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

Why loss function value is too high? Is it expecteted result? #41

Open

padeirocarlos opened this issue Jan 6, 2024 · 0 comments

padeirocarlos commented Jan 6, 2024

I tried running your code for with a pre-trained ResNet50 and MobilieNetV2 model. I got loss function value for output and pred losses:

rec_loss = lp_loss(pred, tgt, p=self.p)
:param pred: output from quantized model
:param tgt: output from FP model
https://github.com/yhhhli/BRECQ/blob/main/quant/block_recon.py#L149

pd_loss = self.pd_loss(F.log_softmax(output / self.T, dim=1), F.softmax(output_fp / self.T, dim=1)) / self.lam
:param pred: output from quantized model
:param tgt: output from FP model
https://github.com/yhhhli/BRECQ/blob/main/quant/block_recon.py#L151

Are there additional settings I missed?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment