Ru Wang

I modified the prototxt according to the comments under this issue. The only difference is that my batchsize is 10, and the loss does not converge and it explodes. I...

@anatolix Thanks, but I'm still confused about whether the vector field has something to do with the area of limbs?And where can I find in the code?

Thank you very much for the excellent example! I will explan my question with your picture.  Take the vector field on the arm for example. My question is that...

Thank you very much! One last question (actually more than one), are all the training data masked by mask_all or mask_miss before going through the network and the masked part...

You mean, for the vgg layers at the beginning of the network, they use the masked pictures, and after these layers they use original pictures? I'm really confused about the...

I am also trying to do this. I deleted all the 'L1' layers and 'vec' layers in the prototxt, and I want to use single-person data to train it. But...

Thanks for your reply! Now I want to implement the demo on VS2015, but your version of caffe doesn't support Win well. Installing caffe on VS is really frustrating and...

I add some of your layers in caffe-win, and try as I might, I cannot run VGG_SSD model successfully. But fortunately I can run shg+sstn model with a bounding box...