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