search

jwyang / lr-gan.pytorch

Pytorch code for our ICLR 2017 paper "Layered-Recursive GAN for image generation"
151 stars 32 forks source link

How to reproduce the Category specific models in 5.4? #9

Open EnQing626 opened 6 years ago

EnQing626 commented 6 years ago

Hi @jwyang , I'm very impressed by your work and very thanks for your publication code. I have few questions about part 5.4 about how to train the Category specific models:

  1. Did you insert the catogory label into z before inputing the LSTM？
  2. Did you put the catogory label as the input of the Discrimitor together with the input image(fake and real)?

Could you please give me some advice? Thanks a lot.