Van Huy

Input data images may have different size but at the moment they have to be square.

The behavior of `tf.image.convert_image_dtype` is quite confusing. When I called this, it returned [0.0, 255.0] instead of [0.0, 1.0]. There is an issue related to it: https://github.com/tensorflow/tensorflow/issues/1763 As you point...

@irfanICMLL after training, you can export model from checkpoint using `export_graph.py` script as described in https://github.com/vanhuyz/CycleGAN-TensorFlow/blob/master/README.md#export-model. After that, you can use the model to transfer images as https://github.com/vanhuyz/CycleGAN-TensorFlow/blob/master/README.md#inference. You can...

Sure! What kind of test do you want?

Yes, I used the test set for that purpose too. The `inference.py` script can be used to generate an image from testA. To convert a whole directory, we need to...

Hi Ross, I've checked your code. It looks like you try to create many different graphs in the loop, and each graph only does inference for 1 image. https://github.com/rosswendt/CycleGAN-TensorFlow/blob/batched_inference/inference.py#L46 I...

You mean input is RGB and output is grayscale?

Are all the images the same size?

Thanks for reporting! At the moment, my implementation can't work with images which are not square. The size of fake images are specified as in https://github.com/vanhuyz/CycleGAN-TensorFlow/blob/master/model.py#L58-L61. This should be fixed...

There is no max-iterations in the code. Your must stop the training progress by hand by pressing Ctrl+C. Please check out this issue https://github.com/vanhuyz/CycleGAN-TensorFlow/issues/45. Maybe I should have included this...