I'm beginning to study and implement GAN to generate more datasets. I'll just try to experiment with state-of-the-art GAN models as described here https://paperswithcode.com/sota/image-generation-on-cifar-10.

The problem is I don't have a big dataset (around 1.000) for image classification, I have tried to train and test my dataset with GoogleNet and InceptionV3 and the results are mediocre. I'm afraid that GAN will require a bigger dataset than the usual image classification. I couldn't find any detailed guideline of how to prepare datasets properly for GAN (e.g. minimum images).

So, how many images are required to produce a good GAN model?

Also, I'm curious whether if I can use my image classification dataset directly to train GAN.

  • $\begingroup$ Have the same question. Did u solve it now? Thanks $\endgroup$
    – Tao Chen
    Jul 30, 2020 at 2:20
  • $\begingroup$ @TaoChen I trained it using 1500 images only, there's no specific guideline for that I think $\endgroup$
    – gameon67
    Jul 30, 2020 at 7:59
  • $\begingroup$ @gameon67 Was it successful training? Did yo use augmentation and does it really help? I have similar dataset around 1500 images and I wonder If it should be extended? $\endgroup$ Aug 31, 2021 at 6:54


You must log in to answer this question.