Hardware Used for training

[TheRed002]

I recently came across posenet and tried to experiment with it. I modified the original architecture of posenet and now my input layer size is 1x100x224x224x3 where 1 is the batch size and 100 are the frames. Actually I have implemented lstm version of posenet. Now I have tried to run training on my own data, first on gtx750 and then on quadro k1200 4 GB gpu with tensorflow backend for keras(i am using posenet,written in keras) and also tried theano backend but everytime I get "out of memory" error. I want to ask what hardware specs your computer had on which you ran your training?
About Data: I have around 6000 png images for training

[ghost]

I think the authors mentioned the GPU they used in the paper as NVidia Titan Black. By the way, so can change the c++ code in caffe/caffe-posenet and print out the required memory and other information to understand your problem in a clear way.

[DRAhmadFaraz]

@TheRed002 sorry for bothering you, Well I also get this issue.. "out of memory" as shown.
have you solved this problem.?

@zhuoruiyang How to configure our device according to it.? I have GTX 940 4GB Nvidia GPU....

[ghost]

Hi Ahmad, I think your hardware may not be powerful enough to run the posenet with the default setting. The best thing you can do with what you have now is to reduce the batch size, try to reduce the size by half each time and see if your GPU has sufficient memory for it. When I ran it two years ago, I used the GeForce 1080 which has 8Gb memory. If reducing the batch size doesn’t work, I guess you need to get a more powerful GPU for the job. Good luck with your work! Please let me know if there is anything I can help. Also, emailing the author of the paper may get more useful information.

On Sat, Apr 27, 2019 at 10:15 Ahmad Faraz Khan ***@***.***> wrote: @TheRed002 <https://github.com/TheRed002> sorry for bothering you, Well I also get this issue.. "out of memory" as shown. have you solved this problem.? [image: Screenshot from 2019-04-27 20-44-59] <https://user-images.githubusercontent.com/38114191/56852826-6c261c00-6939-11e9-95a8-3a1c91e44772.png> @zhuoruiyang <https://github.com/zhuoruiyang> How to configure our device according to it.? I have GTX 940 4GB Nvidia GPU.... — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#17 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AB2BO3WDC46N2UM2H3ZJGEDPSSCZPANCNFSM4DJNW35A> .

-- Sent from Gmail Mobile