-
Notifications
You must be signed in to change notification settings - Fork 1.9k
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.
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
[TTS]Avoid using variable "attn_loss" before assignment #2860
Conversation
@@ -113,16 +113,18 @@ def update_core(self, batch): | |||
loss.backward() | |||
optimizer.step() | |||
|
|||
if self.use_guided_attn_loss: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
good job ! Maybe you should also fix this for class Tacotron2Evaluator
@@ -113,16 +113,18 @@ def update_core(self, batch): | |||
loss.backward() | |||
optimizer.step() | |||
|
|||
if self.use_guided_attn_loss: | |||
report("eval/attn_loss", float(attn_loss)) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should be train/attn_loss here
I have directly pushed to your branch to fix some bugs @hopingZ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR types
PR changes
Describe