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.

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

value about Temperature #1

Open
coallar opened this issue Jun 20, 2022 · 1 comment
Open

value about Temperature #1

coallar opened this issue Jun 20, 2022 · 1 comment

Comments

@coallar
Copy link

coallar commented Jun 20, 2022

Hi, I have a problem about: what is the valu of T or self.tau do you have choiced? or How can i set the value while training my project?
T = self.tau
# taken from https://github.com/peterliht/knowledge-distillation-pytorch/blob/master/model/net.py#L100
# with slight modifications
distillation_loss = F.kl_div(
F.log_softmax(outputs_kd / T, dim=1),
F.log_softmax(teacher_outputs / T, dim=1),
reduction='sum',
log_target=True
) * (T * T) / outputs_kd.numel()

@soroush-abbasi
Copy link
Collaborator

Hi,

We don't use any teacher or distillation loss during training. We train all models from scratch without any teacher. Please let me know if you have any questions. Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants