Skip to content

Fix resumed model training for Multi-GPUs #64

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix resumed model training for Multi-GPUs #64

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 10 additions & 12 deletions guided_diffusion/train_util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,13 +112,12 @@ def _load_and_sync_parameters(self):

if resume_checkpoint:
self.resume_step = parse_resume_step_from_filename(resume_checkpoint)
if dist.get_rank() == 0:
logger.log(f"loading model from checkpoint: {resume_checkpoint}...")
self.model.load_state_dict(
dist_util.load_state_dict(
resume_checkpoint, map_location=dist_util.dev()
)
logger.log(f"loading model from checkpoint: {resume_checkpoint}...")
self.model.load_state_dict(
dist_util.load_state_dict(
resume_checkpoint, map_location=dist_util.dev()
)
)

dist_util.sync_params(self.model.parameters())

Expand All @@ -128,12 +127,11 @@ def _load_ema_parameters(self, rate):
main_checkpoint = find_resume_checkpoint() or self.resume_checkpoint
ema_checkpoint = find_ema_checkpoint(main_checkpoint, self.resume_step, rate)
if ema_checkpoint:
if dist.get_rank() == 0:
logger.log(f"loading EMA from checkpoint: {ema_checkpoint}...")
state_dict = dist_util.load_state_dict(
ema_checkpoint, map_location=dist_util.dev()
)
ema_params = self.mp_trainer.state_dict_to_master_params(state_dict)
logger.log(f"loading EMA from checkpoint: {ema_checkpoint}...")
state_dict = dist_util.load_state_dict(
ema_checkpoint, map_location=dist_util.dev()
)
ema_params = self.mp_trainer.state_dict_to_master_params(state_dict)

dist_util.sync_params(ema_params)
return ema_params
Expand Down