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

capacitron training fixes #2086

Merged
merged 1 commit into from
Nov 1, 2022
+4 −4
Merged

capacitron training fixes #2086

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion TTS/tts/models/base_tts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ def get_data_loader(
loader = DataLoader(
dataset,
batch_size=config.eval_batch_size if is_eval else config.batch_size,
shuffle=False, # shuffle is done in the dataset.
shuffle=True, # if there is no other sampler
collate_fn=dataset.collate_fn,
drop_last=False, # setting this False might cause issues in AMP training.
sampler=sampler,
Expand Down
6 changes: 3 additions & 3 deletions TTS/utils/capacitron_optimizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,9 +38,9 @@ def step(self):
self.param_groups = self.primary_optimizer.param_groups
self.primary_optimizer.step()

def zero_grad(self):
self.primary_optimizer.zero_grad()
self.secondary_optimizer.zero_grad()
def zero_grad(self, set_to_none=False):
self.primary_optimizer.zero_grad(set_to_none)
self.secondary_optimizer.zero_grad(set_to_none)

def load_state_dict(self, state_dict):
self.primary_optimizer.load_state_dict(state_dict[0])
Expand Down