Fast rcnn训练报错:Check failed: data_ *** Check failure stack trace: *** Aborted (core dumped)

环境: Ubuntu16.04 + GTX960M(4G显存) + cuda8.0 + cudnn 7.1.4 for cuda8
用./tools/train_net.py --gpu 0 --solver models/VGG16/solver.prototxt --weights data/imagenet_models/VGG16.v2.caffemodel命令训练Fast rcnn,报错:
 
I0920 20:45:58.371701 24994 net.cpp:270] This network produces output loss_bbox
I0920 20:45:58.371706 24994 net.cpp:270] This network produces output loss_cls
I0920 20:45:58.371732 24994 net.cpp:283] Network initialization done.
I0920 20:45:58.371904 24994 solver.cpp:60] Solver scaffolding done.
Loading pretrained model weights from data/imagenet_models/VGG_CNN_M_1024.v2.caffemodel
I0920 20:45:58.620015 24994 net.cpp:816] Ignoring source layer pool5
I0920 20:45:58.679762 24994 net.cpp:816] Ignoring source layer fc8
I0920 20:45:58.679782 24994 net.cpp:816] Ignoring source layer prob
Solving...
F0920 20:45:59.169987 24994 blob.cpp:95] Check failed: data_ 
*** Check failure stack trace: ***
Aborted (core dumped)

 
截图如下:

QQ截图20180920211238.jpg

 
有人遇到过这个问题吗?谢谢
 
已邀请:

要回复问题请先登录注册