Jun-Yan Zhu

I recommend that you use a semantic segmentation [network](https://github.com/CSAILVision/semantic-segmentation-pytorch) for your task. GANs sometimes struggle when the task's output is discrete,

Have you checked if the data loader reads these maps correctly? Another sanity check is to disable GAN loss and only use L1 loss, and see if you can reasonable...

Sorry for the late reply. It's a little hard to know what's going on without seeing your images and results. You may want to have a close look at the...

This is not normal. Could you first try to train a pix2pix model on a given dataset (e.g. facades) and then try to adapt it to your own dataset? Also...

hmm, it's hard to tell without seeing the data and tasks. Could you try batchSize 1 with 1 GPU?

For grayscale images, you need to use the flag `-input_nc 1 --output_nc`. You can directly use `combine_A_and_B` for the original images. During training time, you can use different `--preprocessing` flags...

It happens when the transformation is difficult to learn or two domains look drastically different. Not sure if reducing the learning rate will help in your case. I will try...

@duke023456 It is hard for CycleGAN to preserve the text in an image. If you can detect the text using an OCR method, you can try to preserve them using...

You can detect the region that contains the text using an OCR detection method, and add a loss function to preserve the pixels within the region.

You are right. The current code does not save the optimizer parameters. You probably have to modify the code.