No need to change caffe.proto ?

xingyizhou / DeepModel

Code repository for Model-based Deep Hand Pose Estimation

GNU General Public License v3.0

111 stars 43 forks source link

No need to change caffe.proto ? #7

Closed davidsonic closed 7 years ago

davidsonic commented 7 years ago

What's confusing me is that you have added a new loss layer to caffe, and registered it. Is there no need to change caffe.proto?

davidsonic commented 7 years ago

And when running python demo.py in the directory of testing, I got "Check failed, registry.count(type)==1 (0 vs 1) Unknown layer type: DeepHandModel"

xingyizhou commented 7 years ago

Hi davidsonic, Since our layer does not require specific layer parameters, there is no need to change caffe.proto. For the Unknown layer type Error, it seems you haven't set up the code successfully, please make sure you have followed the instruction and set the pycaffe_root correctly.

davidsonic commented 7 years ago

Thanks, I tried either adding the definitions into caffe.proto and without. It turned out that both would work. Any way thank you for your reply.