VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 22:35:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor selection and logging for DAdaptation

Browse Source
This commit is contained in:
Kohya S
2023-05-06 18:14:16 +09:00
parent 164a1978de
commit 2127907dd3
6 changed files with 28 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
train_network.py
View File

@@ -43,7 +43,7 @@ def generate_step_logs(args: argparse.Namespace, current_loss, avr_loss, lr_sche
logs["lr/textencoder"] = float(lrs[0])
logs["lr/unet"] = float(lrs[-1]) # may be same to textencoder
if args.optimizer_type.lower() == "DAdaptation".lower() or args.optimizer_type.lower() == "DAdaptAdam".lower() or args.optimizer_type.lower() == "DAdaptAdaGrad".lower() or args.optimizer_type.lower() == "DAdaptAdan".lower() or args.optimizer_type.lower() == "DAdaptSGD".lower(): # tracking d*lr value of unet.
if args.optimizer_type.lower().startswith("DAdapt".lower()): # tracking d*lr value of unet.
logs["lr/d*lr"] = lr_scheduler.optimizers[-1].param_groups[0]["d"] * lr_scheduler.optimizers[-1].param_groups[0]["lr"]
else:
idx = 0
@@ -53,7 +53,7 @@ def generate_step_logs(args: argparse.Namespace, current_loss, avr_loss, lr_sche
for i in range(idx, len(lrs)):
logs[f"lr/group{i}"] = float(lrs[i])
if args.optimizer_type.lower() == "DAdaptation".lower() or args.optimizer_type.lower() == "DAdaptAdam".lower() or args.optimizer_type.lower() == "DAdaptAdaGrad".lower() or args.optimizer_type.lower() == "DAdaptAdan".lower() or args.optimizer_type.lower() == "DAdaptSGD".lower():
if args.optimizer_type.lower().startswith("DAdapt".lower()):
logs[f"lr/d*lr/group{i}"] = (
lr_scheduler.optimizers[-1].param_groups[i]["d"] * lr_scheduler.optimizers[-1].param_groups[i]["lr"]
)
@@ -277,7 +277,7 @@ def train(args):
else:
unet.eval()
text_encoder.eval()
network.prepare_grad_etc(text_encoder, unet)
if not cache_latents:
@@ -713,7 +713,7 @@ def train(args):
if is_main_process:
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.")