scale v-pred loss like noise pred

train_textual_inversion.py

@@ -20,7 +20,13 @@ from library.config_util import (
     BlueprintGenerator,
 )
 import library.custom_train_functions as custom_train_functions
-from library.custom_train_functions import apply_snr_weight, pyramid_noise_like, apply_noise_offset
+from library.custom_train_functions import (
+    apply_snr_weight,
+    prepare_scheduler_for_custom_training,
+    pyramid_noise_like,
+    apply_noise_offset,
+    scale_v_prediction_loss_like_noise_prediction,
+)
 
 imagenet_templates_small = [
     "a photo of a {}",
@@ -338,6 +344,7 @@ def train(args):
     noise_scheduler = DDPMScheduler(
         beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", num_train_timesteps=1000, clip_sample=False
     )
+    prepare_scheduler_for_custom_training(noise_scheduler, accelerator.device)
 
     if accelerator.is_main_process:
         accelerator.init_trackers("textual_inversion" if args.log_tracker_name is None else args.log_tracker_name)
@@ -412,12 +419,14 @@ def train(args):
                 loss = torch.nn.functional.mse_loss(noise_pred.float(), target.float(), reduction="none")
                 loss = loss.mean([1, 2, 3])
 
-                if args.min_snr_gamma:
-                    loss = apply_snr_weight(loss, timesteps, noise_scheduler, args.min_snr_gamma)
-
                 loss_weights = batch["loss_weights"]  # 各sampleごとのweight
                 loss = loss * loss_weights
 
+                if args.min_snr_gamma:
+                    loss = apply_snr_weight(loss, timesteps, noise_scheduler, args.min_snr_gamma)
+                if args.scale_v_pred_loss_like_noise_pred:
+                    loss = scale_v_prediction_loss_like_noise_prediction(loss, timesteps, noise_scheduler)
+
                 loss = loss.mean()  # 平均なのでbatch_sizeで割る必要なし
 
                 accelerator.backward(loss)