SuperK

Inference with different input shape

7

Hi , thanks for your work, I have trained one model with image size 256*256, I could get good results in samples, but when I test it with other input...

The FDDB result is lower than authors?

1

I found there is a gap between yours with author's result. Where is the trouble make this lower?

Could you please tell me where could i find labels.h?

Could I map a video to Euclidean space?

4

Is there any possible to use it in video retrieval？

Question about the weight of two losses

17

Hi , first of all , thanks for your share! I want to ask about that the weight of two losses, adv loss and content loss, how do you set...

关于模型的shape变换

2

hi，作者您好，我已经训练好了一版不错的模型，但是因为训练数据的尺寸都是256*256的，当我将模型的输入换为其他的尺寸时，效果会明显变差，您知道是什么原因吗？