About the training of models applied to 256*256 resolution images

[greywarden]

Thank you for sharing your wonderful work. We would like to use your model as a baseline, but due to the difference in training settings, the direct application of the model parameters you provided to 256256 images would not yield particularly good results. So we would like to train a TFill for a 256256 image version, can you give us some advice on the training settings regarding the model?

[Chuanxia Zheng]

Hi @ScarletBlaze, you can directly use the coarse results in the first stage for $256\times256$ resolution, which provide high qualitative results for both object removal and foreground completion.

[1997Jessie]

Hi @ScarletBlaze, you can directly use the coarse results in the first stage for 256×256 resolution, which provide high qualitative results for both object removal and foreground completion.

Hi,@lyndonzheng ,I wanna train images about 1024*768 resolution ,I don't know about revising --load_size、 --fine_size and --fixed_size to make training best

[1997Jessie]

Hi @ScarletBlaze, you can directly use the coarse results in the first stage for 256×256 resolution, which provide high qualitative results for both object removal and foreground completion.

Looking forward to your reply~