richard Li
richard Li
> The transformation of the face. 3DDFA_V2 adopts the scale orthographic projection. what is the difference between the scale orthographic projection and the weak perspective projection?
@RickyZ92 hi,你好，请问你的问题解决了吗？我现在也在参考https://github.com/AITTSMD/MTCNN-Tensorflow 训练mtcnn，生成了三个三个网络的checkpoint文件，想请教你如何将三个checkpoint文件合并成一个pb文件
@hhaAndroid any expected date? or time frame?
@Fang-Haoshu I trained alphapose in halpe 136 dataset, but the MAP is worse than the pretrained_model(halpe136_fast_res50_256x192.path),Are there any details to pay attention to？and could you shard the train log ?
I also want this database,someone can share?
> 我是去看了作者的示例项目，跟着示例写了写代码 @xys20071111 示例项目代码指的是哪个？
> > > 我是去看了作者的示例项目，跟着示例写了写代码 > > > > > > @xys20071111 示例项目代码指的是哪个？ > > [这个](https://glitch.com/edit/#!/kalidokit) 里面的script.js 谢谢，我现在在研究虚拟人驱动以及AR方向，有联系方式方便后续交流吗
bbox coordinates:[cx cy w h] reference line 156 in mpt.py. I can not understand ``` cx, cy, h = bbox[:,0], bbox[:,1], bbox[:,2] why not: cx, cy, w,h = bbox[:,0], bbox[:,1],...