Jun-Yan Zhu

See `test.py` and this line is loading the model: ```python model = create_model(opt) ```

Thanks for the reply. It follows the pix2pix directory structure rather than CycleGAN's.

There are two choices: (1) predicts a vector z (2) predicts the mean and variance of multi-variate Gaussian, and sample the latent vector using the predicted mean/variance., as done in...

For your question 1 and 3: (1) predict a single vector for cLR-GAN and (2) predict Gaussian mean/variance for cVAE-GAN. In cLR-GAN, we calculate the L1 loss between the sampled...

We don't want the generator and encoder to cooperate and cheat. It is likely that the generator can produce a hidden signal and encoder can decode it. Therefore, we only...

I updated it with 7ef3acd. Could you give a try?

You should use `--model pix2pix` or `--model bicycle_gan`. This script is mostly for development. Please refer to [README](https://github.com/junyanz/BicycleGAN#use-a-pre-trained-model) on how to test a pre-trained model.

I haven't seen the errors in 1 before and I am not sure about what happened. For your question 2, note that ```python self.fake_B_random = self.netG(self.real_A_encoded, self.z_random) ``` fake_B_random is...

I was able to reproduce your error 1 now. It didn't happen for the previous PyTorch version. I fixed it with the latest [commit](https://github.com/junyanz/BicycleGAN/commit/6f0eec8ef0a147a80f64f25103089feb33553a06).

Yes. You are correct. I updated the code with a new [commit](https://github.com/junyanz/BicycleGAN/commit/8dc078bde7889fcaff246cf97c0b97a0e0e9ce87). I set `self.set_requires_grad([self.netE], False)` before `self.backward_G_alone()`. I assume this will disabling computing graidents for E while we backprop...