Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix error on resume training #24

Merged
merged 2 commits into from
Sep 8, 2023
Merged

Fix error on resume training #24

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1791d92
Fix error on resume training: KeyError: "param 'initial_lr' is not sp…
Steve235lab Sep 8, 2023
82409e2
Merge branch 'dev' into fix-resume
Steve235lab Sep 8, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 17 additions & 21 deletions train_ms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,24 +172,20 @@ def run():
net_dur_disc = DDP(net_dur_disc, device_ids=[rank], find_unused_parameters=True)
try:
if net_dur_disc is not None:
_, _, _, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "DUR_*.pth"),
net_dur_disc,
optim_dur_disc,
skip_optimizer=True,
)
_, optim_g, _, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"),
net_g,
optim_g,
skip_optimizer=True,
)
_, optim_d, _, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"),
net_d,
optim_d,
skip_optimizer=True,
)
_, _, dur_resume_lr, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "DUR_*.pth"), net_dur_disc, optim_dur_disc,
skip_optimizer=True)
_, optim_g, g_resume_lr, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"), net_g,
optim_g, skip_optimizer=True)
_, optim_d, d_resume_lr, epoch_str = utils.load_checkpoint(
utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"), net_d,
optim_d, skip_optimizer=True)
if not optim_g.param_groups[0].get("initial_lr"):
optim_g.param_groups[0]["initial_lr"] = g_resume_lr
if not optim_d.param_groups[0].get("initial_lr"):
optim_d.param_groups[0]["initial_lr"] = d_resume_lr


epoch_str = max(epoch_str, 1)
global_step = (epoch_str - 1) * len(train_loader)
Expand All @@ -205,9 +201,9 @@ def run():
optim_d, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
)
if net_dur_disc is not None:
scheduler_dur_disc = torch.optim.lr_scheduler.ExponentialLR(
optim_dur_disc, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
)
if not optim_dur_disc.param_groups[0].get("initial_lr"):
optim_dur_disc.param_groups[0]["initial_lr"] = dur_resume_lr
scheduler_dur_disc = torch.optim.lr_scheduler.ExponentialLR(optim_dur_disc, gamma=hps.train.lr_decay, last_epoch=epoch_str-2)
else:
scheduler_dur_disc = None
scaler = GradScaler(enabled=hps.train.fp16_run)
Expand Down
Loading