caffe run lenet sample ,cuda unknown error

Accelerated Computing CUDA CUDA Programming and Performance
1

hi,guys:

system:ubuntu 16.04
nvidia driver 384.90
cuda 8.0

I run caffe samples /01-learning-lenet.ipynb with jupyter notebook,

while running the followwing sentence,the jupyter python kernel is broken and restart

caffe.set_device(0)
caffe.set_mode_gpu()

load the solver and create train and test nets

solver = None # ignore this workaround for lmdb data (can’t instantiate two solvers on the same data)
solver = caffe.SGDSolver(‘mnist/lenet_auto_solver.prototxt’)

[W 19:00:45.337 NotebookApp] Notebook examples/01-learning-lenet.ipynb is not trusted
WARNING: Logging before InitGoogleLogging() is written to STDERR
E1203 19:02:41.299633 12443 common.cpp:114] Cannot create Cublas handle. Cublas won’t be available.
F1203 19:02:41.361006 12443 benchmark.cpp:112] Check failed: error == cudaSuccess (30 vs. 0) unknown error
*** Check failure stack trace: ***

2