These are chat archives for BVLC/caffe

Aug 2015
Eren Golge
Aug 21 2015 13:02
Hi guys! Do you think I need to increase my batch size in model file if I use multiple GPU or caffe handles it automatically ?
Eren Golge
Aug 21 2015 13:38
Parallelism: the -gpu flag to the caffe tool can take a comma separated list of IDs to run on multiple GPUs. A solver and net will be instantiated for each GPU so the batch size is effectively multiplied by the number of GPUs. To reproduce single GPU training, reduce the batch size in the network definition accordingly.
Aug 21 2015 16:38
I'm trying to run caffe for the first time, following the github tutorial, and after running "python python/ --printresults examples/images/cat.jpg foo" I get a "TypeError: _init() got an unexpected keyword argument 'mean_file'"
I'm not sure how best to go about fixing this- thanks!