kekedan

do you solve the problem ？i meet the same issue

> hello professor, i don't know it exactly what is the two input: > x: (n, 2) image points > X_ind: (n,) corresponding Model vertex indices > is x just...

> Here is the [checkpoint](https://yadi.sk/d/6vqE41BTZKIAKQ), I did not compute all the metrics for this one. But it should be similar to the ones reported in the paper. thank you！

同学，不知道不实现没有，三个定位是用于当前batch的。 有个问题想想你请教下，在论文中Mask是为了用于求导，使用tensorflow相当于是自动求导的，感觉好像并不需要这个，不知道你是怎么实现的，能否交流下，谢谢。