Jae Hyun Lim

Hi! I hope you @AjayTalati are still having interests in implementing DRAW. I'm having trouble with understanding the selective attention model in DRAW. I'm not sure here is the write...

Thanks a lot @AjayTalati I think I get it :) Jaehyun Lim

@alexgkendall Thank you for your reply! 1. I used the models in the link (http://mi.eng.cam.ac.uk/~agk34/resources/PoseNet.zip); thus, the betas are set as follows; - King's College: 500 - Old Hospital: 1000...

Hi Alex, Thank you for reply :) I did use the pretrained model for the googlenet. Best regards, Jaehyun Lim

@alykhantejani > Hi @lim0606 - did you manage to reproduce results with SGD? Yes and no... I did only for King's College data (see https://github.com/lim0606/caffe-posenet-googlenet) I think I have to...

What I ment was that the model was trained with the index order in 15's devkit instead of caffe repo. (The labes are the same) Sorry for ambiguous expressions. Best...

@szagoruyko Thank you for your kind response. It seems really helpful! I will look into it. Best regards, Jaehyun Lim

Thanks @deartonym! I had the same problem, and solved by 1) adding variable `MATLAB_INCLUDE := ./MATLAB/R2014a/toolbox/distcomp/gpu/extern/include` and 2) changing `INCLUDE_DIRS := ...` as `INCLUDE_DIRS := $(PYTHON_INCLUDE) $(MATLAB_INCLUDE) /usr/local/include` in `Makefile.config`