Do the number of images in trainA and trainB need to be the same?

taki0112 / UGATIT

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)

MIT License

6.17k stars 1.05k forks source link

Do the number of images in trainA and trainB need to be the same? #90

Open muziyongshixin opened 4 years ago

muziyongshixin commented 4 years ago

I create a dataset by myself, but the number of samples in trainA and trainB are different, I have read the code. And it seems that it to be okay to handle this situation, but I wonder if this will affect the final result？

dragen1860 commented 4 years ago

this is un-paired fashion. it can be absolutely different.