Open zwxdxcm opened 11 months ago
I mean ... If you wanna train neural field from scratch, it is reasonable to implementing E2E compression, which should use QAT. For pre-trained model, it would be better to use PTQ.
Sorry for the confusion. You are right, and we were incorrectly written. Thank you.
Sorry for the confusion. You are right, and we were incorrectly written. Thank you.
Thanks for your reply. Double check, so this work implement QAT since it trains network from scratch. Have you compare how many time spent on the additional computations during both training and inference?
And I also have another 2 questions.
Thank you !
Oh i understand it seems like a threshold function. but why would you use stop gradient operator?
Thank you for your interest in our work.
OK. Thanks ~~
For what I understood, the masking part is more like a learnable frequency filter, am I correct?
It is not necessarily a frequency filter. The masking method itself can filter whatever you want. For example, if you apply the masking method to spatial grids, it filters spacial coefficients. If you apply it to frequency grids (after DCT), you get frequency filters.
Thanks for your reply !
I am wondering if this description is correct? Why there is not QAT in blue highlight?
Thanks!