nipponjo

Hello, you will most likely have to change the `utils.data.ArabDataset`, where the lists `train_phon.txt` or `test_phon.txt` are processed. The model takes a phonetic alphabet as input. The `text` module contain...

Using your image and mask I get this output when running test.py. That noise looks very unusual. With random weights, the model would fill with grey color. 

I just tested the weights from the link in the Readme and didn't have any problems with it https://drive.google.com/u/0/uc?id=1L63oBNVgz7xSb_3hGbUdkYW1IuRgMkCa&export=download

Hello, you can certainly adapt the model to take more or less than 3 image channels as input. I just added a few lines to `model/networks.py` to make this easier....

Hi, if you have other questions you can write them here.

Hello, I used the demo app to draw the masks in the examples/inpaint/ folder.

I'm not sure. By default, the weight files (e.g. states_tf_places2.pth) need to be put into the pretrained/ folder. The path to the files can be changed in app/models.yaml.

It seem like PS saves the channels in a different order, so that `mask = mask[0:1, :h//grid*grid, :w//grid*grid].unsqueeze(0)` (e.g., in `test.py`) should be changed to `mask = mask[3:4, :h//grid*grid, :w//grid*grid].unsqueeze(0)`...

Hello, I think the binary images cause some difficulties. Firstly, I would extend the output range of the generator so that it can more easily output the -1/1 values. You...

Hello, it is hard to know exactly when to stop, so I would mostly look at the results. In the paper, the learning rate is not lowered and I think...