Could you give me some little experience that why you choice **178** for the celebA dataset drop size?

[Matt-V50]

Here I can see you add a comment.

https://github.com/Xiefan-Guo/CTSDG/blob/def02741ba1a110e70ee1a6365868e5d43731132/datasets/transform.py#L9

Maybe you have some special reason for that, cause other size will not generate nice result.

And that will be helpful for me.

[xiefan-guo]

Hi, we follow the experimental settings of EdgeConnect. For CelebA, we cropped the center 178x178 of the images, then resized them to 256x256 using bilinear interpolation.

[Matt-V50]

Hi, we follow the experimental settings of EdgeConnect. For CelebA, we cropped the center 178x178 of the images, then resized them to 256x256 using bilinear interpolation.

Thanks a lot, by the way, this setting seems to have a big impact on the results.

Maybe this is a little tips for others.

[01SHENyankun]

您好，我们遵循EdgeConnect的实验设置。对于 CelebA，我们裁剪了图像的中心 178x178，然后使用双线性插值将它们调整为 256x256。

非常感谢，顺便说一下，这个设置似乎对结果有很大的影响。

也许这是对其他人的一些提示。

你好，有些问题想向您请教，能否给个联系方式，我的qq：2635505974