longpeng2008
math_functions.cu:123] Check failed: status == CUBLAS_STATUS_SUCCESS (11 vs. 0) CUBLAS_STATUS_MAPPING_ERROR could you provide the script for generating lmdb dataset, I encountered this problem after a sleep, and I don't know...
[type BatchNorm]' not found [type Scale]' not found [type Eltwise]' not found hello，when can you add the support?
using the default everything, the loss can not converge at all.
your python script solver.py is OK。 But when using c++ interface for train, it will failed as follow， Check failed: error == cudaSuccess (77 vs. 0)
/include/caffe/vision_layers.hpp:361:14: error: ‘PowerLayer’ was not declared in this scope shared_ptr square_layer_; so many errors there.
In file included from ./include/caffe/vision_layers.hpp:10:0, from src/caffe/layers/pooling_switches_layer.cpp:9: ./include/caffe/common_layers.hpp:10:33: caffe/data_layers.hpp: No such file or directory.
hello, thanks for your work, I found the code you provided cannot produce the correct synthetic dataset in the paper, the pixels are blurred everywhere, is there anything wrong?
when test examples: test.py ./include/cudarray/common.hpp:95 an illegal memory access was encountered, my enviroument is ubuntu 15.04 and GTM980, actually I don't know where to set CUDNN_ENABLED, so I just replace...
"dot" not found in path，whats the problem?