Creating try_on dataset

[HSinger04]

• Things to optimize – prefer generator code: Simple to write and memory-efficient. And maybe try_on doesn‘t need long to train
  • Speed
  • Memory
• What the dataset should look like
  • Returns: latent_p, latent_g, seg_p, seg_g

[HSinger04]

Note: While it makes sense to pre-label images, it doesn't lead to the segmenter not being needed in the training step anymore, since the segmenter also needs to be used for try_on images.