search

mousecpn / L2A-OT

This repository is an unofficial implementation in PyTorch for Learning to Generate Novel Domains for Domain Generalization
22 stars 4 forks source link

about C.tar and D.tar #7

Open lypliuyouping opened 5 months ago

lypliuyouping commented 5 months ago

Hello, I read your paper carefully and the idea is great, but I don’t understand part of the source code, which is about loading D.tar and C.tar. What do these two refer to? If I want to train myself data, do you want to change these two? I look forward to your reply, thank you!

mousecpn commented 5 months ago

Hi, actually this is not my paper. I just re-implemented it. I don't quite remember what C.tar and D.tar for. It seems it is the checkpoint of GAN. So you probably don't need to change it.

lypliuyouping commented 5 months ago

Okay, thank you very much for your answer. What do the c_init function, d_init, and dgc_init function in the code mean? My basic knowledge is not very good. Thank you for your guidance.

mousecpn commented 5 months ago

I don't really remember. It has been so long ago. From the code, it seems that they are all loading pretrained resnet18 checkpoint. But regarding their specific function in the code, I have no clue now.