convolutional-pose-machines-release
convolutional-pose-machines-release copied to clipboard
How is "intermediate supervision" implemented?
How is "intermediate supervision" implemented? My understanding is that the eq. 5 is the equation that enforce the intermediate supervision. However, when I look at the prototxt, I found no clue of eq.5 inside.
Could anyone please explain for me?
I also have the problem,I don't know how to intermediate supervision, in prototxt every stage just have loss_ for themselves.