Giters

LTH14 / mage

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about applying to my own dataset

mabaisen opened this issue · comments

commented

Hello, i want to use my own galaxy dataset, which is completely different from ImageNet. Should I retrain VQGAN from scratch.

J000000 80+004200 0
256

commented

Yes you need to re-train the VQGAN -- the provided VQGAN checkpoint is pre-trained on ImageNet-1K, which does not include galaxy images. Unfortunately, we cannot release the code for VQGAN training, but the original VQGAN code should give reasonable performance.

commented

Yes you need to re-train the VQGAN -- the provided VQGAN checkpoint is pre-trained on ImageNet-1K, which does not include galaxy images. Unfortunately, we cannot release the code for VQGAN training, but the original VQGAN code should give reasonable performance.

Ok, thank you very much for your answer.