Check failed: (param_.workspace) >= (required_size)

ijkguo / mx-rcnn

Parallel Faster R-CNN implementation with MXNet.

Other

669 stars 292 forks source link

Check failed: (param_.workspace) >= (required_size) #28

Closed zhyj3038 closed 7 years ago

zhyj3038 commented 7 years ago

hello, I run mxrcnn , but itraise following error: /home/ubuntu/mxnet/dmlc-core/include/dmlc/logging.h:235: [10:48:17] src/operator/./convolution-inl.h:296: Check failed: (param.workspace) >= (required_size) Minimum workspace size: 1228800000 Bytes Given: 1073741824 Bytes

I decreased "workspce" paramter from in vgg16-symbol.json and "max_data_shape" in "train_rpn.py", also installed cudnn, but it seems nothing changes , would you please help me ?

ijkguo commented 7 years ago

Make sure mxnet is compiled with cudnn first. Don't modify workspace for convolution and max_data_shape.

zhyj3038 commented 7 years ago

problem solved wen install CUDNN properly, thanks a lot

alysazhang commented 7 years ago

Hi, sorry to disturber you. I have met the same problem, when I run demo.py on CPU. Could this be possible running on CPU?