Fromandto
Fromandto
@hszhao I am training a 713 resolution pspnet on 2 x 12gb titan x with batch size 1, and it seems almost all memories are used. So I guess training...
@huaxinxiao yes, this is exactly what i am concerned ... but I just don't have 32 gpus (or is there anything wrong with my setting so that 4 gpus are...
@suhyung I am using the training script of deeplab-v2. it is compatible.
It seems that your matlab is a windows version ?
I believe evaluation @ 473 resolution consumes < 12gb memory If you don't have a gpu of 12gb memory, maybe you can further reduce resolution to ~300 (like 321) remember...
@rener1199 if input resolution is 473, then conv5_3_pool1/2/3/6_interp resolution is 60 60 * 8 = 480 ~= 473 that's the rule (with 7 pixels mismatch caused by padding/striding) 640 /...
successfully compiled caffe_3d on 14.04
@shurans I am trapped by this new bug cudnn.hpp:145] Check failed: status == CUDNN_STATUS_SUCCESS (3 vs. 0) CUDNN_STATUS_BAD_PARAM I am using cudnn v5 and cuda-7.5 according to this thread: https://groups.google.com/forum/#!topic/caffe-users/89E0Ci3jjm4...
I finally got it running. Using ubuntu 14.04, cudnn-v5 and cuda-8.0. It seems that using ubuntu 16.04, cudnn-v5.1 or cuda-7.5 will all cause hard-to-hack compatibility bugs.