search

daijifeng001 / MNC

Instance-aware Semantic Segmentation via Multi-task Network Cascades
Other
489 stars 182 forks source link

F0102 20:50:54.342540 4460 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory #32

Closed wolf943134497 closed 4 months ago

wolf943134497 commented 7 years ago

I0102 20:50:53.544600 4460 net.cpp:865] Ignoring source layer rpn_loss_bbox I0102 20:50:53.544636 4460 net.cpp:865] Ignoring source layer rpn_loss_cls I0102 20:50:53.544839 4460 net.cpp:865] Ignoring source layer seg_cls_score_ext_seg_cls_score_ext_0_split I0102 20:50:53.544852 4460 net.cpp:865] Ignoring source layer seg_cls_score_seg_cls_score_0_split


Demo for data/demo/2008_000533.jpg
F0102 20:50:54.342540  4460 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0)  out of memory
*** Check failure stack trace: ***
已放弃 (核心已转储)
I use  GPU has  8G of RAM(GTX 1070) .not use cuDNN .because cuDNN v5 not support .
The problem is solved by using cuDNN v4.
SamuelSJTU commented 7 years ago

I think it's not only cudnn v5 problem, py-faster-rcnn can solve the problem with cudnn v5 https://github.com/rbgirshick/py-faster-rcnn/issues/237 but still got the error , I have solve the problem by modifying the mnc_config.py (in MNC/lib) to reduce some number that will reduce the cost of GPU memory