Van Huy

Sorry but I have no ideas. What environment did you run?

Please check out this issue https://github.com/tensorflow/tensorflow/issues/7778. Simply just ignore those warnings. If you set up your GPU correctly, TensorFlow will use it by default. You can check https://stackoverflow.com/questions/38009682/how-to-tell-if-tensorflow-is-using-gpu-acceleration-from-inside-python-shell to make...

I'm not sure about 2-channel pictures but you can try to convert them to 3-channels using PIL, OpenCV or ImageMagick then train CycleGAN as usual 🤔

You can look at https://github.com/vanhuyz/CycleGAN-TensorFlow/issues/17.

It seems ran out of memory. What is your environment? Do you train something else at the same time?

I haven't seen this issue before. Could you please give me more information about how to reproduce this issue? For example, your environment, what steps you did, your data information,...