Closed terrychenism closed 8 years ago
Thanks for your contribution! We will run some tests and let you know if anything needs to be changed. :)
Couple of notes:
lr_mult
, decay_mult
, and bias_filler
during training, so there's no need to include them in the prototxt for training. (and, lr_mult
, decay_mult
, bias_filler
are for weight initialization and weight updates during training, but I don't think they have any affect during inference.)weight initialization xavier
lines.Good suggestions, I have updated the deploy file
deploy.prototxt added