tongxueqing issues

Repositories
Issues
Comments

Results 2 issues of


                                            tongxueqing

Why delete the sigmoid in the output layers?

Thanks for your wonderful work. I wonder why you delete the sigmoid in the output layers in DenseNet.py in the latter version? And I guess it will be reasonable if...

Question about SMPL tracking

Thanks for you wonderful open-source work! How do you do SMPL tracking to initialize? Why the initial shape parameter is not learnable but the pose per frame is learnable?