fix duplicated sample gen for every epoch ref #907

train_controlnet.py

@@ -11,10 +11,13 @@ import toml
 
 from tqdm import tqdm
 import torch
+
 try:
     import intel_extension_for_pytorch as ipex
+
     if torch.xpu.is_available():
         from library.ipex import ipex_init
+
         ipex_init()
 except Exception:
     pass
@@ -335,7 +338,9 @@ def train(args):
         init_kwargs = {}
         if args.log_tracker_config is not None:
             init_kwargs = toml.load(args.log_tracker_config)
-        accelerator.init_trackers("controlnet_train" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs)
+        accelerator.init_trackers(
+            "controlnet_train" if args.log_tracker_name is None else args.log_tracker_name, init_kwargs=init_kwargs
+        )
 
     loss_recorder = train_util.LossRecorder()
     del train_dataset_group
@@ -371,22 +376,13 @@ def train(args):
             accelerator.print(f"removing old checkpoint: {old_ckpt_file}")
             os.remove(old_ckpt_file)
 
+    # For --sample_at_first
+    train_util.sample_images(
+        accelerator, args, 0, global_step, accelerator.device, vae, tokenizer, text_encoder, unet, controlnet=controlnet
+    )
+
     # training loop
     for epoch in range(num_train_epochs):
-        # For --sample_at_first
-        train_util.sample_images(
-            accelerator,
-            args,
-            epoch,
-            global_step,
-            accelerator.device,
-            vae,
-            tokenizer,
-            text_encoder,
-            unet,
-            controlnet=controlnet,
-        )
-
         if is_main_process:
             accelerator.print(f"\nepoch {epoch+1}/{num_train_epochs}")
         current_epoch.value = epoch + 1