XiaoYangon

Hello，I have question：When there is a person or only one significant target in the image , the effect of generating any size ratio image is not true. such as zebra...

about mask

2

Hi，I have a question，I find mask_type is " pconv" and "square", Is the mask of pre_trained model square or pconv?

Pretrained model

2

hello , thanks for releaseing the pretrained model . I download the model of places2 data，then run test.py to see the results in places2 val data, other paramers are unchanged，but...

about ATNConv

2

Hi , I have a question. in the ATNConv module, the patches of high level feature map are got with stride 1，Is the calculation too large in conv，your gpu config？，Can...

The wrong results

1

Hello, thank you very much for the code. Now,I use celeba-hq data to train model. In the program, according to the parameter opt.display_freq, the intermediate results can be displayed. However,...

Train error

1

hello，I'm very sorry to disturb you. I use my data to train model, but Training process has a error： Exception in thread Thread-1: Traceback (most recent call last): File "/usr/local/python3/lib/python3.6/threading.py",...

Thanks for your excellent work! I have some question. In the dataloader.py ： mask = 1 - mask inputImage = groundTruth * mask here，Dose zeros denotes the area to be...

Joint font style and text effect transfer

3

Hello, your project is really meaningful. In the paper, you mention jointfont style and text effect transfer? how can this be realized? Looking forward to your reply.