When doing inference, why we use paired image in pix2pix?

[ghost]

HI,

I am following the tutorial of Pix2Pix. In the tutorial, when doing inference, the input is "image_path = 'tests/data/paired/test/3.jpg', which is a paired image.

Then I began to train Pix2Pix using our own dataset, after the training, when we input paired image, the result is pretty good, however, when we input only the domain A image, the translated B fake image have different result. In real life inference, we do not have the ground truth along side with the input image. My question is why we use Paired image as the input in the tutorial?

When input is paired image:

When input is unpaired image:

As a further question, can we train pix2pix using unpaired methods?

Thanks Tao