_run_name:
-            init_kwargs['wandb'] = {'name': args.wandb_run_name}
+            init_kwargs["wandb"] = {"name": args.wandb_run_name}
         if args.log_tracker_config is not None:
             init_kwargs = toml.load(args.log_tracker_config)
         accelerator.init_trackers("finetuning" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs)
@@ -532,7 +546,7 @@ def train(args):
                     # assert ((encoder_hidden_states1.to("cpu") - ehs1.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
                     # assert ((encoder_hidden_states2.to("cpu") - ehs2.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
                     # assert ((pool2.to("cpu") - p2.to(dtype=weight_dtype)).abs().max() > 1e-2).sum() <= b_size * 2
-                    # print("text encoder outputs verified")
+                    # logger.info("text encoder outputs verified")
 
                 # get size embeddings
                 orig_size = batch["original_sizes_hw"]
@@ -719,12 +733,13 @@ def train(args):
             logit_scale,
             ckpt_info,
         )
-        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, True, True, True)
     train_util.add_training_arguments(parser, False)
@@ -747,7 +762,9 @@ def setup_parser() -> argparse.ArgumentParser:
         help="learning rate for text encoder 2 (BiG-G) / text encoder 2 (BiG-G)の学習率",
     )
 
-    parser.add_argument("--diffusers_xformers", action="store_true", help="use xformers by diffusers / Diffusersでxformersを使用する")
+    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")
     parser.add_argument(
         "--no_half_vae",